@alicloud/aidge20260428 5.12.2 → 5.14.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/client.d.ts +774 -630
- package/dist/client.js +863 -630
- package/dist/client.js.map +1 -1
- package/dist/models/AddDisplayKnowledgeResponseBody.d.ts +3 -0
- package/dist/models/AddDisplayKnowledgeResponseBody.js.map +1 -1
- package/dist/models/AiTryOnRequest.d.ts +65 -8
- package/dist/models/AiTryOnRequest.js +10 -0
- package/dist/models/AiTryOnRequest.js.map +1 -1
- package/dist/models/AiTryOnResponseBody.d.ts +8 -8
- package/dist/models/CategoryAttributeMatchResponseBody.d.ts +3 -0
- package/dist/models/CategoryAttributeMatchResponseBody.js.map +1 -1
- package/dist/models/DeleteDisplayKnowledgeResponseBody.d.ts +3 -0
- package/dist/models/DeleteDisplayKnowledgeResponseBody.js.map +1 -1
- package/dist/models/DocumentTranslateRequest.d.ts +10 -7
- package/dist/models/DocumentTranslateRequest.js.map +1 -1
- package/dist/models/DocumentTranslateResponseBody.d.ts +3 -3
- package/dist/models/EcomVideoRecreationRequest.d.ts +11 -17
- package/dist/models/EcomVideoRecreationRequest.js.map +1 -1
- package/dist/models/EcomVideoRecreationResponseBody.d.ts +3 -3
- package/dist/models/EcomVideoRecreationShrinkRequest.d.ts +2 -2
- package/dist/models/GeneralRephotographyDetectionResponseBody.d.ts +4 -4
- package/dist/models/GenerateProductContentRequest.d.ts +11 -13
- package/dist/models/GenerateProductContentRequest.js.map +1 -1
- package/dist/models/GenerateProductContentResponseBody.d.ts +9 -7
- package/dist/models/GenerateProductContentResponseBody.js.map +1 -1
- package/dist/models/ImageMattingAsyncRequest.d.ts +1 -1
- package/dist/models/ImageMattingAsyncResponseBody.d.ts +2 -2
- package/dist/models/ImageRecognitionAsyncRequest.d.ts +14 -11
- package/dist/models/ImageRecognitionAsyncRequest.js.map +1 -1
- package/dist/models/ImageRecognitionAsyncResponseBody.d.ts +5 -5
- package/dist/models/ImageRecognitionAsyncShrinkRequest.d.ts +14 -11
- package/dist/models/ImageRecognitionAsyncShrinkRequest.js.map +1 -1
- package/dist/models/ImageRemovalProAsyncRequest.d.ts +1 -1
- package/dist/models/ImageRemovalProAsyncResponseBody.d.ts +5 -7
- package/dist/models/ImageRemovalProAsyncResponseBody.js.map +1 -1
- package/dist/models/ImageRemovalProResponseBody.d.ts +3 -0
- package/dist/models/ImageRemovalProResponseBody.js.map +1 -1
- package/dist/models/ImageRemoveAsyncRequest.d.ts +19 -8
- package/dist/models/ImageRemoveAsyncRequest.js.map +1 -1
- package/dist/models/ImageRemoveAsyncResponseBody.d.ts +8 -6
- package/dist/models/ImageRemoveAsyncResponseBody.js.map +1 -1
- package/dist/models/ImageRemoveAsyncShrinkRequest.d.ts +19 -8
- package/dist/models/ImageRemoveAsyncShrinkRequest.js.map +1 -1
- package/dist/models/ImageTranslationPlusAsyncRequest.d.ts +11 -11
- package/dist/models/ImageTranslationPlusAsyncResponseBody.d.ts +4 -4
- package/dist/models/ImageTranslationProAsyncRequest.d.ts +5 -5
- package/dist/models/ImageTranslationProAsyncResponseBody.d.ts +1 -1
- package/dist/models/ImageTranslationStandardAsyncRequest.d.ts +1 -1
- package/dist/models/ImageTranslationStandardAsyncResponseBody.d.ts +3 -3
- package/dist/models/ImageTranslationStandardRequest.d.ts +4 -4
- package/dist/models/ImageTranslationStandardResponseBody.d.ts +10 -10
- package/dist/models/ImageUpscaleRequest.d.ts +1 -1
- package/dist/models/ImageUpscaleResponseBody.d.ts +7 -7
- package/dist/models/MaterialInspectionRequest.d.ts +4 -4
- package/dist/models/MaterialInspectionResponseBody.d.ts +9 -9
- package/dist/models/MerchandisePlacementDetectionLiteResponseBody.d.ts +15 -12
- package/dist/models/MerchandisePlacementDetectionLiteResponseBody.js.map +1 -1
- package/dist/models/MerchandisePlacementDetectionProRequest.d.ts +5 -5
- package/dist/models/MerchandisePlacementDetectionProResponseBody.d.ts +6 -6
- package/dist/models/MerchandisePlacementDetectionRequest.d.ts +7 -7
- package/dist/models/MerchandisePlacementDetectionResponseBody.d.ts +19 -19
- package/dist/models/MerchandisePriceTagDetectionRequest.d.ts +1 -1
- package/dist/models/MerchandisePriceTagDetectionResponseBody.d.ts +11 -11
- package/dist/models/MerchandiseSceneDetectionRequest.d.ts +1 -1
- package/dist/models/MerchandiseSceneDetectionResponseBody.d.ts +16 -10
- package/dist/models/MerchandiseSceneDetectionResponseBody.js.map +1 -1
- package/dist/models/MilkPowderCanBottomCodeRephotographyDetectionResponseBody.d.ts +7 -7
- package/dist/models/MilkPowderCartonCodeRephotographyDetectionResponseBody.d.ts +12 -9
- package/dist/models/MilkPowderCartonCodeRephotographyDetectionResponseBody.js.map +1 -1
- package/dist/models/PrepaidTextTranslateRequest.d.ts +8 -8
- package/dist/models/PrepaidTextTranslateResponseBody.d.ts +11 -8
- package/dist/models/PrepaidTextTranslateResponseBody.js.map +1 -1
- package/dist/models/PrepaidTextTranslateShrinkRequest.d.ts +8 -8
- package/dist/models/ProductVideoGenerationRequest.d.ts +62 -0
- package/dist/models/ProductVideoGenerationRequest.js +71 -0
- package/dist/models/ProductVideoGenerationRequest.js.map +1 -0
- package/dist/models/ProductVideoGenerationResponse.d.ts +19 -0
- package/dist/models/ProductVideoGenerationResponse.js +69 -0
- package/dist/models/ProductVideoGenerationResponse.js.map +1 -0
- package/dist/models/ProductVideoGenerationResponseBody.d.ts +86 -0
- package/dist/models/ProductVideoGenerationResponseBody.js +92 -0
- package/dist/models/ProductVideoGenerationResponseBody.js.map +1 -0
- package/dist/models/ProductVideoGenerationShrinkRequest.d.ts +62 -0
- package/dist/models/ProductVideoGenerationShrinkRequest.js +68 -0
- package/dist/models/ProductVideoGenerationShrinkRequest.js.map +1 -0
- package/dist/models/QueryDisplayKnowledgeResponseBody.d.ts +3 -0
- package/dist/models/QueryDisplayKnowledgeResponseBody.js.map +1 -1
- package/dist/models/SizeChartExtractAsyncRequest.d.ts +3 -3
- package/dist/models/SizeChartExtractAsyncResponseBody.d.ts +7 -5
- package/dist/models/SizeChartExtractAsyncResponseBody.js.map +1 -1
- package/dist/models/SizeChartExtractAsyncShrinkRequest.d.ts +3 -3
- package/dist/models/StorefrontSceneRecognitionRequest.d.ts +1 -1
- package/dist/models/StorefrontSceneRecognitionResponseBody.d.ts +9 -6
- package/dist/models/StorefrontSceneRecognitionResponseBody.js.map +1 -1
- package/dist/models/SubmitProductMatchRequest.d.ts +8 -8
- package/dist/models/SubmitProductMatchResponseBody.d.ts +7 -7
- package/dist/models/TextTranslateAsyncRequest.d.ts +9 -9
- package/dist/models/TextTranslateAsyncResponseBody.d.ts +6 -6
- package/dist/models/TextTranslateAsyncShrinkRequest.d.ts +9 -9
- package/dist/models/UpdateDisplayKnowledgeResponseBody.d.ts +3 -0
- package/dist/models/UpdateDisplayKnowledgeResponseBody.js.map +1 -1
- package/dist/models/VacancyDetectionRequest.d.ts +39 -0
- package/dist/models/VacancyDetectionRequest.js +62 -0
- package/dist/models/VacancyDetectionRequest.js.map +1 -0
- package/dist/models/VacancyDetectionResponse.d.ts +19 -0
- package/dist/models/VacancyDetectionResponse.js +69 -0
- package/dist/models/VacancyDetectionResponse.js.map +1 -0
- package/dist/models/VacancyDetectionResponseBody.d.ts +83 -0
- package/dist/models/VacancyDetectionResponseBody.js +93 -0
- package/dist/models/VacancyDetectionResponseBody.js.map +1 -0
- package/dist/models/VideoGenerationRequest.d.ts +18 -17
- package/dist/models/VideoGenerationRequest.js.map +1 -1
- package/dist/models/VideoGenerationResponseBody.d.ts +2 -2
- package/dist/models/VideoTranslationRequest.d.ts +8 -17
- package/dist/models/VideoTranslationRequest.js.map +1 -1
- package/dist/models/VideoTranslationResponseBody.d.ts +4 -6
- package/dist/models/VideoTranslationResponseBody.js.map +1 -1
- package/dist/models/VideoTranslationShrinkRequest.d.ts +8 -17
- package/dist/models/VideoTranslationShrinkRequest.js.map +1 -1
- package/dist/models/VirtualTryOnResponseBody.d.ts +7 -6
- package/dist/models/VirtualTryOnResponseBody.js.map +1 -1
- package/dist/models/model.d.ts +9 -0
- package/dist/models/model.js +23 -5
- package/dist/models/model.js.map +1 -1
- package/package.json +1 -1
- package/src/client.ts +882 -630
- package/src/models/AddDisplayKnowledgeResponseBody.ts +3 -0
- package/src/models/AiTryOnRequest.ts +75 -8
- package/src/models/AiTryOnResponseBody.ts +8 -8
- package/src/models/CategoryAttributeMatchResponseBody.ts +3 -0
- package/src/models/DeleteDisplayKnowledgeResponseBody.ts +3 -0
- package/src/models/DocumentTranslateRequest.ts +10 -7
- package/src/models/DocumentTranslateResponseBody.ts +3 -3
- package/src/models/EcomVideoRecreationRequest.ts +11 -17
- package/src/models/EcomVideoRecreationResponseBody.ts +3 -3
- package/src/models/EcomVideoRecreationShrinkRequest.ts +2 -2
- package/src/models/GeneralRephotographyDetectionResponseBody.ts +4 -4
- package/src/models/GenerateProductContentRequest.ts +11 -13
- package/src/models/GenerateProductContentResponseBody.ts +9 -7
- package/src/models/ImageMattingAsyncRequest.ts +1 -1
- package/src/models/ImageMattingAsyncResponseBody.ts +2 -2
- package/src/models/ImageRecognitionAsyncRequest.ts +14 -11
- package/src/models/ImageRecognitionAsyncResponseBody.ts +5 -5
- package/src/models/ImageRecognitionAsyncShrinkRequest.ts +14 -11
- package/src/models/ImageRemovalProAsyncRequest.ts +1 -1
- package/src/models/ImageRemovalProAsyncResponseBody.ts +5 -7
- package/src/models/ImageRemovalProResponseBody.ts +3 -0
- package/src/models/ImageRemoveAsyncRequest.ts +19 -8
- package/src/models/ImageRemoveAsyncResponseBody.ts +8 -6
- package/src/models/ImageRemoveAsyncShrinkRequest.ts +19 -8
- package/src/models/ImageTranslationPlusAsyncRequest.ts +11 -11
- package/src/models/ImageTranslationPlusAsyncResponseBody.ts +4 -4
- package/src/models/ImageTranslationProAsyncRequest.ts +5 -5
- package/src/models/ImageTranslationProAsyncResponseBody.ts +1 -1
- package/src/models/ImageTranslationStandardAsyncRequest.ts +1 -1
- package/src/models/ImageTranslationStandardAsyncResponseBody.ts +3 -3
- package/src/models/ImageTranslationStandardRequest.ts +4 -4
- package/src/models/ImageTranslationStandardResponseBody.ts +10 -10
- package/src/models/ImageUpscaleRequest.ts +1 -1
- package/src/models/ImageUpscaleResponseBody.ts +7 -7
- package/src/models/MaterialInspectionRequest.ts +4 -4
- package/src/models/MaterialInspectionResponseBody.ts +9 -9
- package/src/models/MerchandisePlacementDetectionLiteResponseBody.ts +15 -12
- package/src/models/MerchandisePlacementDetectionProRequest.ts +5 -5
- package/src/models/MerchandisePlacementDetectionProResponseBody.ts +6 -6
- package/src/models/MerchandisePlacementDetectionRequest.ts +7 -7
- package/src/models/MerchandisePlacementDetectionResponseBody.ts +19 -19
- package/src/models/MerchandisePriceTagDetectionRequest.ts +1 -1
- package/src/models/MerchandisePriceTagDetectionResponseBody.ts +11 -11
- package/src/models/MerchandiseSceneDetectionRequest.ts +1 -1
- package/src/models/MerchandiseSceneDetectionResponseBody.ts +16 -10
- package/src/models/MilkPowderCanBottomCodeRephotographyDetectionResponseBody.ts +7 -7
- package/src/models/MilkPowderCartonCodeRephotographyDetectionResponseBody.ts +12 -9
- package/src/models/PrepaidTextTranslateRequest.ts +8 -8
- package/src/models/PrepaidTextTranslateResponseBody.ts +11 -8
- package/src/models/PrepaidTextTranslateShrinkRequest.ts +8 -8
- package/src/models/ProductVideoGenerationRequest.ts +88 -0
- package/src/models/ProductVideoGenerationResponse.ts +40 -0
- package/src/models/ProductVideoGenerationResponseBody.ts +124 -0
- package/src/models/ProductVideoGenerationShrinkRequest.ts +85 -0
- package/src/models/QueryDisplayKnowledgeResponseBody.ts +3 -0
- package/src/models/SizeChartExtractAsyncRequest.ts +3 -3
- package/src/models/SizeChartExtractAsyncResponseBody.ts +7 -5
- package/src/models/SizeChartExtractAsyncShrinkRequest.ts +3 -3
- package/src/models/StorefrontSceneRecognitionRequest.ts +1 -1
- package/src/models/StorefrontSceneRecognitionResponseBody.ts +9 -6
- package/src/models/SubmitProductMatchRequest.ts +8 -8
- package/src/models/SubmitProductMatchResponseBody.ts +7 -7
- package/src/models/TextTranslateAsyncRequest.ts +9 -9
- package/src/models/TextTranslateAsyncResponseBody.ts +6 -6
- package/src/models/TextTranslateAsyncShrinkRequest.ts +9 -9
- package/src/models/UpdateDisplayKnowledgeResponseBody.ts +3 -0
- package/src/models/VacancyDetectionRequest.ts +56 -0
- package/src/models/VacancyDetectionResponse.ts +40 -0
- package/src/models/VacancyDetectionResponseBody.ts +120 -0
- package/src/models/VideoGenerationRequest.ts +18 -17
- package/src/models/VideoGenerationResponseBody.ts +2 -2
- package/src/models/VideoTranslationRequest.ts +8 -17
- package/src/models/VideoTranslationResponseBody.ts +4 -6
- package/src/models/VideoTranslationShrinkRequest.ts +8 -17
- package/src/models/VirtualTryOnResponseBody.ts +7 -6
- package/src/models/model.ts +9 -0
package/dist/client.d.ts
CHANGED
|
@@ -24,38 +24,68 @@ export default class Client extends OpenApi {
|
|
|
24
24
|
*/
|
|
25
25
|
addDisplayKnowledge(request: $_model.AddDisplayKnowledgeRequest): Promise<$_model.AddDisplayKnowledgeResponse>;
|
|
26
26
|
/**
|
|
27
|
-
* Generates
|
|
27
|
+
* Generates virtual try-on images by using AI algorithms to replace a model\\"s clothing with a specified garment based on the input garment and model images. The operation preserves the model\\"s posture, facial features, and other visual details while ensuring a realistic and well-fitted appearance of the garment. It returns a processed image based on the provided URL of the original product image.
|
|
28
28
|
*
|
|
29
29
|
* @remarks
|
|
30
|
-
*
|
|
31
|
-
*
|
|
32
|
-
*
|
|
33
|
-
*
|
|
34
|
-
*
|
|
35
|
-
*
|
|
36
|
-
*
|
|
37
|
-
*
|
|
38
|
-
*
|
|
39
|
-
*
|
|
40
|
-
*
|
|
41
|
-
*
|
|
42
|
-
*
|
|
43
|
-
* -
|
|
44
|
-
*
|
|
45
|
-
*
|
|
46
|
-
*
|
|
47
|
-
*
|
|
48
|
-
*
|
|
49
|
-
*
|
|
50
|
-
*
|
|
51
|
-
* | **Type** | **Model image** | **Clothing image** | **Try-on result image** |
|
|
30
|
+
* # Product overview
|
|
31
|
+
* Virtual try-on is an AI-based image generation API service that replaces the clothing on a model with specified garments based on user-provided clothing and model images. It preserves the model\\"s other details and scene details without changing the model\\"s pose or facial features, ensuring a realistic and well-fitted appearance of the garments. You only need to provide the URLs of the original product images to obtain the processed images.
|
|
32
|
+
* # Scenarios
|
|
33
|
+
* * **Virtual try-on for clothing, shoes, and hats:**
|
|
34
|
+
*
|
|
35
|
+
* Supports virtual try-on for 14 categories of clothing, shoes, hats, and accessories, including tops, coats, bottoms, dresses, jumpsuits, socks, shoes, hats, earrings, necklaces, bracelets, scarves, bags, and glasses. After you upload a person image and product images, the system intelligently matches the position and proportion of the products based on the person\\"s pose and body parts to generate natural and realistic try-on effects. This intuitively displays the on-body performance of the clothing and presents a coordinated and realistic wearing effect.
|
|
36
|
+
* * **Model replacement (model skin/face replacement)**
|
|
37
|
+
*
|
|
38
|
+
* You provide the original model scene image and the face or reference image of the target model to apply the target person\\"s face to the model in the original image. This is applicable to customer-specified models, unified brand images, and character image adaptation for different markets. It also reduces the duplication of using the same model image as other merchants.
|
|
39
|
+
*
|
|
40
|
+
* * **Pose replacement (pose fission)**
|
|
41
|
+
*
|
|
42
|
+
* You provide the original model scene image and a pose reference image with a specified pose to generate the effect of the original person and outfit in the new pose. This displays the fit, silhouette, and on-body performance of the products in different poses such as standing, raising hands, and turning around.
|
|
43
|
+
* * **E-commerce product display and marketing:**
|
|
44
|
+
*
|
|
45
|
+
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional shooting, outfit changes, and post-production, and improving the production efficiency of product images.
|
|
46
|
+
* * **Online shopping experience optimization:**
|
|
47
|
+
*
|
|
48
|
+
* Consumers can preview the wearing effect of products through virtual try-on to more intuitively understand the style, matching, and overall effect of the products, assisting in purchase decisions and enhancing the shopping experience.
|
|
49
|
+
* # Features
|
|
50
|
+
* | Feature | Supported scope | User input and specification method | Scenario value |
|
|
52
51
|
* | --- | --- | --- | --- |
|
|
53
|
-
* |
|
|
54
|
-
*
|
|
55
|
-
*
|
|
56
|
-
*
|
|
57
|
-
*
|
|
58
|
-
*
|
|
52
|
+
* | **Clothing replacement/product wearing** | * Clothing: tops, bottoms (pants, skirts), coats, dresses, jumpsuits/rompers.
|
|
53
|
+
*
|
|
54
|
+
* * Shoes and hats: shoes, socks, hats.
|
|
55
|
+
*
|
|
56
|
+
* * Accessories: earrings, necklaces, bracelets, scarves, bags, glasses. | Upload a model image and product images, and the products will naturally fit the model. The system automatically matches the wearing position based on the clothing category, ensuring that the pose, proportion, and wearing layers are consistent with real human effects, while maintaining the person\\"s scene and pose in the original image.
|
|
57
|
+
* Try-on modes:
|
|
58
|
+
* * Supports single-item try-on.
|
|
59
|
+
*
|
|
60
|
+
* * Supports multi-item outfit matching (multiple items in one image or multiple items across multiple images).
|
|
61
|
+
*
|
|
62
|
+
* Note: The multi-item outfit matching capability was newly launched in November. | Uniformly generates the wearing effects of clothing, shoes, hats, and accessories, reducing item-by-item outfit changes and real-life shooting. |
|
|
63
|
+
* | **Model replacement/model skin replacement (face replacement)** | Supports user-specified target models.
|
|
64
|
+
* The original image can be a single-item try-on image or a multi-item outfit image. | Upload the original model scene image and provide one face photo or clear model reference image of the target person to replace the face and identity features of the model in the scene with those of the target person.
|
|
65
|
+
* The original outfit, pose, and scene are all preserved, and the generated result uses the person\\"s pose and background from the scene image. | Uses customer-specified or authorized model images to reduce duplication with existing model images and unify brand visuals. |
|
|
66
|
+
* | **Pose replacement/pose fission** | Generates images based on the user-specified pose.
|
|
67
|
+
* The original image can be a single-item try-on image or a multi-item outfit image. | Upload the original model scene image and one pose reference image to change the model\\"s pose to the action in the reference image. The person and outfit remain unchanged, and the wrinkles, drape, and layers of the clothing naturally adjust to the new pose. | Displays the fit, silhouette, and on-body style of the products in different poses, expanding the detail pages and marketing materials. |
|
|
68
|
+
* # 4. Effect examples
|
|
69
|
+
* | Scenario | Type/outfit description | Original model scene image | Product image/reference image | Effect image |
|
|
70
|
+
* | --- | --- | --- | --- | --- |
|
|
71
|
+
* | Single-item try-on | **Vest**
|
|
72
|
+
* Black buttoned sleeveless vest |  |  |  |
|
|
73
|
+
* | Single-item try-on | Top |  |  |  |
|
|
74
|
+
* | Single-item try-on | Bottom |  |  |  |
|
|
75
|
+
* | Single-item try-on | Shoes |  |  |  |
|
|
76
|
+
* | Single-item try-on | Jumpsuit |  |  |  |
|
|
77
|
+
* | Single-item try-on | Skirt |  |  |  |
|
|
78
|
+
* | Single-item try-on | Hat |  |  |  |
|
|
79
|
+
* | Multi-item try-on | **Two-item outfit**
|
|
80
|
+
* Dress + high heels |  |  |  |
|
|
81
|
+
* | Multi-item try-on | **Three-item outfit**
|
|
82
|
+
* Striped polo shirt + denim shorts + work boots |  |  |  |
|
|
83
|
+
* | Multi-item try-on | **Four-item outfit**
|
|
84
|
+
* Printed T-shirt + pants + hat + bag |  |  |  |
|
|
85
|
+
* | Model replacement | **Model skin/face replacement**
|
|
86
|
+
* Preserves the original top, pants, and scene |  |  |  |
|
|
87
|
+
* | Pose replacement | **Specified pose**
|
|
88
|
+
* Preserves the original outfit and adjusts to the hand-raising pose in the reference image |  |  |  |
|
|
59
89
|
*
|
|
60
90
|
* @param request - AiTryOnRequest
|
|
61
91
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -63,38 +93,68 @@ export default class Client extends OpenApi {
|
|
|
63
93
|
*/
|
|
64
94
|
aiTryOnWithOptions(request: $_model.AiTryOnRequest, runtime: $dara.RuntimeOptions): Promise<$_model.AiTryOnResponse>;
|
|
65
95
|
/**
|
|
66
|
-
* Generates
|
|
96
|
+
* Generates virtual try-on images by using AI algorithms to replace a model\\"s clothing with a specified garment based on the input garment and model images. The operation preserves the model\\"s posture, facial features, and other visual details while ensuring a realistic and well-fitted appearance of the garment. It returns a processed image based on the provided URL of the original product image.
|
|
67
97
|
*
|
|
68
98
|
* @remarks
|
|
69
|
-
*
|
|
70
|
-
*
|
|
71
|
-
*
|
|
72
|
-
*
|
|
73
|
-
*
|
|
74
|
-
*
|
|
75
|
-
*
|
|
76
|
-
*
|
|
77
|
-
*
|
|
78
|
-
*
|
|
79
|
-
*
|
|
80
|
-
*
|
|
81
|
-
*
|
|
82
|
-
* -
|
|
83
|
-
*
|
|
84
|
-
*
|
|
85
|
-
*
|
|
86
|
-
*
|
|
87
|
-
*
|
|
88
|
-
*
|
|
89
|
-
*
|
|
90
|
-
* | **Type** | **Model image** | **Clothing image** | **Try-on result image** |
|
|
99
|
+
* # Product overview
|
|
100
|
+
* Virtual try-on is an AI-based image generation API service that replaces the clothing on a model with specified garments based on user-provided clothing and model images. It preserves the model\\"s other details and scene details without changing the model\\"s pose or facial features, ensuring a realistic and well-fitted appearance of the garments. You only need to provide the URLs of the original product images to obtain the processed images.
|
|
101
|
+
* # Scenarios
|
|
102
|
+
* * **Virtual try-on for clothing, shoes, and hats:**
|
|
103
|
+
*
|
|
104
|
+
* Supports virtual try-on for 14 categories of clothing, shoes, hats, and accessories, including tops, coats, bottoms, dresses, jumpsuits, socks, shoes, hats, earrings, necklaces, bracelets, scarves, bags, and glasses. After you upload a person image and product images, the system intelligently matches the position and proportion of the products based on the person\\"s pose and body parts to generate natural and realistic try-on effects. This intuitively displays the on-body performance of the clothing and presents a coordinated and realistic wearing effect.
|
|
105
|
+
* * **Model replacement (model skin/face replacement)**
|
|
106
|
+
*
|
|
107
|
+
* You provide the original model scene image and the face or reference image of the target model to apply the target person\\"s face to the model in the original image. This is applicable to customer-specified models, unified brand images, and character image adaptation for different markets. It also reduces the duplication of using the same model image as other merchants.
|
|
108
|
+
*
|
|
109
|
+
* * **Pose replacement (pose fission)**
|
|
110
|
+
*
|
|
111
|
+
* You provide the original model scene image and a pose reference image with a specified pose to generate the effect of the original person and outfit in the new pose. This displays the fit, silhouette, and on-body performance of the products in different poses such as standing, raising hands, and turning around.
|
|
112
|
+
* * **E-commerce product display and marketing:**
|
|
113
|
+
*
|
|
114
|
+
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional shooting, outfit changes, and post-production, and improving the production efficiency of product images.
|
|
115
|
+
* * **Online shopping experience optimization:**
|
|
116
|
+
*
|
|
117
|
+
* Consumers can preview the wearing effect of products through virtual try-on to more intuitively understand the style, matching, and overall effect of the products, assisting in purchase decisions and enhancing the shopping experience.
|
|
118
|
+
* # Features
|
|
119
|
+
* | Feature | Supported scope | User input and specification method | Scenario value |
|
|
91
120
|
* | --- | --- | --- | --- |
|
|
92
|
-
* |
|
|
93
|
-
*
|
|
94
|
-
*
|
|
95
|
-
*
|
|
96
|
-
*
|
|
97
|
-
*
|
|
121
|
+
* | **Clothing replacement/product wearing** | * Clothing: tops, bottoms (pants, skirts), coats, dresses, jumpsuits/rompers.
|
|
122
|
+
*
|
|
123
|
+
* * Shoes and hats: shoes, socks, hats.
|
|
124
|
+
*
|
|
125
|
+
* * Accessories: earrings, necklaces, bracelets, scarves, bags, glasses. | Upload a model image and product images, and the products will naturally fit the model. The system automatically matches the wearing position based on the clothing category, ensuring that the pose, proportion, and wearing layers are consistent with real human effects, while maintaining the person\\"s scene and pose in the original image.
|
|
126
|
+
* Try-on modes:
|
|
127
|
+
* * Supports single-item try-on.
|
|
128
|
+
*
|
|
129
|
+
* * Supports multi-item outfit matching (multiple items in one image or multiple items across multiple images).
|
|
130
|
+
*
|
|
131
|
+
* Note: The multi-item outfit matching capability was newly launched in November. | Uniformly generates the wearing effects of clothing, shoes, hats, and accessories, reducing item-by-item outfit changes and real-life shooting. |
|
|
132
|
+
* | **Model replacement/model skin replacement (face replacement)** | Supports user-specified target models.
|
|
133
|
+
* The original image can be a single-item try-on image or a multi-item outfit image. | Upload the original model scene image and provide one face photo or clear model reference image of the target person to replace the face and identity features of the model in the scene with those of the target person.
|
|
134
|
+
* The original outfit, pose, and scene are all preserved, and the generated result uses the person\\"s pose and background from the scene image. | Uses customer-specified or authorized model images to reduce duplication with existing model images and unify brand visuals. |
|
|
135
|
+
* | **Pose replacement/pose fission** | Generates images based on the user-specified pose.
|
|
136
|
+
* The original image can be a single-item try-on image or a multi-item outfit image. | Upload the original model scene image and one pose reference image to change the model\\"s pose to the action in the reference image. The person and outfit remain unchanged, and the wrinkles, drape, and layers of the clothing naturally adjust to the new pose. | Displays the fit, silhouette, and on-body style of the products in different poses, expanding the detail pages and marketing materials. |
|
|
137
|
+
* # 4. Effect examples
|
|
138
|
+
* | Scenario | Type/outfit description | Original model scene image | Product image/reference image | Effect image |
|
|
139
|
+
* | --- | --- | --- | --- | --- |
|
|
140
|
+
* | Single-item try-on | **Vest**
|
|
141
|
+
* Black buttoned sleeveless vest |  |  |  |
|
|
142
|
+
* | Single-item try-on | Top |  |  |  |
|
|
143
|
+
* | Single-item try-on | Bottom |  |  |  |
|
|
144
|
+
* | Single-item try-on | Shoes |  |  |  |
|
|
145
|
+
* | Single-item try-on | Jumpsuit |  |  |  |
|
|
146
|
+
* | Single-item try-on | Skirt |  |  |  |
|
|
147
|
+
* | Single-item try-on | Hat |  |  |  |
|
|
148
|
+
* | Multi-item try-on | **Two-item outfit**
|
|
149
|
+
* Dress + high heels |  |  |  |
|
|
150
|
+
* | Multi-item try-on | **Three-item outfit**
|
|
151
|
+
* Striped polo shirt + denim shorts + work boots |  |  |  |
|
|
152
|
+
* | Multi-item try-on | **Four-item outfit**
|
|
153
|
+
* Printed T-shirt + pants + hat + bag |  |  |  |
|
|
154
|
+
* | Model replacement | **Model skin/face replacement**
|
|
155
|
+
* Preserves the original top, pants, and scene |  |  |  |
|
|
156
|
+
* | Pose replacement | **Specified pose**
|
|
157
|
+
* Preserves the original outfit and adjusts to the hand-raising pose in the reference image |  |  |  |
|
|
98
158
|
*
|
|
99
159
|
* @param request - AiTryOnRequest
|
|
100
160
|
* @returns AiTryOnResponse
|
|
@@ -387,18 +447,18 @@ export default class Client extends OpenApi {
|
|
|
387
447
|
*/
|
|
388
448
|
diduiAreaDeduction(request: $_model.DiduiAreaDeductionRequest): Promise<$_model.DiduiAreaDeductionResponse>;
|
|
389
449
|
/**
|
|
390
|
-
* Analyzes the area of floor displays based on product recognition, SKU asset knowledge bases, and dedicated area reasoning model building. The product first locates products in
|
|
450
|
+
* Analyzes the area of floor displays based on product recognition, SKU asset knowledge bases, and dedicated area reasoning model building. The product first locates products in floor displays, reads the actual length, width, height, and reference images of the corresponding SKUs, and infers the two side lengths and area of the bounding rectangle of the floor display area. This feature is suitable for evaluating the scale of floor displays in stores and conducting inspection reviews.
|
|
391
451
|
*
|
|
392
452
|
* @remarks
|
|
393
453
|
* *Scenarios**
|
|
394
454
|
* - Floor display area evaluation: Infers the area of the bounding rectangle based on the overall photo of the floor display and the actual dimensions of the products.
|
|
395
|
-
* - Multi-SKU mixed layout analysis: Uses the dimensions of different products to infer
|
|
396
|
-
* - Area result review: Verifies the results
|
|
455
|
+
* - Multi-SKU mixed layout analysis: Uses the dimensions of different products to infer side lengths.
|
|
456
|
+
* - Area result review: Verifies the results based on the original image, product assets, and the returned two side lengths and area.
|
|
397
457
|
* **Features**
|
|
398
458
|
* - SKU asset-driven: Specifies the asset knowledge base by using ragId. Each participating product must have a name, positive length, width, and height, and at least one HTTPS reference image.
|
|
399
459
|
* - Phased area inference: Sequentially forms decision edges, SKU projections, dimension accumulation, and the final area.
|
|
400
|
-
* - Unified units: SKU asset dimensions are stored in centimeters. The
|
|
401
|
-
* - Completeness and
|
|
460
|
+
* - Unified units: SKU asset dimensions are stored in centimeters. The result side lengths are output in meters and the area is output in square meters.
|
|
461
|
+
* - Completeness and value verification: Returns a failure if assets are missing, no valid bounding boxes are found, or the area does not match the product of the side lengths.
|
|
402
462
|
*
|
|
403
463
|
* @param request - DiduiAreaDeductionProRequest
|
|
404
464
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -406,40 +466,47 @@ export default class Client extends OpenApi {
|
|
|
406
466
|
*/
|
|
407
467
|
diduiAreaDeductionProWithOptions(request: $_model.DiduiAreaDeductionProRequest, runtime: $dara.RuntimeOptions): Promise<$_model.DiduiAreaDeductionProResponse>;
|
|
408
468
|
/**
|
|
409
|
-
* Analyzes the area of floor displays based on product recognition, SKU asset knowledge bases, and dedicated area reasoning model building. The product first locates products in
|
|
469
|
+
* Analyzes the area of floor displays based on product recognition, SKU asset knowledge bases, and dedicated area reasoning model building. The product first locates products in floor displays, reads the actual length, width, height, and reference images of the corresponding SKUs, and infers the two side lengths and area of the bounding rectangle of the floor display area. This feature is suitable for evaluating the scale of floor displays in stores and conducting inspection reviews.
|
|
410
470
|
*
|
|
411
471
|
* @remarks
|
|
412
472
|
* *Scenarios**
|
|
413
473
|
* - Floor display area evaluation: Infers the area of the bounding rectangle based on the overall photo of the floor display and the actual dimensions of the products.
|
|
414
|
-
* - Multi-SKU mixed layout analysis: Uses the dimensions of different products to infer
|
|
415
|
-
* - Area result review: Verifies the results
|
|
474
|
+
* - Multi-SKU mixed layout analysis: Uses the dimensions of different products to infer side lengths.
|
|
475
|
+
* - Area result review: Verifies the results based on the original image, product assets, and the returned two side lengths and area.
|
|
416
476
|
* **Features**
|
|
417
477
|
* - SKU asset-driven: Specifies the asset knowledge base by using ragId. Each participating product must have a name, positive length, width, and height, and at least one HTTPS reference image.
|
|
418
478
|
* - Phased area inference: Sequentially forms decision edges, SKU projections, dimension accumulation, and the final area.
|
|
419
|
-
* - Unified units: SKU asset dimensions are stored in centimeters. The
|
|
420
|
-
* - Completeness and
|
|
479
|
+
* - Unified units: SKU asset dimensions are stored in centimeters. The result side lengths are output in meters and the area is output in square meters.
|
|
480
|
+
* - Completeness and value verification: Returns a failure if assets are missing, no valid bounding boxes are found, or the area does not match the product of the side lengths.
|
|
421
481
|
*
|
|
422
482
|
* @param request - DiduiAreaDeductionProRequest
|
|
423
483
|
* @returns DiduiAreaDeductionProResponse
|
|
424
484
|
*/
|
|
425
485
|
diduiAreaDeductionPro(request: $_model.DiduiAreaDeductionProRequest): Promise<$_model.DiduiAreaDeductionProResponse>;
|
|
426
486
|
/**
|
|
427
|
-
* Translates documents
|
|
487
|
+
* Translates documents with a solution designed specifically for document translation. It supports over 150 languages and provides pivot translation capabilities with thousands of pivot combinations. It handles multi-scenario, multi-page, and highly complex document translation, but does not currently support scanned documents. It excels in the following aspects:
|
|
488
|
+
* - Content accuracy: translation accuracy, and accuracy of parameters and units.
|
|
489
|
+
* - Structural integrity: overall layout continuity, and restoration of page margins and layouts.
|
|
428
490
|
*
|
|
429
491
|
* @remarks
|
|
430
|
-
*
|
|
431
|
-
* Designed specifically for document translation, this
|
|
492
|
+
* # Product introduction
|
|
493
|
+
* Designed specifically for document translation, this service supports more than 150 languages and provides bridging translation capabilities with thousands of language combinations. It handles multi-scenario, multi-page, and highly complex document translations, but does not currently support scanned documents.
|
|
432
494
|
* It excels in the following aspects:
|
|
433
|
-
*
|
|
434
|
-
*
|
|
435
|
-
*
|
|
436
|
-
*
|
|
437
|
-
*
|
|
438
|
-
*
|
|
439
|
-
*
|
|
440
|
-
*
|
|
441
|
-
*
|
|
442
|
-
*
|
|
495
|
+
* * Content accuracy: translation accuracy, and accuracy of parameters and units.
|
|
496
|
+
*
|
|
497
|
+
* * Structural integrity: overall layout continuity, and restoration of page margins and layouts.
|
|
498
|
+
* # Scenarios
|
|
499
|
+
* Cross-border e-commerce product manuals, contracts, agreements, business proposals, qualification documents, teaching materials, courseware, and various other scenarios.
|
|
500
|
+
* # Features
|
|
501
|
+
* * Supports PDF, Word, and Excel formats. Supports source documents that contain multiple languages. For the detailed language list, see Section 4.4.
|
|
502
|
+
*
|
|
503
|
+
* * Supports the translation of text within images in documents, as well as complex translation scenarios involving other charts and special symbols.
|
|
504
|
+
*
|
|
505
|
+
* * Supports highly accurate layout restoration after translation.
|
|
506
|
+
*
|
|
507
|
+
* * Supports the translation of a single PDF or Word document with up to **800 pages**.
|
|
508
|
+
*
|
|
509
|
+
* * Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and translation omission (ABC-null value). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API to meet your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance. For detailed instructions on translation intervention, see [Full-modal translation - Translation intervention instruction manual](https://www.alibabacloud.com/help/en/aidge/full-modal-translation-translation-intervention-instruction-manual)
|
|
443
510
|
*
|
|
444
511
|
* @param request - DocumentTranslateRequest
|
|
445
512
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -447,67 +514,74 @@ export default class Client extends OpenApi {
|
|
|
447
514
|
*/
|
|
448
515
|
documentTranslateWithOptions(request: $_model.DocumentTranslateRequest, runtime: $dara.RuntimeOptions): Promise<$_model.DocumentTranslateResponse>;
|
|
449
516
|
/**
|
|
450
|
-
* Translates documents
|
|
517
|
+
* Translates documents with a solution designed specifically for document translation. It supports over 150 languages and provides pivot translation capabilities with thousands of pivot combinations. It handles multi-scenario, multi-page, and highly complex document translation, but does not currently support scanned documents. It excels in the following aspects:
|
|
518
|
+
* - Content accuracy: translation accuracy, and accuracy of parameters and units.
|
|
519
|
+
* - Structural integrity: overall layout continuity, and restoration of page margins and layouts.
|
|
451
520
|
*
|
|
452
521
|
* @remarks
|
|
453
|
-
*
|
|
454
|
-
* Designed specifically for document translation, this
|
|
522
|
+
* # Product introduction
|
|
523
|
+
* Designed specifically for document translation, this service supports more than 150 languages and provides bridging translation capabilities with thousands of language combinations. It handles multi-scenario, multi-page, and highly complex document translations, but does not currently support scanned documents.
|
|
455
524
|
* It excels in the following aspects:
|
|
456
|
-
*
|
|
457
|
-
*
|
|
458
|
-
*
|
|
459
|
-
*
|
|
460
|
-
*
|
|
461
|
-
*
|
|
462
|
-
*
|
|
463
|
-
*
|
|
464
|
-
*
|
|
465
|
-
*
|
|
525
|
+
* * Content accuracy: translation accuracy, and accuracy of parameters and units.
|
|
526
|
+
*
|
|
527
|
+
* * Structural integrity: overall layout continuity, and restoration of page margins and layouts.
|
|
528
|
+
* # Scenarios
|
|
529
|
+
* Cross-border e-commerce product manuals, contracts, agreements, business proposals, qualification documents, teaching materials, courseware, and various other scenarios.
|
|
530
|
+
* # Features
|
|
531
|
+
* * Supports PDF, Word, and Excel formats. Supports source documents that contain multiple languages. For the detailed language list, see Section 4.4.
|
|
532
|
+
*
|
|
533
|
+
* * Supports the translation of text within images in documents, as well as complex translation scenarios involving other charts and special symbols.
|
|
534
|
+
*
|
|
535
|
+
* * Supports highly accurate layout restoration after translation.
|
|
536
|
+
*
|
|
537
|
+
* * Supports the translation of a single PDF or Word document with up to **800 pages**.
|
|
538
|
+
*
|
|
539
|
+
* * Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and translation omission (ABC-null value). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API to meet your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance. For detailed instructions on translation intervention, see [Full-modal translation - Translation intervention instruction manual](https://www.alibabacloud.com/help/en/aidge/full-modal-translation-translation-intervention-instruction-manual)
|
|
466
540
|
*
|
|
467
541
|
* @param request - DocumentTranslateRequest
|
|
468
542
|
* @returns DocumentTranslateResponse
|
|
469
543
|
*/
|
|
470
544
|
documentTranslate(request: $_model.DocumentTranslateRequest): Promise<$_model.DocumentTranslateResponse>;
|
|
471
545
|
/**
|
|
472
|
-
*
|
|
546
|
+
* Provides an AI video service for e-commerce content production, covering video understanding, element replacement, quality verification, and result delivery. The service focuses on product and person consistency, detail restoration, conversion expression, and scaled production. It supports targeted replacement of products or persons based on viral video templates, quickly generating multiple versions of content while preserving original actions, camera rhythms, and marketing structures to reduce shooting, editing, and adaptation costs.
|
|
473
547
|
*
|
|
474
548
|
* @remarks
|
|
475
549
|
* ## **Product introduction**
|
|
476
|
-
* E-commerce video
|
|
550
|
+
* E-commerce video variation is an AI video service for product content production, covering video understanding, element replacement, quality verification, and result delivery. The service focuses on product and person consistency, detail restoration, conversion expression, and scaled production. It supports targeted replacement of products or persons based on viral video templates, quickly generating multiple versions of content while preserving original actions, camera rhythms, and marketing structures to reduce shooting, editing, and adaptation costs.
|
|
477
551
|
* ## **Scenarios**
|
|
478
|
-
* - **Video material
|
|
479
|
-
* - **
|
|
480
|
-
* - **Product explanation and selling point expression:** Suitable for products such as apparel, beauty and personal care, food and
|
|
481
|
-
* - **Multi-selling point and multi-version testing:**
|
|
482
|
-
* ## **
|
|
552
|
+
* - **Video material variation:** Uses an existing e-commerce video as a template and replaces only specified products or persons in the video, preserving the original camera angles, rhythm, and marketing expression as much as possible. This is suitable for producing materials with multiple SKUs, models, regions, and versions.
|
|
553
|
+
* - **New product launch and rapid material generation:** For centrally launched new products, this reduces manual shooting, studio setup, post-production editing, and repetitive production processes. It quickly deploys new product video materials, helping merchants shorten the launch cycle from spotting a viral video to breaking down the script and shooting new content.
|
|
554
|
+
* - **Product explanation and selling point expression:** Suitable for products such as apparel, beauty and personal care, food and beverages, home and daily necessities, 3C digital products, and small home appliances. It can plan the explanation structure, display actions, and camera rhythm based on the selling points of the original video, and generate explanation videos tailored for the conversion of new products.
|
|
555
|
+
* - **Multi-selling point and multi-version testing:** Quickly generates multiple versions based on different product selling points, target audiences, scripts, camera angles, and visual styles, supporting merchants in conducting content testing and iterating delivery materials.
|
|
556
|
+
* ## **Feature overview**
|
|
483
557
|
* ### **Core capabilities**
|
|
484
558
|
* * **Supports two replacement modes:**
|
|
485
559
|
*
|
|
486
|
-
* * **Product replacement (**`product_replacement`**)**: Preserves the identity, actions, scene, and sales structure
|
|
560
|
+
* * **Product replacement (**`product_replacement`**)**: Preserves the original video\\"s host identity, actions, scene, and sales structure, and replaces the original product with the target product.
|
|
487
561
|
*
|
|
488
|
-
* * **Person replacement (**`person_replacement`**)**: Preserves the product, actions, scene, and sales structure
|
|
562
|
+
* * **Person replacement (**`person_replacement`**)**: Preserves the original video\\"s product, actions, scene, and sales structure, and replaces the on-screen person with the target person from reference images or descriptions.
|
|
489
563
|
*
|
|
490
564
|
* * **Supports two generation modes:**
|
|
491
565
|
*
|
|
492
|
-
* * **Reference generation (**`reference`**)**: 1:1 replication. Uses the original video as a complete reference to automatically generate a new video with the same duration. It preserves the original script, storyboard, actions, scene, and
|
|
566
|
+
* * **Reference generation (**`reference`**)**: 1:1 replication. Uses the original video as a complete reference to automatically generate a new video with the same duration as the original video. It preserves the original script, storyboard, actions, scene, and rhythm, and only performs targeted replacement of specified content such as persons or products.
|
|
493
567
|
*
|
|
494
|
-
* * **Rebuild generation (**`rebuild`**)**: Breaks down the script, storyboard, and key elements of the original video, retains only core content such as specified persons or products, and then redesigns and generates a new video. It is not limited by the
|
|
568
|
+
* * **Rebuild generation (**`rebuild`**)**: Breaks down the script, storyboard, and key elements of the original video, retains only core content such as specified persons or products, and then redesigns and generates a new video. It is not limited by the original video duration and supports inputting a target duration.
|
|
495
569
|
*
|
|
496
|
-
* * **Fully automated end-to-end generation with zero prompt
|
|
570
|
+
* * **Fully automated end-to-end generation with zero prompt threshold**: Only requires passing the reference video and target product or person images. The system automatically completes the entire process of video understanding, script planning, storyboard design, first-frame generation, and video synthesis.
|
|
497
571
|
*
|
|
498
|
-
* * **Product understanding and information structuring**: Identifies product categories, appearance, materials, colors, structures, and key components, and combines them with
|
|
572
|
+
* * **Product understanding and information structuring**: Identifies product categories, appearance, materials, colors, structures, and key components, and combines them with titles, attributes, and selling points provided by merchants to generate usable video expression information.
|
|
499
573
|
*
|
|
500
574
|
* * **Template video element replacement**: Supports replacing products or persons within the authorized scope, and defines the replacement scope and protection scope to minimize changes in non-target areas.
|
|
501
575
|
*
|
|
502
|
-
* * **Product subject consistency**: Maintains the stability of the product\\"s shape, color, texture, pattern, packaging, and logo across different camera
|
|
576
|
+
* * **Product subject consistency**: Maintains the stability of the product\\"s shape, color, texture, pattern, packaging, and logo as much as possible across different camera angles, perspectives, actions, and scenes.
|
|
503
577
|
*
|
|
504
578
|
* * **Product fidelity**: Multi-round VL quality inspection locks the product state (color, texture, structure, print) throughout the process to prevent product feature drift.
|
|
505
579
|
*
|
|
506
|
-
* * **Selling point script and storyboard replication**:
|
|
580
|
+
* * **Selling point script and storyboard replication**: Follows the selling point planning, video structure, camera sequence, display actions, voiceover content, and ending style of the original video.
|
|
507
581
|
*
|
|
508
|
-
* * **Commercial model adaptation**: Supports matching corresponding model images and
|
|
582
|
+
* * **Commercial model adaptation**: Supports matching corresponding model images and display methods based on product style, fit, target audience, and market demand.
|
|
509
583
|
*
|
|
510
|
-
* * **Quality verification and result feedback**: Performs multi-dimensional checks on the product subject, person,
|
|
584
|
+
* * **Quality verification and result feedback**: Performs multi-dimensional checks on the product subject, person, clothing, text, picture integrity, audio, and overall usability, and outputs result information for manual review.
|
|
511
585
|
*
|
|
512
586
|
* @param tmpReq - EcomVideoRecreationRequest
|
|
513
587
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -515,63 +589,63 @@ export default class Client extends OpenApi {
|
|
|
515
589
|
*/
|
|
516
590
|
ecomVideoRecreationWithOptions(tmpReq: $_model.EcomVideoRecreationRequest, runtime: $dara.RuntimeOptions): Promise<$_model.EcomVideoRecreationResponse>;
|
|
517
591
|
/**
|
|
518
|
-
*
|
|
592
|
+
* Provides an AI video service for e-commerce content production, covering video understanding, element replacement, quality verification, and result delivery. The service focuses on product and person consistency, detail restoration, conversion expression, and scaled production. It supports targeted replacement of products or persons based on viral video templates, quickly generating multiple versions of content while preserving original actions, camera rhythms, and marketing structures to reduce shooting, editing, and adaptation costs.
|
|
519
593
|
*
|
|
520
594
|
* @remarks
|
|
521
595
|
* ## **Product introduction**
|
|
522
|
-
* E-commerce video
|
|
596
|
+
* E-commerce video variation is an AI video service for product content production, covering video understanding, element replacement, quality verification, and result delivery. The service focuses on product and person consistency, detail restoration, conversion expression, and scaled production. It supports targeted replacement of products or persons based on viral video templates, quickly generating multiple versions of content while preserving original actions, camera rhythms, and marketing structures to reduce shooting, editing, and adaptation costs.
|
|
523
597
|
* ## **Scenarios**
|
|
524
|
-
* - **Video material
|
|
525
|
-
* - **
|
|
526
|
-
* - **Product explanation and selling point expression:** Suitable for products such as apparel, beauty and personal care, food and
|
|
527
|
-
* - **Multi-selling point and multi-version testing:**
|
|
528
|
-
* ## **
|
|
598
|
+
* - **Video material variation:** Uses an existing e-commerce video as a template and replaces only specified products or persons in the video, preserving the original camera angles, rhythm, and marketing expression as much as possible. This is suitable for producing materials with multiple SKUs, models, regions, and versions.
|
|
599
|
+
* - **New product launch and rapid material generation:** For centrally launched new products, this reduces manual shooting, studio setup, post-production editing, and repetitive production processes. It quickly deploys new product video materials, helping merchants shorten the launch cycle from spotting a viral video to breaking down the script and shooting new content.
|
|
600
|
+
* - **Product explanation and selling point expression:** Suitable for products such as apparel, beauty and personal care, food and beverages, home and daily necessities, 3C digital products, and small home appliances. It can plan the explanation structure, display actions, and camera rhythm based on the selling points of the original video, and generate explanation videos tailored for the conversion of new products.
|
|
601
|
+
* - **Multi-selling point and multi-version testing:** Quickly generates multiple versions based on different product selling points, target audiences, scripts, camera angles, and visual styles, supporting merchants in conducting content testing and iterating delivery materials.
|
|
602
|
+
* ## **Feature overview**
|
|
529
603
|
* ### **Core capabilities**
|
|
530
604
|
* * **Supports two replacement modes:**
|
|
531
605
|
*
|
|
532
|
-
* * **Product replacement (**`product_replacement`**)**: Preserves the identity, actions, scene, and sales structure
|
|
606
|
+
* * **Product replacement (**`product_replacement`**)**: Preserves the original video\\"s host identity, actions, scene, and sales structure, and replaces the original product with the target product.
|
|
533
607
|
*
|
|
534
|
-
* * **Person replacement (**`person_replacement`**)**: Preserves the product, actions, scene, and sales structure
|
|
608
|
+
* * **Person replacement (**`person_replacement`**)**: Preserves the original video\\"s product, actions, scene, and sales structure, and replaces the on-screen person with the target person from reference images or descriptions.
|
|
535
609
|
*
|
|
536
610
|
* * **Supports two generation modes:**
|
|
537
611
|
*
|
|
538
|
-
* * **Reference generation (**`reference`**)**: 1:1 replication. Uses the original video as a complete reference to automatically generate a new video with the same duration. It preserves the original script, storyboard, actions, scene, and
|
|
612
|
+
* * **Reference generation (**`reference`**)**: 1:1 replication. Uses the original video as a complete reference to automatically generate a new video with the same duration as the original video. It preserves the original script, storyboard, actions, scene, and rhythm, and only performs targeted replacement of specified content such as persons or products.
|
|
539
613
|
*
|
|
540
|
-
* * **Rebuild generation (**`rebuild`**)**: Breaks down the script, storyboard, and key elements of the original video, retains only core content such as specified persons or products, and then redesigns and generates a new video. It is not limited by the
|
|
614
|
+
* * **Rebuild generation (**`rebuild`**)**: Breaks down the script, storyboard, and key elements of the original video, retains only core content such as specified persons or products, and then redesigns and generates a new video. It is not limited by the original video duration and supports inputting a target duration.
|
|
541
615
|
*
|
|
542
|
-
* * **Fully automated end-to-end generation with zero prompt
|
|
616
|
+
* * **Fully automated end-to-end generation with zero prompt threshold**: Only requires passing the reference video and target product or person images. The system automatically completes the entire process of video understanding, script planning, storyboard design, first-frame generation, and video synthesis.
|
|
543
617
|
*
|
|
544
|
-
* * **Product understanding and information structuring**: Identifies product categories, appearance, materials, colors, structures, and key components, and combines them with
|
|
618
|
+
* * **Product understanding and information structuring**: Identifies product categories, appearance, materials, colors, structures, and key components, and combines them with titles, attributes, and selling points provided by merchants to generate usable video expression information.
|
|
545
619
|
*
|
|
546
620
|
* * **Template video element replacement**: Supports replacing products or persons within the authorized scope, and defines the replacement scope and protection scope to minimize changes in non-target areas.
|
|
547
621
|
*
|
|
548
|
-
* * **Product subject consistency**: Maintains the stability of the product\\"s shape, color, texture, pattern, packaging, and logo across different camera
|
|
622
|
+
* * **Product subject consistency**: Maintains the stability of the product\\"s shape, color, texture, pattern, packaging, and logo as much as possible across different camera angles, perspectives, actions, and scenes.
|
|
549
623
|
*
|
|
550
624
|
* * **Product fidelity**: Multi-round VL quality inspection locks the product state (color, texture, structure, print) throughout the process to prevent product feature drift.
|
|
551
625
|
*
|
|
552
|
-
* * **Selling point script and storyboard replication**:
|
|
626
|
+
* * **Selling point script and storyboard replication**: Follows the selling point planning, video structure, camera sequence, display actions, voiceover content, and ending style of the original video.
|
|
553
627
|
*
|
|
554
|
-
* * **Commercial model adaptation**: Supports matching corresponding model images and
|
|
628
|
+
* * **Commercial model adaptation**: Supports matching corresponding model images and display methods based on product style, fit, target audience, and market demand.
|
|
555
629
|
*
|
|
556
|
-
* * **Quality verification and result feedback**: Performs multi-dimensional checks on the product subject, person,
|
|
630
|
+
* * **Quality verification and result feedback**: Performs multi-dimensional checks on the product subject, person, clothing, text, picture integrity, audio, and overall usability, and outputs result information for manual review.
|
|
557
631
|
*
|
|
558
632
|
* @param request - EcomVideoRecreationRequest
|
|
559
633
|
* @returns EcomVideoRecreationResponse
|
|
560
634
|
*/
|
|
561
635
|
ecomVideoRecreation(request: $_model.EcomVideoRecreationRequest): Promise<$_model.EcomVideoRecreationResponse>;
|
|
562
636
|
/**
|
|
563
|
-
* Detects whether an image is recaptured and
|
|
637
|
+
* Detects whether an image is recaptured and locates main physical products, screen display areas, printed photos, and visible recapture clues based on recapture recognition and multimodal large model element localization. This general-purpose image moderation service applies to risk screening and manual review of store inspection photos across multiple categories.
|
|
564
638
|
*
|
|
565
639
|
* @remarks
|
|
566
640
|
* *Scenarios**
|
|
567
|
-
* 1. Inspection photo review: Screens
|
|
568
|
-
* 2. Screen or printed photo recapture verification:
|
|
641
|
+
* 1. Inspection photo review: Screens photos submitted by stores for recapture risks.
|
|
642
|
+
* 2. Screen or printed photo recapture verification: Locates visible screens, printed photos, and other media.
|
|
569
643
|
* 3. Review clue display: Annotates products and visible clues on the original image to assist in manual review.
|
|
570
644
|
* **Features**
|
|
571
|
-
* 1. General recapture detection: Outputs a Boolean
|
|
645
|
+
* 1. General recapture detection: Outputs a Boolean conclusion for isFake.
|
|
572
646
|
* 2. Review element localization: Distinguishes physical products, screens, printed photos, and visible recapture clues. Products inside screens are not repeatedly output as physical products.
|
|
573
647
|
* 3. Separate presentation of clues and conclusions: Localization text only describes visible phenomena and does not directly use normal reflections or standard packaging prints as recapture evidence.
|
|
574
|
-
* Supports
|
|
648
|
+
* Supports single HTTPS image input. Supplementary localization returns up to 12 targets. Each target includes a category, a bounding box, and up to 24 characters of visible text, and uses coverage to indicate whether the localization is complete.
|
|
575
649
|
*
|
|
576
650
|
* @param request - GeneralRephotographyDetectionRequest
|
|
577
651
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -579,40 +653,40 @@ export default class Client extends OpenApi {
|
|
|
579
653
|
*/
|
|
580
654
|
generalRephotographyDetectionWithOptions(request: $_model.GeneralRephotographyDetectionRequest, runtime: $dara.RuntimeOptions): Promise<$_model.GeneralRephotographyDetectionResponse>;
|
|
581
655
|
/**
|
|
582
|
-
* Detects whether an image is recaptured and
|
|
656
|
+
* Detects whether an image is recaptured and locates main physical products, screen display areas, printed photos, and visible recapture clues based on recapture recognition and multimodal large model element localization. This general-purpose image moderation service applies to risk screening and manual review of store inspection photos across multiple categories.
|
|
583
657
|
*
|
|
584
658
|
* @remarks
|
|
585
659
|
* *Scenarios**
|
|
586
|
-
* 1. Inspection photo review: Screens
|
|
587
|
-
* 2. Screen or printed photo recapture verification:
|
|
660
|
+
* 1. Inspection photo review: Screens photos submitted by stores for recapture risks.
|
|
661
|
+
* 2. Screen or printed photo recapture verification: Locates visible screens, printed photos, and other media.
|
|
588
662
|
* 3. Review clue display: Annotates products and visible clues on the original image to assist in manual review.
|
|
589
663
|
* **Features**
|
|
590
|
-
* 1. General recapture detection: Outputs a Boolean
|
|
664
|
+
* 1. General recapture detection: Outputs a Boolean conclusion for isFake.
|
|
591
665
|
* 2. Review element localization: Distinguishes physical products, screens, printed photos, and visible recapture clues. Products inside screens are not repeatedly output as physical products.
|
|
592
666
|
* 3. Separate presentation of clues and conclusions: Localization text only describes visible phenomena and does not directly use normal reflections or standard packaging prints as recapture evidence.
|
|
593
|
-
* Supports
|
|
667
|
+
* Supports single HTTPS image input. Supplementary localization returns up to 12 targets. Each target includes a category, a bounding box, and up to 24 characters of visible text, and uses coverage to indicate whether the localization is complete.
|
|
594
668
|
*
|
|
595
669
|
* @param request - GeneralRephotographyDetectionRequest
|
|
596
670
|
* @returns GeneralRephotographyDetectionResponse
|
|
597
671
|
*/
|
|
598
672
|
generalRephotographyDetection(request: $_model.GeneralRephotographyDetectionRequest): Promise<$_model.GeneralRephotographyDetectionResponse>;
|
|
599
673
|
/**
|
|
600
|
-
* Generates or rewrites e-commerce product copy,
|
|
674
|
+
* Generates or rewrites e-commerce product copy, such as titles, short highlights, search keywords, bulleted selling points, and product descriptions, based on input product information or existing copy, and adapts the content type and length to the requirements of the target platform. Supports Chinese and English input materials and optional multilingual translation for scenarios such as domestic product listing, cross-border product distribution, and product copy localization. Uses synchronous invocation to process one copy type for a single product per request.
|
|
601
675
|
*
|
|
602
676
|
* @remarks
|
|
603
677
|
* # Product introduction
|
|
604
|
-
*
|
|
605
|
-
*
|
|
678
|
+
* E-commerce product copy generation is an AI text service for e-commerce product content production. By inputting product materials or existing copy, you can generate or rewrite product titles, short highlights, search keywords, bullet points, and product descriptions, and adapt the content type and length to the target platform as needed.
|
|
679
|
+
* It supports Chinese and English material inputs and optional multilingual translation, and applies to scenarios such as domestic product listing, cross-border distribution, and product copy localization. The API uses synchronous calls and processes one copy type for one product per request.
|
|
606
680
|
* # Scenarios
|
|
607
681
|
* | **Scenario** | **Description** |
|
|
608
682
|
* | --- | --- |
|
|
609
|
-
* | Same-platform localization | Select rewrite
|
|
683
|
+
* | Same-platform localization | Select rewrite and translate as needed to retain the original facts and type structure. |
|
|
610
684
|
* | Cross-platform content adaptation | Select the target platform to generate or rewrite content according to its configuration limits. The source platform of the input is not required. |
|
|
611
|
-
* | New product material
|
|
612
|
-
* | Batch operation tool integration | The caller submits requests product by product. The workflow itself does not provide batch task or
|
|
685
|
+
* | New product material production | Select generate to generate the target type based on product materials. Categories and attributes can be used to supplement facts. |
|
|
686
|
+
* | Batch operation tool integration | The caller submits requests product by product. The workflow itself does not provide batch task or queue APIs. |
|
|
613
687
|
* # Features
|
|
614
688
|
* ## Core capabilities
|
|
615
|
-
* This capability supports the
|
|
689
|
+
* This capability supports the production of different copy content types in domestic and cross-border e-commerce scenarios. It can produce titles, detailed descriptions, keywords, highlights, and descriptions that adapt to the content rules (length requirements and writing styles) of different platforms, and supports cross-language production.
|
|
616
690
|
* | Content type | Platform | | | | | | Target language |
|
|
617
691
|
* | --- | --- | --- | --- | --- | --- | --- | --- |
|
|
618
692
|
* | | Amazon | Temu | TikTok | Shopify | Wildberries | Tmall |
|
|
@@ -622,19 +696,19 @@ export default class Client extends OpenApi {
|
|
|
622
696
|
* | **bulletPoint** | ✓ | | | ✓ | | |
|
|
623
697
|
* | **keywords** | ✓ | | | | | |
|
|
624
698
|
* | **description** | ✓ | ✓ | ✓ | ✓ | ✓ | |
|
|
625
|
-
* Based on the
|
|
699
|
+
* Based on the content inputs provided by users, two production modes are supported:
|
|
626
700
|
* | **Mode** | **Description** | **Recommended scenario** |
|
|
627
701
|
* | --- | --- | --- |
|
|
628
|
-
* | Generate | Reorganizes and writes copy based on product
|
|
629
|
-
* | Rewrite | Retains the original information and main structure
|
|
702
|
+
* | Generate | Reorganizes and writes copy based on product materials. | Only product parameters, attributes, or selling points are available, or other types of product materials are available, and new titles, keywords, product descriptions, and other copy need to be created. |
|
|
703
|
+
* | Rewrite | Retains the original information and main structure, and optimizes the expression. | Existing product copy is available, and you want to adjust the wording, improve readability, or localize it with translation. |
|
|
630
704
|
* # Examples
|
|
631
705
|
* The following examples use the Amazon platform:
|
|
632
706
|
* | **Content type** | **Source language** | **Source content** | **Target language** | **Generated result** | **Capability advantage** |
|
|
633
707
|
* | --- | --- | --- | --- | --- | --- |
|
|
634
|
-
* | bulletPoint | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | [Vielseitiges Harz-Filtersystem\\] Silikontrichter und Metallfiltergitter für 3D-Druck; Einfüllen von gebrauchtem lichtempfindlichem Harz in Flaschen mit 15 mm Halsweite | Extracts core selling points, retains key information such as bottle neck size, and presents
|
|
708
|
+
* | bulletPoint | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | [Vielseitiges Harz-Filtersystem\\] Silikontrichter und Metallfiltergitter für 3D-Druck; Einfüllen von gebrauchtem lichtempfindlichem Harz in Flaschen mit 15 mm Halsweite | Extracts core selling points, retains key information such as bottle neck size, and presents it in German bullet points for quick reading. |
|
|
635
709
|
* | description | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | [Vielseitiges Harz-Filtrationssystem\\] Diese Kombination aus Silikontrichter und Metallfilternetz richtet sich an alle, die mit 3D-Druck arbeiten. Der flexible Silikontrichter passt sicher auf Standardflaschen mit einer Halsweite von 15 mm und ermöglicht ein sauberes Zurückfüllen von gebrauchtem lichtempfindlichem Harz ohne Kleckern. Das feine Metallfilter fängt verfestigte Partikel zuverlässig ab, sodass Ihr Harz frei von Verunreinigungen bleibt und seine Nutzbarkeit erhalten wird. Die robuste Konstruktion des Filters unterstützt eine gleichmäßige Durchflussrate beim Umfüllen. | Organizes the product purpose, usage, and filtration features into a coherent German introduction for easy understanding. |
|
|
636
|
-
* | highlight | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | [Vielseitiges Harz-Filtrationssystem\\] Silikontrichter, Metallfilternetz, für 3D-Druck-Harz |
|
|
637
|
-
* | keywords | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | Silikontrichter Metallfilter Harz Filterungssystem 3D Drucker Harz umfüllen Metall Sieb für Photosensitive Harze | Extracts German search terms related to materials, categories, and purposes
|
|
710
|
+
* | highlight | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | [Vielseitiges Harz-Filtrationssystem\\] Silikontrichter, Metallfilternetz, für 3D-Druck-Harz | Simplifies long materials, highlights core components and purposes, and makes it easy to grasp product features at a glance. |
|
|
711
|
+
* | keywords | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | Silikontrichter Metallfilter Harz Filterungssystem 3D Drucker Harz umfüllen Metall Sieb für Photosensitive Harze | Extracts German search terms related to materials, categories, and purposes to reduce manual sorting and translation. |
|
|
638
712
|
* | title | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | Silikontrichter mit Metallfilter für 3D-Druck-Harz | Extracts the product name, core components, and purpose to generate a concise and clear German title. |
|
|
639
713
|
*
|
|
640
714
|
* @param request - GenerateProductContentRequest
|
|
@@ -643,22 +717,22 @@ export default class Client extends OpenApi {
|
|
|
643
717
|
*/
|
|
644
718
|
generateProductContentWithOptions(request: $_model.GenerateProductContentRequest, runtime: $dara.RuntimeOptions): Promise<$_model.GenerateProductContentResponse>;
|
|
645
719
|
/**
|
|
646
|
-
* Generates or rewrites e-commerce product copy,
|
|
720
|
+
* Generates or rewrites e-commerce product copy, such as titles, short highlights, search keywords, bulleted selling points, and product descriptions, based on input product information or existing copy, and adapts the content type and length to the requirements of the target platform. Supports Chinese and English input materials and optional multilingual translation for scenarios such as domestic product listing, cross-border product distribution, and product copy localization. Uses synchronous invocation to process one copy type for a single product per request.
|
|
647
721
|
*
|
|
648
722
|
* @remarks
|
|
649
723
|
* # Product introduction
|
|
650
|
-
*
|
|
651
|
-
*
|
|
724
|
+
* E-commerce product copy generation is an AI text service for e-commerce product content production. By inputting product materials or existing copy, you can generate or rewrite product titles, short highlights, search keywords, bullet points, and product descriptions, and adapt the content type and length to the target platform as needed.
|
|
725
|
+
* It supports Chinese and English material inputs and optional multilingual translation, and applies to scenarios such as domestic product listing, cross-border distribution, and product copy localization. The API uses synchronous calls and processes one copy type for one product per request.
|
|
652
726
|
* # Scenarios
|
|
653
727
|
* | **Scenario** | **Description** |
|
|
654
728
|
* | --- | --- |
|
|
655
|
-
* | Same-platform localization | Select rewrite
|
|
729
|
+
* | Same-platform localization | Select rewrite and translate as needed to retain the original facts and type structure. |
|
|
656
730
|
* | Cross-platform content adaptation | Select the target platform to generate or rewrite content according to its configuration limits. The source platform of the input is not required. |
|
|
657
|
-
* | New product material
|
|
658
|
-
* | Batch operation tool integration | The caller submits requests product by product. The workflow itself does not provide batch task or
|
|
731
|
+
* | New product material production | Select generate to generate the target type based on product materials. Categories and attributes can be used to supplement facts. |
|
|
732
|
+
* | Batch operation tool integration | The caller submits requests product by product. The workflow itself does not provide batch task or queue APIs. |
|
|
659
733
|
* # Features
|
|
660
734
|
* ## Core capabilities
|
|
661
|
-
* This capability supports the
|
|
735
|
+
* This capability supports the production of different copy content types in domestic and cross-border e-commerce scenarios. It can produce titles, detailed descriptions, keywords, highlights, and descriptions that adapt to the content rules (length requirements and writing styles) of different platforms, and supports cross-language production.
|
|
662
736
|
* | Content type | Platform | | | | | | Target language |
|
|
663
737
|
* | --- | --- | --- | --- | --- | --- | --- | --- |
|
|
664
738
|
* | | Amazon | Temu | TikTok | Shopify | Wildberries | Tmall |
|
|
@@ -668,19 +742,19 @@ export default class Client extends OpenApi {
|
|
|
668
742
|
* | **bulletPoint** | ✓ | | | ✓ | | |
|
|
669
743
|
* | **keywords** | ✓ | | | | | |
|
|
670
744
|
* | **description** | ✓ | ✓ | ✓ | ✓ | ✓ | |
|
|
671
|
-
* Based on the
|
|
745
|
+
* Based on the content inputs provided by users, two production modes are supported:
|
|
672
746
|
* | **Mode** | **Description** | **Recommended scenario** |
|
|
673
747
|
* | --- | --- | --- |
|
|
674
|
-
* | Generate | Reorganizes and writes copy based on product
|
|
675
|
-
* | Rewrite | Retains the original information and main structure
|
|
748
|
+
* | Generate | Reorganizes and writes copy based on product materials. | Only product parameters, attributes, or selling points are available, or other types of product materials are available, and new titles, keywords, product descriptions, and other copy need to be created. |
|
|
749
|
+
* | Rewrite | Retains the original information and main structure, and optimizes the expression. | Existing product copy is available, and you want to adjust the wording, improve readability, or localize it with translation. |
|
|
676
750
|
* # Examples
|
|
677
751
|
* The following examples use the Amazon platform:
|
|
678
752
|
* | **Content type** | **Source language** | **Source content** | **Target language** | **Generated result** | **Capability advantage** |
|
|
679
753
|
* | --- | --- | --- | --- | --- | --- |
|
|
680
|
-
* | bulletPoint | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | [Vielseitiges Harz-Filtersystem\\] Silikontrichter und Metallfiltergitter für 3D-Druck; Einfüllen von gebrauchtem lichtempfindlichem Harz in Flaschen mit 15 mm Halsweite | Extracts core selling points, retains key information such as bottle neck size, and presents
|
|
754
|
+
* | bulletPoint | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | [Vielseitiges Harz-Filtersystem\\] Silikontrichter und Metallfiltergitter für 3D-Druck; Einfüllen von gebrauchtem lichtempfindlichem Harz in Flaschen mit 15 mm Halsweite | Extracts core selling points, retains key information such as bottle neck size, and presents it in German bullet points for quick reading. |
|
|
681
755
|
* | description | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | [Vielseitiges Harz-Filtrationssystem\\] Diese Kombination aus Silikontrichter und Metallfilternetz richtet sich an alle, die mit 3D-Druck arbeiten. Der flexible Silikontrichter passt sicher auf Standardflaschen mit einer Halsweite von 15 mm und ermöglicht ein sauberes Zurückfüllen von gebrauchtem lichtempfindlichem Harz ohne Kleckern. Das feine Metallfilter fängt verfestigte Partikel zuverlässig ab, sodass Ihr Harz frei von Verunreinigungen bleibt und seine Nutzbarkeit erhalten wird. Die robuste Konstruktion des Filters unterstützt eine gleichmäßige Durchflussrate beim Umfüllen. | Organizes the product purpose, usage, and filtration features into a coherent German introduction for easy understanding. |
|
|
682
|
-
* | highlight | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | [Vielseitiges Harz-Filtrationssystem\\] Silikontrichter, Metallfilternetz, für 3D-Druck-Harz |
|
|
683
|
-
* | keywords | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | Silikontrichter Metallfilter Harz Filterungssystem 3D Drucker Harz umfüllen Metall Sieb für Photosensitive Harze | Extracts German search terms related to materials, categories, and purposes
|
|
756
|
+
* | highlight | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | [Vielseitiges Harz-Filtrationssystem\\] Silikontrichter, Metallfilternetz, für 3D-Druck-Harz | Simplifies long materials, highlights core components and purposes, and makes it easy to grasp product features at a glance. |
|
|
757
|
+
* | keywords | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | Silikontrichter Metallfilter Harz Filterungssystem 3D Drucker Harz umfüllen Metall Sieb für Photosensitive Harze | Extracts German search terms related to materials, categories, and purposes to reduce manual sorting and translation. |
|
|
684
758
|
* | title | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | Silikontrichter mit Metallfilter für 3D-Druck-Harz | Extracts the product name, core components, and purpose to generate a concise and clear German title. |
|
|
685
759
|
*
|
|
686
760
|
* @param request - GenerateProductContentRequest
|
|
@@ -804,24 +878,24 @@ export default class Client extends OpenApi {
|
|
|
804
878
|
*/
|
|
805
879
|
imageMatting(request: $_model.ImageMattingRequest): Promise<$_model.ImageMattingResponse>;
|
|
806
880
|
/**
|
|
807
|
-
*
|
|
881
|
+
* Automatically identifies the salient subject in an image, separates the subject from the background, and returns the subject image with the background removed. This operation also provides multiple background options and custom size options to optimize product displays.
|
|
808
882
|
*
|
|
809
883
|
* @remarks
|
|
810
884
|
* # Scenarios
|
|
811
885
|
* * Supports secondary editing of materials: After separating the image subject from the background, you can further edit the image.
|
|
812
886
|
*
|
|
813
|
-
* * Improves material processing efficiency: Quickly extracts the subjects of various material images
|
|
887
|
+
* * Improves material processing efficiency: Quickly extracts the subjects of various material images for background replacement, improving the production efficiency of advertising images and marketing posters.
|
|
814
888
|
* # Features.
|
|
815
|
-
* #### 1. One-click
|
|
816
|
-
* * **AI-based automatic recognition**: Based on deep learning models, intelligently distinguishes foreground subjects (portraits, products, objects, etc.) from the background without manual outlining.
|
|
889
|
+
* #### 1. One-click accurate subject recognition
|
|
890
|
+
* * **AI-based automatic recognition**: Based on deep learning models, it intelligently distinguishes foreground subjects (portraits, products, objects, etc.) from the background without manual outlining.
|
|
817
891
|
*
|
|
818
|
-
* * **Multi-scenario adaptation**: Supports
|
|
892
|
+
* * **Multi-scenario adaptation**: Supports accurate segmentation in complex scenarios (such as hair, transparent objects, and fur edges) with an accuracy rate of over 95%.
|
|
819
893
|
* #### 2. Intelligent edge optimization
|
|
820
894
|
* * **Detail-level processing**: Performs automatic optimization on edge jaggies and semi-transparent areas (such as smoke and glass) to retain natural transition effects.
|
|
821
895
|
* #### 3. Multi-format output and background operations
|
|
822
896
|
* * **Transparent background export**: Directly generates PNG images with transparent backgrounds and white backgrounds, adapting to e-commerce and design scenarios.
|
|
823
897
|
*
|
|
824
|
-
* * **
|
|
898
|
+
* * **Custom background color support**
|
|
825
899
|
* # Effect comparison
|
|
826
900
|
* | **Original image (input)** | **Result image (output)** |
|
|
827
901
|
* | --- | --- |
|
|
@@ -835,24 +909,24 @@ export default class Client extends OpenApi {
|
|
|
835
909
|
*/
|
|
836
910
|
imageMattingAsyncWithOptions(request: $_model.ImageMattingAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageMattingAsyncResponse>;
|
|
837
911
|
/**
|
|
838
|
-
*
|
|
912
|
+
* Automatically identifies the salient subject in an image, separates the subject from the background, and returns the subject image with the background removed. This operation also provides multiple background options and custom size options to optimize product displays.
|
|
839
913
|
*
|
|
840
914
|
* @remarks
|
|
841
915
|
* # Scenarios
|
|
842
916
|
* * Supports secondary editing of materials: After separating the image subject from the background, you can further edit the image.
|
|
843
917
|
*
|
|
844
|
-
* * Improves material processing efficiency: Quickly extracts the subjects of various material images
|
|
918
|
+
* * Improves material processing efficiency: Quickly extracts the subjects of various material images for background replacement, improving the production efficiency of advertising images and marketing posters.
|
|
845
919
|
* # Features.
|
|
846
|
-
* #### 1. One-click
|
|
847
|
-
* * **AI-based automatic recognition**: Based on deep learning models, intelligently distinguishes foreground subjects (portraits, products, objects, etc.) from the background without manual outlining.
|
|
920
|
+
* #### 1. One-click accurate subject recognition
|
|
921
|
+
* * **AI-based automatic recognition**: Based on deep learning models, it intelligently distinguishes foreground subjects (portraits, products, objects, etc.) from the background without manual outlining.
|
|
848
922
|
*
|
|
849
|
-
* * **Multi-scenario adaptation**: Supports
|
|
923
|
+
* * **Multi-scenario adaptation**: Supports accurate segmentation in complex scenarios (such as hair, transparent objects, and fur edges) with an accuracy rate of over 95%.
|
|
850
924
|
* #### 2. Intelligent edge optimization
|
|
851
925
|
* * **Detail-level processing**: Performs automatic optimization on edge jaggies and semi-transparent areas (such as smoke and glass) to retain natural transition effects.
|
|
852
926
|
* #### 3. Multi-format output and background operations
|
|
853
927
|
* * **Transparent background export**: Directly generates PNG images with transparent backgrounds and white backgrounds, adapting to e-commerce and design scenarios.
|
|
854
928
|
*
|
|
855
|
-
* * **
|
|
929
|
+
* * **Custom background color support**
|
|
856
930
|
* # Effect comparison
|
|
857
931
|
* | **Original image (input)** | **Result image (output)** |
|
|
858
932
|
* | --- | --- |
|
|
@@ -1016,15 +1090,15 @@ export default class Client extends OpenApi {
|
|
|
1016
1090
|
*/
|
|
1017
1091
|
imageRecognition(request: $_model.ImageRecognitionRequest): Promise<$_model.ImageRecognitionResponse>;
|
|
1018
1092
|
/**
|
|
1019
|
-
* Identifies specific elements in e-commerce images.
|
|
1093
|
+
* Identifies specific elements in e-commerce images. This API extracts image details to help users quickly identify text, logos, watermarks, and text-containing color blocks in the main subject and background, significantly improving the efficiency and accuracy of image filtering.
|
|
1020
1094
|
*
|
|
1021
1095
|
* @remarks
|
|
1022
1096
|
* # Scenarios
|
|
1023
1097
|
* 1. Intelligent image filtering and optimization:
|
|
1024
|
-
* Merchants and platforms can use the intelligent element recognition API to filter images and automatically identify images containing specific elements such as watermarks and logos. After filtering, they can
|
|
1098
|
+
* Merchants and platforms can use the intelligent element recognition API to filter images and automatically identify images containing specific elements such as watermarks and logos. After filtering, they can call the intelligent elimination API to optimize these images, improve image quality, and shorten the product release cycle.
|
|
1025
1099
|
* 2. Automated image processing and efficiency improvement:
|
|
1026
1100
|
* Through the intelligent element recognition API, merchants and platforms can automate the image processing workflow and automatically identify and mark image elements that need to be optimized. This workflow reduces manual intervention and improves the efficiency of image processing.
|
|
1027
|
-
* #
|
|
1101
|
+
* # Feature description
|
|
1028
1102
|
* **1. Definitions of image subject, image background, text, logo, watermark, and text-containing color block: For details, see the relevant examples in the elimination documentation (reserved text link).**
|
|
1029
1103
|
* * Image subject: The core product area in the image.
|
|
1030
1104
|
*
|
|
@@ -1034,11 +1108,11 @@ export default class Client extends OpenApi {
|
|
|
1034
1108
|
*
|
|
1035
1109
|
* * Logo: A logo or trademark.
|
|
1036
1110
|
*
|
|
1037
|
-
* * Watermark: Monochrome transparent text, logos, images, URLs,
|
|
1111
|
+
* * Watermark: Monochrome transparent text, logos, images, URLs, store names, etc.
|
|
1038
1112
|
*
|
|
1039
|
-
* * Text-containing color block: A color block containing text outside the subject.
|
|
1113
|
+
* * Text-containing color block: A color block containing text outside the main subject.
|
|
1040
1114
|
*
|
|
1041
|
-
* **2. The
|
|
1115
|
+
* **2. The intelligent element recognition API provides the following features:**
|
|
1042
1116
|
* * Element recognition: Identifies whether elements such as text, logos, watermarks, and text-containing color blocks exist in the image subject and background.
|
|
1043
1117
|
*
|
|
1044
1118
|
* * Workflow collaboration: Used in combination with the intelligent elimination API. The intelligent element recognition API first identifies the elements to be removed, and then the intelligent elimination API effectively removes them to ensure the accuracy and efficiency of image processing.
|
|
@@ -1091,15 +1165,15 @@ export default class Client extends OpenApi {
|
|
|
1091
1165
|
*/
|
|
1092
1166
|
imageRecognitionAsyncWithOptions(tmpReq: $_model.ImageRecognitionAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageRecognitionAsyncResponse>;
|
|
1093
1167
|
/**
|
|
1094
|
-
* Identifies specific elements in e-commerce images.
|
|
1168
|
+
* Identifies specific elements in e-commerce images. This API extracts image details to help users quickly identify text, logos, watermarks, and text-containing color blocks in the main subject and background, significantly improving the efficiency and accuracy of image filtering.
|
|
1095
1169
|
*
|
|
1096
1170
|
* @remarks
|
|
1097
1171
|
* # Scenarios
|
|
1098
1172
|
* 1. Intelligent image filtering and optimization:
|
|
1099
|
-
* Merchants and platforms can use the intelligent element recognition API to filter images and automatically identify images containing specific elements such as watermarks and logos. After filtering, they can
|
|
1173
|
+
* Merchants and platforms can use the intelligent element recognition API to filter images and automatically identify images containing specific elements such as watermarks and logos. After filtering, they can call the intelligent elimination API to optimize these images, improve image quality, and shorten the product release cycle.
|
|
1100
1174
|
* 2. Automated image processing and efficiency improvement:
|
|
1101
1175
|
* Through the intelligent element recognition API, merchants and platforms can automate the image processing workflow and automatically identify and mark image elements that need to be optimized. This workflow reduces manual intervention and improves the efficiency of image processing.
|
|
1102
|
-
* #
|
|
1176
|
+
* # Feature description
|
|
1103
1177
|
* **1. Definitions of image subject, image background, text, logo, watermark, and text-containing color block: For details, see the relevant examples in the elimination documentation (reserved text link).**
|
|
1104
1178
|
* * Image subject: The core product area in the image.
|
|
1105
1179
|
*
|
|
@@ -1109,11 +1183,11 @@ export default class Client extends OpenApi {
|
|
|
1109
1183
|
*
|
|
1110
1184
|
* * Logo: A logo or trademark.
|
|
1111
1185
|
*
|
|
1112
|
-
* * Watermark: Monochrome transparent text, logos, images, URLs,
|
|
1186
|
+
* * Watermark: Monochrome transparent text, logos, images, URLs, store names, etc.
|
|
1113
1187
|
*
|
|
1114
|
-
* * Text-containing color block: A color block containing text outside the subject.
|
|
1188
|
+
* * Text-containing color block: A color block containing text outside the main subject.
|
|
1115
1189
|
*
|
|
1116
|
-
* **2. The
|
|
1190
|
+
* **2. The intelligent element recognition API provides the following features:**
|
|
1117
1191
|
* * Element recognition: Identifies whether elements such as text, logos, watermarks, and text-containing color blocks exist in the image subject and background.
|
|
1118
1192
|
*
|
|
1119
1193
|
* * Workflow collaboration: Used in combination with the intelligent elimination API. The intelligent element recognition API first identifies the elements to be removed, and then the intelligent elimination API effectively removes them to ensure the accuracy and efficiency of image processing.
|
|
@@ -1228,27 +1302,27 @@ export default class Client extends OpenApi {
|
|
|
1228
1302
|
*/
|
|
1229
1303
|
imageRemovalPro(request: $_model.ImageRemovalProRequest): Promise<$_model.ImageRemovalProResponse>;
|
|
1230
1304
|
/**
|
|
1231
|
-
*
|
|
1305
|
+
* Provides intelligent image erasure tailored for e-commerce images, automatically identifying and removing text, specific names, transparent text blocks, and unwanted overlays. It allows you to specify objects to remove as needed, enabling efficient and precise processing of large image batches and simplifying image editing workflows.
|
|
1232
1306
|
*
|
|
1233
1307
|
* @remarks
|
|
1234
1308
|
* ## Scenarios
|
|
1235
|
-
* * **Efficient e-commerce
|
|
1309
|
+
* * **Efficient processing of e-commerce images:**
|
|
1236
1310
|
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
1237
|
-
* * **
|
|
1238
|
-
*
|
|
1311
|
+
* * **Synchronization of product information across multiple platforms:**
|
|
1312
|
+
* When merchants list products on different e-commerce platforms, they can quickly remove specific text and watermarks to comply with the image specifications of different platforms.
|
|
1239
1313
|
* ## Features
|
|
1240
|
-
* 1. First,
|
|
1314
|
+
* 1. First, clarify the definitions of the image subject and the image background. When specifying the objects to remove, you can choose to remove them from the image subject or the image background. Both API and editor integration methods are supported.
|
|
1241
1315
|
*
|
|
1242
|
-
* 1. Image subject:
|
|
1316
|
+
* 1. Image subject: The core product area in the image.
|
|
1243
1317
|
*
|
|
1244
|
-
* 2. Image background:
|
|
1318
|
+
* 2. Image background: The rest of the image excluding the product subject.
|
|
1245
1319
|
*
|
|
1246
|
-
* 2. Second, the objects to be removed
|
|
1247
|
-
* ##
|
|
1320
|
+
* 2. Second, the objects to be removed support the following four types: text, specific names, transparent text blocks, and watermarks. Refer to the following examples to clarify your requirements and perform targeted operations:
|
|
1321
|
+
* ## Before and after
|
|
1248
1322
|
* | **Original image** | **Processed image** |
|
|
1249
1323
|
* | --- | --- |
|
|
1250
|
-
* |  |  |
|
|
1325
|
+
* |  |  |
|
|
1252
1326
|
*
|
|
1253
1327
|
* @param request - ImageRemovalProAsyncRequest
|
|
1254
1328
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -1256,27 +1330,27 @@ export default class Client extends OpenApi {
|
|
|
1256
1330
|
*/
|
|
1257
1331
|
imageRemovalProAsyncWithOptions(request: $_model.ImageRemovalProAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageRemovalProAsyncResponse>;
|
|
1258
1332
|
/**
|
|
1259
|
-
*
|
|
1333
|
+
* Provides intelligent image erasure tailored for e-commerce images, automatically identifying and removing text, specific names, transparent text blocks, and unwanted overlays. It allows you to specify objects to remove as needed, enabling efficient and precise processing of large image batches and simplifying image editing workflows.
|
|
1260
1334
|
*
|
|
1261
1335
|
* @remarks
|
|
1262
1336
|
* ## Scenarios
|
|
1263
|
-
* * **Efficient e-commerce
|
|
1337
|
+
* * **Efficient processing of e-commerce images:**
|
|
1264
1338
|
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
1265
|
-
* * **
|
|
1266
|
-
*
|
|
1339
|
+
* * **Synchronization of product information across multiple platforms:**
|
|
1340
|
+
* When merchants list products on different e-commerce platforms, they can quickly remove specific text and watermarks to comply with the image specifications of different platforms.
|
|
1267
1341
|
* ## Features
|
|
1268
|
-
* 1. First,
|
|
1342
|
+
* 1. First, clarify the definitions of the image subject and the image background. When specifying the objects to remove, you can choose to remove them from the image subject or the image background. Both API and editor integration methods are supported.
|
|
1269
1343
|
*
|
|
1270
|
-
* 1. Image subject:
|
|
1344
|
+
* 1. Image subject: The core product area in the image.
|
|
1271
1345
|
*
|
|
1272
|
-
* 2. Image background:
|
|
1346
|
+
* 2. Image background: The rest of the image excluding the product subject.
|
|
1273
1347
|
*
|
|
1274
|
-
* 2. Second, the objects to be removed
|
|
1275
|
-
* ##
|
|
1348
|
+
* 2. Second, the objects to be removed support the following four types: text, specific names, transparent text blocks, and watermarks. Refer to the following examples to clarify your requirements and perform targeted operations:
|
|
1349
|
+
* ## Before and after
|
|
1276
1350
|
* | **Original image** | **Processed image** |
|
|
1277
1351
|
* | --- | --- |
|
|
1278
|
-
* |  |  |
|
|
1353
|
+
* |  |  |
|
|
1280
1354
|
*
|
|
1281
1355
|
* @param request - ImageRemovalProAsyncRequest
|
|
1282
1356
|
* @returns ImageRemovalProAsyncResponse
|
|
@@ -1466,35 +1540,35 @@ export default class Client extends OpenApi {
|
|
|
1466
1540
|
*/
|
|
1467
1541
|
imageRemove(request: $_model.ImageRemoveRequest): Promise<$_model.ImageRemoveResponse>;
|
|
1468
1542
|
/**
|
|
1469
|
-
*
|
|
1543
|
+
* Provides intelligent object removal tailored for e-commerce images. It automatically identifies and removes text, specific names, transparent text blocks, and watermarks. You can also specify objects for removal as needed, enabling efficient and accurate processing of large image batches and simplifying image editing workflows.
|
|
1470
1544
|
*
|
|
1471
1545
|
* @remarks
|
|
1472
1546
|
* ## Scenarios
|
|
1473
1547
|
* * **Efficient processing of e-commerce images:**
|
|
1474
1548
|
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
1475
1549
|
* * **Multi-platform product information synchronization:**
|
|
1476
|
-
* When merchants
|
|
1550
|
+
* When merchants list products on different e-commerce platforms, they can quickly remove specific text and watermarks to comply with the image specifications of different platforms.
|
|
1477
1551
|
* * **Marketing material preparation:**
|
|
1478
1552
|
* Merchants can easily remove original promotional information and quickly update it with the latest campaign information.
|
|
1479
|
-
* > Note: Merchants or platforms can
|
|
1553
|
+
* > Note: Merchants or platforms can remove impurities from images in batches to optimize image quality. Use this API in combination with the Intelligent Recognition API (coming soon) to first filter images containing text, specific names, transparent text blocks, and watermarks, and then use the Intelligent Erasure API for batch removal. The Intelligent Recognition API focuses on recognition, while the Intelligent Erasure API focuses on erasure. Calling them in sequence maximizes the erasure effect and reduces false removals and false recognitions.
|
|
1480
1554
|
* ## Features
|
|
1481
|
-
* 1. First, clarify the definitions of the image subject and the image background. In actual use, when specifying the objects to remove, you can choose whether the removal scope is the image subject or the image background
|
|
1555
|
+
* 1. First, clarify the definitions of the image subject and the image background. In actual use, when specifying the objects to remove, you can choose whether the removal scope is the image subject or the image background. Both API and editor integration methods are supported to meet different needs.
|
|
1482
1556
|
*
|
|
1483
1557
|
* 1. Image subject: the core product area in the image.
|
|
1484
1558
|
*
|
|
1485
1559
|
* 2. Image background: the rest of the image other than the product subject.
|
|
1486
1560
|
*
|
|
1487
|
-
* 2. Second, the
|
|
1561
|
+
* 2. Second, the following three types of objects can be removed:
|
|
1488
1562
|
*
|
|
1489
|
-
* 1.
|
|
1563
|
+
* 1. Select by type: You can select text, specific names, transparent text blocks, and watermarks. Refer to the following examples to clarify your requirements and perform targeted operations.
|
|
1490
1564
|
*
|
|
1491
|
-
* 2. (Upgraded)
|
|
1565
|
+
* 2. (Upgraded) Specify images to remove: You can specify multiple images at a time.
|
|
1492
1566
|
*
|
|
1493
|
-
* 3. (Upgraded)
|
|
1567
|
+
* 3. (Upgraded) Specify text to remove: You can specify multiple text strings at a time.
|
|
1494
1568
|
*
|
|
1495
|
-
* Processing flow:
|
|
1569
|
+
* Processing flow: Pass the original image URL -> The OCR and VLM models detect text or image positions -> Determine the coordinates of the area to be inpainted -> AI inpainting generates a clean image -> Return the result image URL.
|
|
1496
1570
|
* ## Effect comparison
|
|
1497
|
-
* | **Objects that can be removed
|
|
1571
|
+
* | **Objects that can be removed** | **Original image** | **Processed image** |
|
|
1498
1572
|
* | --- | --- | --- |
|
|
1499
1573
|
* | Text | * Involves the image subject area
|
|
1500
1574
|
*
|
|
@@ -1544,8 +1618,8 @@ export default class Client extends OpenApi {
|
|
|
1544
1618
|
* * Does not involve the image subject area
|
|
1545
1619
|
*
|
|
1546
1620
|
*  |
|
|
1547
|
-
* | Specified image element
|
|
1548
|
-
* | Specified text
|
|
1621
|
+
* | Specified image element removal (supports multiple image URLs) |  |  |
|
|
1622
|
+
* | Specified text removal (supports multiple text strings) |  |  |
|
|
1549
1623
|
*
|
|
1550
1624
|
* @param tmpReq - ImageRemoveAsyncRequest
|
|
1551
1625
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -1553,35 +1627,35 @@ export default class Client extends OpenApi {
|
|
|
1553
1627
|
*/
|
|
1554
1628
|
imageRemoveAsyncWithOptions(tmpReq: $_model.ImageRemoveAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageRemoveAsyncResponse>;
|
|
1555
1629
|
/**
|
|
1556
|
-
*
|
|
1630
|
+
* Provides intelligent object removal tailored for e-commerce images. It automatically identifies and removes text, specific names, transparent text blocks, and watermarks. You can also specify objects for removal as needed, enabling efficient and accurate processing of large image batches and simplifying image editing workflows.
|
|
1557
1631
|
*
|
|
1558
1632
|
* @remarks
|
|
1559
1633
|
* ## Scenarios
|
|
1560
1634
|
* * **Efficient processing of e-commerce images:**
|
|
1561
1635
|
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
1562
1636
|
* * **Multi-platform product information synchronization:**
|
|
1563
|
-
* When merchants
|
|
1637
|
+
* When merchants list products on different e-commerce platforms, they can quickly remove specific text and watermarks to comply with the image specifications of different platforms.
|
|
1564
1638
|
* * **Marketing material preparation:**
|
|
1565
1639
|
* Merchants can easily remove original promotional information and quickly update it with the latest campaign information.
|
|
1566
|
-
* > Note: Merchants or platforms can
|
|
1640
|
+
* > Note: Merchants or platforms can remove impurities from images in batches to optimize image quality. Use this API in combination with the Intelligent Recognition API (coming soon) to first filter images containing text, specific names, transparent text blocks, and watermarks, and then use the Intelligent Erasure API for batch removal. The Intelligent Recognition API focuses on recognition, while the Intelligent Erasure API focuses on erasure. Calling them in sequence maximizes the erasure effect and reduces false removals and false recognitions.
|
|
1567
1641
|
* ## Features
|
|
1568
|
-
* 1. First, clarify the definitions of the image subject and the image background. In actual use, when specifying the objects to remove, you can choose whether the removal scope is the image subject or the image background
|
|
1642
|
+
* 1. First, clarify the definitions of the image subject and the image background. In actual use, when specifying the objects to remove, you can choose whether the removal scope is the image subject or the image background. Both API and editor integration methods are supported to meet different needs.
|
|
1569
1643
|
*
|
|
1570
1644
|
* 1. Image subject: the core product area in the image.
|
|
1571
1645
|
*
|
|
1572
1646
|
* 2. Image background: the rest of the image other than the product subject.
|
|
1573
1647
|
*
|
|
1574
|
-
* 2. Second, the
|
|
1648
|
+
* 2. Second, the following three types of objects can be removed:
|
|
1575
1649
|
*
|
|
1576
|
-
* 1.
|
|
1650
|
+
* 1. Select by type: You can select text, specific names, transparent text blocks, and watermarks. Refer to the following examples to clarify your requirements and perform targeted operations.
|
|
1577
1651
|
*
|
|
1578
|
-
* 2. (Upgraded)
|
|
1652
|
+
* 2. (Upgraded) Specify images to remove: You can specify multiple images at a time.
|
|
1579
1653
|
*
|
|
1580
|
-
* 3. (Upgraded)
|
|
1654
|
+
* 3. (Upgraded) Specify text to remove: You can specify multiple text strings at a time.
|
|
1581
1655
|
*
|
|
1582
|
-
* Processing flow:
|
|
1656
|
+
* Processing flow: Pass the original image URL -> The OCR and VLM models detect text or image positions -> Determine the coordinates of the area to be inpainted -> AI inpainting generates a clean image -> Return the result image URL.
|
|
1583
1657
|
* ## Effect comparison
|
|
1584
|
-
* | **Objects that can be removed
|
|
1658
|
+
* | **Objects that can be removed** | **Original image** | **Processed image** |
|
|
1585
1659
|
* | --- | --- | --- |
|
|
1586
1660
|
* | Text | * Involves the image subject area
|
|
1587
1661
|
*
|
|
@@ -1631,8 +1705,8 @@ export default class Client extends OpenApi {
|
|
|
1631
1705
|
* * Does not involve the image subject area
|
|
1632
1706
|
*
|
|
1633
1707
|
*  |
|
|
1634
|
-
* | Specified image element
|
|
1635
|
-
* | Specified text
|
|
1708
|
+
* | Specified image element removal (supports multiple image URLs) |  |  |
|
|
1709
|
+
* | Specified text removal (supports multiple text strings) |  |  |
|
|
1636
1710
|
*
|
|
1637
1711
|
* @param request - ImageRemoveAsyncRequest
|
|
1638
1712
|
* @returns ImageRemoveAsyncResponse
|
|
@@ -1710,17 +1784,17 @@ export default class Client extends OpenApi {
|
|
|
1710
1784
|
*/
|
|
1711
1785
|
imageTranslationPlus(request: $_model.ImageTranslationPlusRequest): Promise<$_model.ImageTranslationPlusResponse>;
|
|
1712
1786
|
/**
|
|
1713
|
-
*
|
|
1787
|
+
* Translates e-commerce images by using the Image Translation Plus edition. This edition adopts the Mixture of Experts (MoE) architecture and delivers higher translation accuracy for multiple minor languages compared with the Lite and Pro editions.
|
|
1714
1788
|
*
|
|
1715
1789
|
* @remarks
|
|
1716
1790
|
* ## Scenarios
|
|
1717
1791
|
* Main images and detail images for cross-border e-commerce.
|
|
1718
1792
|
* ## Features
|
|
1719
|
-
* * **Product subject information protection**:
|
|
1793
|
+
* * **Product subject information protection**: Allows you to specify whether to translate the text on the product subject. This helps you protect the subject information, such as the embedded product name, from being translated.
|
|
1720
1794
|
*
|
|
1721
|
-
* * **Brand name protection**:
|
|
1795
|
+
* * **Brand name protection**: Allows you to specify whether to translate the brand names in the image. This helps you protect the brand name information from being translated.
|
|
1722
1796
|
*
|
|
1723
|
-
* * **Translation intervention**:
|
|
1797
|
+
* * **Translation intervention**: Allows you to customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), and skipping translation (ABC-null). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when you call the API operation. This meets your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention words. If you need more, contact the platform for assistance.
|
|
1724
1798
|
* ## Supported language pairs
|
|
1725
1799
|
* | **No.** | **Source language** | | **Target language** | |
|
|
1726
1800
|
* | --- | --- | --- | --- | --- |
|
|
@@ -1738,8 +1812,8 @@ export default class Client extends OpenApi {
|
|
|
1738
1812
|
* | 11 | en | English | de | German |
|
|
1739
1813
|
* | 12 | en | English | pl | Polish |
|
|
1740
1814
|
* ## Preparations and call process
|
|
1741
|
-
* Image Translation Plus and other
|
|
1742
|
-
* For the
|
|
1815
|
+
* The asynchronous API operations for Image Translation Plus and other features share the same result retrieval process, RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
1816
|
+
* For the asynchronous call process, subscription rules, message formats and encryption protocols, and detailed integration solutions, refer to [Asynchronous API operation call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
1743
1817
|
*
|
|
1744
1818
|
* @param request - ImageTranslationPlusAsyncRequest
|
|
1745
1819
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -1747,17 +1821,17 @@ export default class Client extends OpenApi {
|
|
|
1747
1821
|
*/
|
|
1748
1822
|
imageTranslationPlusAsyncWithOptions(request: $_model.ImageTranslationPlusAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageTranslationPlusAsyncResponse>;
|
|
1749
1823
|
/**
|
|
1750
|
-
*
|
|
1824
|
+
* Translates e-commerce images by using the Image Translation Plus edition. This edition adopts the Mixture of Experts (MoE) architecture and delivers higher translation accuracy for multiple minor languages compared with the Lite and Pro editions.
|
|
1751
1825
|
*
|
|
1752
1826
|
* @remarks
|
|
1753
1827
|
* ## Scenarios
|
|
1754
1828
|
* Main images and detail images for cross-border e-commerce.
|
|
1755
1829
|
* ## Features
|
|
1756
|
-
* * **Product subject information protection**:
|
|
1830
|
+
* * **Product subject information protection**: Allows you to specify whether to translate the text on the product subject. This helps you protect the subject information, such as the embedded product name, from being translated.
|
|
1757
1831
|
*
|
|
1758
|
-
* * **Brand name protection**:
|
|
1832
|
+
* * **Brand name protection**: Allows you to specify whether to translate the brand names in the image. This helps you protect the brand name information from being translated.
|
|
1759
1833
|
*
|
|
1760
|
-
* * **Translation intervention**:
|
|
1834
|
+
* * **Translation intervention**: Allows you to customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), and skipping translation (ABC-null). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when you call the API operation. This meets your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention words. If you need more, contact the platform for assistance.
|
|
1761
1835
|
* ## Supported language pairs
|
|
1762
1836
|
* | **No.** | **Source language** | | **Target language** | |
|
|
1763
1837
|
* | --- | --- | --- | --- | --- |
|
|
@@ -1775,8 +1849,8 @@ export default class Client extends OpenApi {
|
|
|
1775
1849
|
* | 11 | en | English | de | German |
|
|
1776
1850
|
* | 12 | en | English | pl | Polish |
|
|
1777
1851
|
* ## Preparations and call process
|
|
1778
|
-
* Image Translation Plus and other
|
|
1779
|
-
* For the
|
|
1852
|
+
* The asynchronous API operations for Image Translation Plus and other features share the same result retrieval process, RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
1853
|
+
* For the asynchronous call process, subscription rules, message formats and encryption protocols, and detailed integration solutions, refer to [Asynchronous API operation call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
1780
1854
|
*
|
|
1781
1855
|
* @param request - ImageTranslationPlusAsyncRequest
|
|
1782
1856
|
* @returns ImageTranslationPlusAsyncResponse
|
|
@@ -1822,22 +1896,22 @@ export default class Client extends OpenApi {
|
|
|
1822
1896
|
*/
|
|
1823
1897
|
imageTranslationPro(request: $_model.ImageTranslationProRequest): Promise<$_model.ImageTranslationProResponse>;
|
|
1824
1898
|
/**
|
|
1825
|
-
* Translates images by using Image Translation Pro, which is designed
|
|
1899
|
+
* Translates images by using the Image Translation Pro edition, which is designed for e-commerce images, integrates multimodal large model technology for more accurate image understanding, significantly improves translation quality, and continuously expands and optimizes multilingual translation capabilities, supporting more than 400 language pairs including bridged languages.
|
|
1826
1900
|
*
|
|
1827
1901
|
* @remarks
|
|
1828
1902
|
* ## Scenarios
|
|
1829
|
-
* E-commerce product images, marketing images, and images
|
|
1903
|
+
* E-commerce product images, marketing images, and images in various other scenarios.
|
|
1830
1904
|
* ## Features
|
|
1831
|
-
* * Product subject information protection: You can specify whether to translate the text on the product subject. This helps you protect the subject information, such as the product name, from being translated.
|
|
1905
|
+
* * Product subject information protection: You can specify whether to translate the text on the product subject. This helps you protect the subject information, such as the embedded product name, from being translated.
|
|
1832
1906
|
*
|
|
1833
1907
|
* * Secondary editing after translation: You can specify whether to return layout information such as the position, font, and color of the text. This information can be used for secondary editing when you integrate an image editor. The SDK package for the editor is not yet available. Follow platform notifications for updates.
|
|
1834
1908
|
*
|
|
1835
1909
|
* * Brand name protection: You can specify whether to translate brand names in the image. This helps you protect brand name information from being translated.
|
|
1836
1910
|
*
|
|
1837
|
-
* * Translation intervention: You can customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), or omitting the translation (ABC-null
|
|
1911
|
+
* * Translation intervention: You can customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), or omitting the translation (ABC-null). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API, which meets your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention entries. If you need more, contact the platform for assistance.
|
|
1838
1912
|
* ## Preparations and call process
|
|
1839
1913
|
* Image Translation Pro supports both synchronous and asynchronous call methods. This topic describes the asynchronous call API. For synchronous calls, refer to [Image Translation Pro](https://www.alibabacloud.com/help/en/aidge/image-translation-pro).
|
|
1840
|
-
*
|
|
1914
|
+
* Asynchronous APIs for text translation and other capabilities share the same result retrieval process, RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
1841
1915
|
* For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls, refer to [Asynchronous API call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
1842
1916
|
*
|
|
1843
1917
|
* @param request - ImageTranslationProAsyncRequest
|
|
@@ -1846,22 +1920,22 @@ export default class Client extends OpenApi {
|
|
|
1846
1920
|
*/
|
|
1847
1921
|
imageTranslationProAsyncWithOptions(request: $_model.ImageTranslationProAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageTranslationProAsyncResponse>;
|
|
1848
1922
|
/**
|
|
1849
|
-
* Translates images by using Image Translation Pro, which is designed
|
|
1923
|
+
* Translates images by using the Image Translation Pro edition, which is designed for e-commerce images, integrates multimodal large model technology for more accurate image understanding, significantly improves translation quality, and continuously expands and optimizes multilingual translation capabilities, supporting more than 400 language pairs including bridged languages.
|
|
1850
1924
|
*
|
|
1851
1925
|
* @remarks
|
|
1852
1926
|
* ## Scenarios
|
|
1853
|
-
* E-commerce product images, marketing images, and images
|
|
1927
|
+
* E-commerce product images, marketing images, and images in various other scenarios.
|
|
1854
1928
|
* ## Features
|
|
1855
|
-
* * Product subject information protection: You can specify whether to translate the text on the product subject. This helps you protect the subject information, such as the product name, from being translated.
|
|
1929
|
+
* * Product subject information protection: You can specify whether to translate the text on the product subject. This helps you protect the subject information, such as the embedded product name, from being translated.
|
|
1856
1930
|
*
|
|
1857
1931
|
* * Secondary editing after translation: You can specify whether to return layout information such as the position, font, and color of the text. This information can be used for secondary editing when you integrate an image editor. The SDK package for the editor is not yet available. Follow platform notifications for updates.
|
|
1858
1932
|
*
|
|
1859
1933
|
* * Brand name protection: You can specify whether to translate brand names in the image. This helps you protect brand name information from being translated.
|
|
1860
1934
|
*
|
|
1861
|
-
* * Translation intervention: You can customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), or omitting the translation (ABC-null
|
|
1935
|
+
* * Translation intervention: You can customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), or omitting the translation (ABC-null). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API, which meets your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention entries. If you need more, contact the platform for assistance.
|
|
1862
1936
|
* ## Preparations and call process
|
|
1863
1937
|
* Image Translation Pro supports both synchronous and asynchronous call methods. This topic describes the asynchronous call API. For synchronous calls, refer to [Image Translation Pro](https://www.alibabacloud.com/help/en/aidge/image-translation-pro).
|
|
1864
|
-
*
|
|
1938
|
+
* Asynchronous APIs for text translation and other capabilities share the same result retrieval process, RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
1865
1939
|
* For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls, refer to [Asynchronous API call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
1866
1940
|
*
|
|
1867
1941
|
* @param request - ImageTranslationProAsyncRequest
|
|
@@ -1869,22 +1943,22 @@ export default class Client extends OpenApi {
|
|
|
1869
1943
|
*/
|
|
1870
1944
|
imageTranslationProAsync(request: $_model.ImageTranslationProAsyncRequest): Promise<$_model.ImageTranslationProAsyncResponse>;
|
|
1871
1945
|
/**
|
|
1872
|
-
*
|
|
1946
|
+
* Provides image translation tailored for e-commerce, supporting over 400 language pairs, including bridged pairs. Accurately processes complex text layouts within images and ensures translated content aligns with the image context, helping e-commerce platforms and developers easily achieve multilingual conversion and presentation. Additionally, returns layer information such as text position, font, and color to facilitate secondary editing through image editors.
|
|
1873
1947
|
*
|
|
1874
1948
|
* @remarks
|
|
1875
|
-
* # 1. Product
|
|
1876
|
-
* The image translation product is tailored for e-commerce images, supporting over 400 language pairs
|
|
1949
|
+
* # 1. Product introduction
|
|
1950
|
+
* The image translation product is tailored for e-commerce images, supporting over 400 language pairs, including bridged pairs. It accurately processes complex text layouts within images and ensures that the translated content aligns with the image context, helping e-commerce platforms and developers easily achieve multilingual conversion and presentation. Additionally, it returns layer information such as text position, font, and color to facilitate secondary editing through image editors.
|
|
1877
1951
|
* # 2. Scenarios
|
|
1878
1952
|
* E-commerce product images, marketing images, and images for various other scenarios.
|
|
1879
1953
|
* # 3. Features
|
|
1880
|
-
* * **Product subject information protection**: Allows you to
|
|
1954
|
+
* * **Product subject information protection**: Allows you to choose whether to translate the text on the product subject. This helps protect the subject information from being translated, avoiding the translation of embedded information such as product names.
|
|
1881
1955
|
*
|
|
1882
|
-
* * **Brand name protection**: Allows you to
|
|
1956
|
+
* * **Brand name protection**: Allows you to choose whether to translate brand names in the image. This helps protect brand name information from being translated.
|
|
1883
1957
|
*
|
|
1884
|
-
* * **Secondary editing after translation (layer information)**: Allows you to
|
|
1958
|
+
* * **Secondary editing after translation (layer information)**: Allows you to choose whether to return layer information such as text position, font, and color. This information can be used to integrate with image editors for secondary editing of the translation results. For updates on the release of the editor SDK package, refer to platform notifications.
|
|
1885
1959
|
*
|
|
1886
|
-
* * **Translation intervention**: Allows you to customize translation results, including
|
|
1887
|
-
* <props="china">* **Image editor integration**: For more information, see [Image
|
|
1960
|
+
* * **Translation intervention**: Allows you to customize translation results, including do not translate (ABC-ABC), specify translation (ABC-DEF), and skip translation (ABC-null value). This is commonly used in scenarios such as brand word protection. You can achieve this by passing the corresponding intervention glossary ID when calling the API, meeting your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance.
|
|
1961
|
+
* <props="china">* **Image editor integration**: For more information, see [Image translation editor protocol](https://www.alibabacloud.com/help/en/document_detail/3042647.html).
|
|
1888
1962
|
*
|
|
1889
1963
|
* @param request - ImageTranslationStandardRequest
|
|
1890
1964
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -1892,45 +1966,45 @@ export default class Client extends OpenApi {
|
|
|
1892
1966
|
*/
|
|
1893
1967
|
imageTranslationStandardWithOptions(request: $_model.ImageTranslationStandardRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageTranslationStandardResponse>;
|
|
1894
1968
|
/**
|
|
1895
|
-
*
|
|
1969
|
+
* Provides image translation tailored for e-commerce, supporting over 400 language pairs, including bridged pairs. Accurately processes complex text layouts within images and ensures translated content aligns with the image context, helping e-commerce platforms and developers easily achieve multilingual conversion and presentation. Additionally, returns layer information such as text position, font, and color to facilitate secondary editing through image editors.
|
|
1896
1970
|
*
|
|
1897
1971
|
* @remarks
|
|
1898
|
-
* # 1. Product
|
|
1899
|
-
* The image translation product is tailored for e-commerce images, supporting over 400 language pairs
|
|
1972
|
+
* # 1. Product introduction
|
|
1973
|
+
* The image translation product is tailored for e-commerce images, supporting over 400 language pairs, including bridged pairs. It accurately processes complex text layouts within images and ensures that the translated content aligns with the image context, helping e-commerce platforms and developers easily achieve multilingual conversion and presentation. Additionally, it returns layer information such as text position, font, and color to facilitate secondary editing through image editors.
|
|
1900
1974
|
* # 2. Scenarios
|
|
1901
1975
|
* E-commerce product images, marketing images, and images for various other scenarios.
|
|
1902
1976
|
* # 3. Features
|
|
1903
|
-
* * **Product subject information protection**: Allows you to
|
|
1977
|
+
* * **Product subject information protection**: Allows you to choose whether to translate the text on the product subject. This helps protect the subject information from being translated, avoiding the translation of embedded information such as product names.
|
|
1904
1978
|
*
|
|
1905
|
-
* * **Brand name protection**: Allows you to
|
|
1979
|
+
* * **Brand name protection**: Allows you to choose whether to translate brand names in the image. This helps protect brand name information from being translated.
|
|
1906
1980
|
*
|
|
1907
|
-
* * **Secondary editing after translation (layer information)**: Allows you to
|
|
1981
|
+
* * **Secondary editing after translation (layer information)**: Allows you to choose whether to return layer information such as text position, font, and color. This information can be used to integrate with image editors for secondary editing of the translation results. For updates on the release of the editor SDK package, refer to platform notifications.
|
|
1908
1982
|
*
|
|
1909
|
-
* * **Translation intervention**: Allows you to customize translation results, including
|
|
1910
|
-
* <props="china">* **Image editor integration**: For more information, see [Image
|
|
1983
|
+
* * **Translation intervention**: Allows you to customize translation results, including do not translate (ABC-ABC), specify translation (ABC-DEF), and skip translation (ABC-null value). This is commonly used in scenarios such as brand word protection. You can achieve this by passing the corresponding intervention glossary ID when calling the API, meeting your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance.
|
|
1984
|
+
* <props="china">* **Image editor integration**: For more information, see [Image translation editor protocol](https://www.alibabacloud.com/help/en/document_detail/3042647.html).
|
|
1911
1985
|
*
|
|
1912
1986
|
* @param request - ImageTranslationStandardRequest
|
|
1913
1987
|
* @returns ImageTranslationStandardResponse
|
|
1914
1988
|
*/
|
|
1915
1989
|
imageTranslationStandard(request: $_model.ImageTranslationStandardRequest): Promise<$_model.ImageTranslationStandardResponse>;
|
|
1916
1990
|
/**
|
|
1917
|
-
* Translates
|
|
1991
|
+
* Translates e-commerce images and supports over 400 language pairs, including bridged pairs. Accurately processes complex text layouts within images and ensures that the translated content matches the image context, which helps e-commerce platforms and developers easily achieve multilingual conversion and presentation of image content. Additionally, the service returns layer information such as the position, font, and color of text in the image to facilitate secondary editing of translation results by using image editors.
|
|
1918
1992
|
*
|
|
1919
1993
|
* @remarks
|
|
1920
1994
|
* ## Scenarios
|
|
1921
|
-
*
|
|
1995
|
+
* Product images, marketing images, and images for various other scenarios in e-commerce.
|
|
1922
1996
|
* ## Features
|
|
1923
|
-
* * **Product subject information protection**: Allows you to specify whether to translate text on the product subject. This
|
|
1997
|
+
* * **Product subject information protection**: Allows you to specify whether to translate the text on the product subject. This helps protect the subject information from being translated and prevents embedded information such as product names from being translated.
|
|
1924
1998
|
*
|
|
1925
|
-
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image. This
|
|
1999
|
+
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image. This helps protect brand name information from being translated.
|
|
1926
2000
|
*
|
|
1927
|
-
* * **Secondary editing after translation (layer information)**: Allows you to specify whether to return layer information such as
|
|
2001
|
+
* * **Secondary editing after translation (layer information)**: Allows you to specify whether to return layer information such as the position, font, and color of the text. This information can be used to integrate with image editors for secondary editing of translation results. For the release progress of the editor SDK package, refer to platform notifications.
|
|
1928
2002
|
*
|
|
1929
|
-
* * **Translation intervention**: Allows you to customize translation results, including
|
|
2003
|
+
* * **Translation intervention**: Allows you to customize translation results, including no translation (ABC-ABC), specified translation (ABC-DEF), and skip translation (ABC-null value). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API operation to meet your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention words. If you need more, contact the platform for assistance.
|
|
1930
2004
|
* ## Preparations and call process
|
|
1931
|
-
* * Image Translation Standard Edition supports both synchronous and asynchronous
|
|
1932
|
-
* * The asynchronous
|
|
1933
|
-
* * For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls, refer to [Asynchronous API call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
2005
|
+
* * Image Translation Standard Edition supports both synchronous and asynchronous call methods. This topic describes the asynchronous call API operation. For synchronous calls, refer to [Image Translation Standard Edition](https://www.alibabacloud.com/help/en/aidge/image-translation).
|
|
2006
|
+
* * The asynchronous API operations for Image Translation Standard Edition and other features share the same result retrieval process, ApsaraMQ for RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
2007
|
+
* * For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls, refer to [Asynchronous API operation call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
1934
2008
|
*
|
|
1935
2009
|
* @param request - ImageTranslationStandardAsyncRequest
|
|
1936
2010
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -1938,45 +2012,47 @@ export default class Client extends OpenApi {
|
|
|
1938
2012
|
*/
|
|
1939
2013
|
imageTranslationStandardAsyncWithOptions(request: $_model.ImageTranslationStandardAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageTranslationStandardAsyncResponse>;
|
|
1940
2014
|
/**
|
|
1941
|
-
* Translates
|
|
2015
|
+
* Translates e-commerce images and supports over 400 language pairs, including bridged pairs. Accurately processes complex text layouts within images and ensures that the translated content matches the image context, which helps e-commerce platforms and developers easily achieve multilingual conversion and presentation of image content. Additionally, the service returns layer information such as the position, font, and color of text in the image to facilitate secondary editing of translation results by using image editors.
|
|
1942
2016
|
*
|
|
1943
2017
|
* @remarks
|
|
1944
2018
|
* ## Scenarios
|
|
1945
|
-
*
|
|
2019
|
+
* Product images, marketing images, and images for various other scenarios in e-commerce.
|
|
1946
2020
|
* ## Features
|
|
1947
|
-
* * **Product subject information protection**: Allows you to specify whether to translate text on the product subject. This
|
|
2021
|
+
* * **Product subject information protection**: Allows you to specify whether to translate the text on the product subject. This helps protect the subject information from being translated and prevents embedded information such as product names from being translated.
|
|
1948
2022
|
*
|
|
1949
|
-
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image. This
|
|
2023
|
+
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image. This helps protect brand name information from being translated.
|
|
1950
2024
|
*
|
|
1951
|
-
* * **Secondary editing after translation (layer information)**: Allows you to specify whether to return layer information such as
|
|
2025
|
+
* * **Secondary editing after translation (layer information)**: Allows you to specify whether to return layer information such as the position, font, and color of the text. This information can be used to integrate with image editors for secondary editing of translation results. For the release progress of the editor SDK package, refer to platform notifications.
|
|
1952
2026
|
*
|
|
1953
|
-
* * **Translation intervention**: Allows you to customize translation results, including
|
|
2027
|
+
* * **Translation intervention**: Allows you to customize translation results, including no translation (ABC-ABC), specified translation (ABC-DEF), and skip translation (ABC-null value). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API operation to meet your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention words. If you need more, contact the platform for assistance.
|
|
1954
2028
|
* ## Preparations and call process
|
|
1955
|
-
* * Image Translation Standard Edition supports both synchronous and asynchronous
|
|
1956
|
-
* * The asynchronous
|
|
1957
|
-
* * For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls, refer to [Asynchronous API call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
2029
|
+
* * Image Translation Standard Edition supports both synchronous and asynchronous call methods. This topic describes the asynchronous call API operation. For synchronous calls, refer to [Image Translation Standard Edition](https://www.alibabacloud.com/help/en/aidge/image-translation).
|
|
2030
|
+
* * The asynchronous API operations for Image Translation Standard Edition and other features share the same result retrieval process, ApsaraMQ for RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
2031
|
+
* * For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls, refer to [Asynchronous API operation call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
1958
2032
|
*
|
|
1959
2033
|
* @param request - ImageTranslationStandardAsyncRequest
|
|
1960
2034
|
* @returns ImageTranslationStandardAsyncResponse
|
|
1961
2035
|
*/
|
|
1962
2036
|
imageTranslationStandardAsync(request: $_model.ImageTranslationStandardAsyncRequest): Promise<$_model.ImageTranslationStandardAsyncResponse>;
|
|
1963
2037
|
/**
|
|
1964
|
-
* Upscales e-commerce images by intelligently enhancing resolution and details, improving textures and image quality during the upscaling process. Supports high-definition outputs such as 2K and 4K to meet the requirements for product main images, detail images, and marketing materials, and
|
|
2038
|
+
* Upscales e-commerce images by intelligently enhancing resolution and details, improving textures and image quality during the upscaling process. Supports high-definition outputs such as 2K and 4K to meet the requirements for product main images, detail images, and marketing materials, enabling efficient and clear processing of large batches of images to improve product image quality. (Synchronous)
|
|
1965
2039
|
*
|
|
1966
2040
|
* @remarks
|
|
1967
|
-
* # Product
|
|
1968
|
-
* The high-definition upscaling product is customized for e-commerce images. It intelligently enhances image resolution and
|
|
2041
|
+
* # Product Introduction
|
|
2042
|
+
* The high-definition upscaling product is customized for e-commerce images. It intelligently enhances image resolution and detail performance, and provides texture enhancement and image quality optimization during the upscaling procedure. It supports high-definition outputs such as 2K and 4K to meet the high-definition requirements for product main images, detail images, and marketing materials. It enables efficient and clear processing of large batches of images to improve product image quality. (synchronous)
|
|
1969
2043
|
* # Scenarios
|
|
1970
|
-
* * High-definition e-commerce product images: Enhances the resolution and details of product main images, detail images, and marketing materials to make textures and materials clearer
|
|
1971
|
-
*
|
|
1972
|
-
* *
|
|
2044
|
+
* * High-definition e-commerce product images: Enhances the resolution and details of product main images, detail images, and marketing materials to make details such as product textures and materials clearer, improving the quality of product displays.
|
|
2045
|
+
*
|
|
2046
|
+
* * Multi-platform product material adaptation: Upscales existing product images in high definition to meet the image display requirements of different e-commerce platforms, satisfying the material usage needs across multiple platforms and scenarios.
|
|
2047
|
+
*
|
|
2048
|
+
* * Batch optimization of existing images: Enhances existing low-resolution product images in high definition to reduce reshooting and production costs, improving the reuse efficiency of image materials.
|
|
1973
2049
|
* # Features
|
|
1974
|
-
* 1. Intelligent high-definition upscaling: Based on AI image enhancement technology, it improves the resolution and optimizes the details of input images to enhance image clarity and texture
|
|
2050
|
+
* 1. Intelligent high-definition upscaling: Based on AI image enhancement technology, it improves the resolution and optimizes the details of input images to enhance image clarity and texture performance.
|
|
1975
2051
|
*
|
|
1976
2052
|
* 2. Multiple upscaling factors: Supports 2x and 4x upscaling factors, allowing flexible selection based on image quality and business requirements.
|
|
1977
2053
|
*
|
|
1978
2054
|
* 3. Synchronous API calls: Supports synchronous submission of images and retrieval of processing results through APIs, facilitating integration into e-commerce image processing workflows.
|
|
1979
|
-
* #
|
|
2055
|
+
* # Before and after
|
|
1980
2056
|
* | **Original image** | **Upscaled image** |
|
|
1981
2057
|
* | --- | --- |
|
|
1982
2058
|
* |  |  |
|
|
@@ -1987,22 +2063,24 @@ export default class Client extends OpenApi {
|
|
|
1987
2063
|
*/
|
|
1988
2064
|
imageUpscaleWithOptions(request: $_model.ImageUpscaleRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageUpscaleResponse>;
|
|
1989
2065
|
/**
|
|
1990
|
-
* Upscales e-commerce images by intelligently enhancing resolution and details, improving textures and image quality during the upscaling process. Supports high-definition outputs such as 2K and 4K to meet the requirements for product main images, detail images, and marketing materials, and
|
|
2066
|
+
* Upscales e-commerce images by intelligently enhancing resolution and details, improving textures and image quality during the upscaling process. Supports high-definition outputs such as 2K and 4K to meet the requirements for product main images, detail images, and marketing materials, enabling efficient and clear processing of large batches of images to improve product image quality. (Synchronous)
|
|
1991
2067
|
*
|
|
1992
2068
|
* @remarks
|
|
1993
|
-
* # Product
|
|
1994
|
-
* The high-definition upscaling product is customized for e-commerce images. It intelligently enhances image resolution and
|
|
2069
|
+
* # Product Introduction
|
|
2070
|
+
* The high-definition upscaling product is customized for e-commerce images. It intelligently enhances image resolution and detail performance, and provides texture enhancement and image quality optimization during the upscaling procedure. It supports high-definition outputs such as 2K and 4K to meet the high-definition requirements for product main images, detail images, and marketing materials. It enables efficient and clear processing of large batches of images to improve product image quality. (synchronous)
|
|
1995
2071
|
* # Scenarios
|
|
1996
|
-
* * High-definition e-commerce product images: Enhances the resolution and details of product main images, detail images, and marketing materials to make textures and materials clearer
|
|
1997
|
-
*
|
|
1998
|
-
* *
|
|
2072
|
+
* * High-definition e-commerce product images: Enhances the resolution and details of product main images, detail images, and marketing materials to make details such as product textures and materials clearer, improving the quality of product displays.
|
|
2073
|
+
*
|
|
2074
|
+
* * Multi-platform product material adaptation: Upscales existing product images in high definition to meet the image display requirements of different e-commerce platforms, satisfying the material usage needs across multiple platforms and scenarios.
|
|
2075
|
+
*
|
|
2076
|
+
* * Batch optimization of existing images: Enhances existing low-resolution product images in high definition to reduce reshooting and production costs, improving the reuse efficiency of image materials.
|
|
1999
2077
|
* # Features
|
|
2000
|
-
* 1. Intelligent high-definition upscaling: Based on AI image enhancement technology, it improves the resolution and optimizes the details of input images to enhance image clarity and texture
|
|
2078
|
+
* 1. Intelligent high-definition upscaling: Based on AI image enhancement technology, it improves the resolution and optimizes the details of input images to enhance image clarity and texture performance.
|
|
2001
2079
|
*
|
|
2002
2080
|
* 2. Multiple upscaling factors: Supports 2x and 4x upscaling factors, allowing flexible selection based on image quality and business requirements.
|
|
2003
2081
|
*
|
|
2004
2082
|
* 3. Synchronous API calls: Supports synchronous submission of images and retrieval of processing results through APIs, facilitating integration into e-commerce image processing workflows.
|
|
2005
|
-
* #
|
|
2083
|
+
* # Before and after
|
|
2006
2084
|
* | **Original image** | **Upscaled image** |
|
|
2007
2085
|
* | --- | --- |
|
|
2008
2086
|
* |  |  |
|
|
@@ -2035,29 +2113,29 @@ export default class Client extends OpenApi {
|
|
|
2035
2113
|
*/
|
|
2036
2114
|
languageDetect(request: $_model.LanguageDetectRequest): Promise<$_model.LanguageDetectResponse>;
|
|
2037
2115
|
/**
|
|
2038
|
-
*
|
|
2116
|
+
* Inspects the compliance of in-store marketing material displays based on a multimodal large language model (MLLM) for offline retail and channel store inspection scenarios. It evaluates standard materials such as functional table cards, posters, and door-shaped display stands, along with long-tail materials like light cloths, KT boards, floor stickers, and light boxes in actual store photos against inspection rules at the natural language level. The operation outputs structured conclusions and Chinese evidence descriptions that can be directly integrated into business systems. This is a **synchronous** call that returns results in a single request.
|
|
2039
2117
|
*
|
|
2040
2118
|
* @remarks
|
|
2041
2119
|
* ## **Scenarios**
|
|
2042
|
-
* - **
|
|
2120
|
+
* - **Store marketing material compliance inspection**: Automatically determines whether specified marketing materials (feature table cards, posters, door-shaped display stands, etc.) are placed or posted in the store according to the standard display guidelines issued by the headquarters. Identifies typical issues such as missing materials, placement faults, and content mismatch.
|
|
2043
2121
|
*
|
|
2044
|
-
* - **New product
|
|
2122
|
+
* - **New product or campaign material verification**: During new product releases or sales promotions, automatically verifies in batches the listing of campaign materials in actual store photos as required, replacing manual sampling inspections.
|
|
2045
2123
|
*
|
|
2046
|
-
* - **Adaptive dual-image comparison and single-image detection**: A single API supports both
|
|
2124
|
+
* - **Adaptive dual-image comparison and single-image detection**: A single API operation supports both dual-image comparison (reference image + target image, Pattern A) and single-image detection (target image only, Pattern B). An automatic switchover is performed based on whether `ImageRefer` is provided, so callers do not need to distinguish between invoke methods.
|
|
2047
2125
|
* ## **Features**
|
|
2048
|
-
* - **Multi-mode intelligent routing**: Built-in material type parsing capability
|
|
2126
|
+
* - **Multi-mode intelligent routing**: Built-in material type parsing capability. Automatically identifies the target material type based on the natural language text in `Rules` and routes the request to the corresponding material detection pipeline. Callers only need to pass the image URL and rule text. Currently supports routing for four detection items: functional table cards, posters, door-shaped display stands, and other materials. More specific marketing material detection pipelines will be added in the future.
|
|
2049
2127
|
*
|
|
2050
|
-
* - **MLLM semantic
|
|
2128
|
+
* - **MLLM semantic understanding + structured rule collaboration**: Uses a multimodal large language model to perform semantic-level understanding such as material recognition, content comparison, and text OCR. Combines rule cleaning and structured models to break down natural language rules into step-by-step verifiable steps (S1, S2, etc.), ensuring accuracy while maintaining rule flexibility and traceability.
|
|
2051
2129
|
*
|
|
2052
|
-
* - **Structured
|
|
2130
|
+
* - **Structured audit conclusion output**: The output is unified into the structure of `Result.OverallResult` + `Result.Steps[]` + `Result.Evidence`. The overall conclusion is derived from the logical AND of all steps. Each step is independently visible, making it easy to directly drive downstream business systems and support case-level manual review tracing.
|
|
2053
2131
|
*
|
|
2054
|
-
* - **Supported input formats**: Currently supports publicly accessible image URLs.
|
|
2055
|
-
* ## **
|
|
2056
|
-
* - **Synchronous call**:
|
|
2132
|
+
* - **Supported input formats**: Currently supports publicly accessible image URLs. Supports both single-image (Mode B) and dual-image (Mode A) calling formats, with completely identical output structures.
|
|
2133
|
+
* ## **Invoke methods**
|
|
2134
|
+
* - **Synchronous call**: Returns the detection result in a single request without the need for polling. The response uses a unified envelope containing `Code`, `Message`, `RequestId`, `Success`, and `Data`.
|
|
2057
2135
|
*
|
|
2058
|
-
* - **Authentication and signing**: Invoked through the Aidge gateway. Authentication, signing, and common parameters follow the platform
|
|
2136
|
+
* - **Authentication and signing**: Invoked through the Aidge gateway. Authentication, signing, and common parameters follow the unified platform access methods. Refer to the officially published API documentation for the specific request path.
|
|
2059
2137
|
*
|
|
2060
|
-
* - **Timeout settings**: Set the request timeout to no less than the maximum response time of the API
|
|
2138
|
+
* - **Timeout settings**: Set the request timeout to a value no less than the maximum response time of the API operation. Refer to the officially published documentation for the specific value.
|
|
2061
2139
|
*
|
|
2062
2140
|
* @param request - MaterialInspectionRequest
|
|
2063
2141
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -2065,54 +2143,54 @@ export default class Client extends OpenApi {
|
|
|
2065
2143
|
*/
|
|
2066
2144
|
materialInspectionWithOptions(request: $_model.MaterialInspectionRequest, runtime: $dara.RuntimeOptions): Promise<$_model.MaterialInspectionResponse>;
|
|
2067
2145
|
/**
|
|
2068
|
-
*
|
|
2146
|
+
* Inspects the compliance of in-store marketing material displays based on a multimodal large language model (MLLM) for offline retail and channel store inspection scenarios. It evaluates standard materials such as functional table cards, posters, and door-shaped display stands, along with long-tail materials like light cloths, KT boards, floor stickers, and light boxes in actual store photos against inspection rules at the natural language level. The operation outputs structured conclusions and Chinese evidence descriptions that can be directly integrated into business systems. This is a **synchronous** call that returns results in a single request.
|
|
2069
2147
|
*
|
|
2070
2148
|
* @remarks
|
|
2071
2149
|
* ## **Scenarios**
|
|
2072
|
-
* - **
|
|
2150
|
+
* - **Store marketing material compliance inspection**: Automatically determines whether specified marketing materials (feature table cards, posters, door-shaped display stands, etc.) are placed or posted in the store according to the standard display guidelines issued by the headquarters. Identifies typical issues such as missing materials, placement faults, and content mismatch.
|
|
2073
2151
|
*
|
|
2074
|
-
* - **New product
|
|
2152
|
+
* - **New product or campaign material verification**: During new product releases or sales promotions, automatically verifies in batches the listing of campaign materials in actual store photos as required, replacing manual sampling inspections.
|
|
2075
2153
|
*
|
|
2076
|
-
* - **Adaptive dual-image comparison and single-image detection**: A single API supports both
|
|
2154
|
+
* - **Adaptive dual-image comparison and single-image detection**: A single API operation supports both dual-image comparison (reference image + target image, Pattern A) and single-image detection (target image only, Pattern B). An automatic switchover is performed based on whether `ImageRefer` is provided, so callers do not need to distinguish between invoke methods.
|
|
2077
2155
|
* ## **Features**
|
|
2078
|
-
* - **Multi-mode intelligent routing**: Built-in material type parsing capability
|
|
2156
|
+
* - **Multi-mode intelligent routing**: Built-in material type parsing capability. Automatically identifies the target material type based on the natural language text in `Rules` and routes the request to the corresponding material detection pipeline. Callers only need to pass the image URL and rule text. Currently supports routing for four detection items: functional table cards, posters, door-shaped display stands, and other materials. More specific marketing material detection pipelines will be added in the future.
|
|
2079
2157
|
*
|
|
2080
|
-
* - **MLLM semantic
|
|
2158
|
+
* - **MLLM semantic understanding + structured rule collaboration**: Uses a multimodal large language model to perform semantic-level understanding such as material recognition, content comparison, and text OCR. Combines rule cleaning and structured models to break down natural language rules into step-by-step verifiable steps (S1, S2, etc.), ensuring accuracy while maintaining rule flexibility and traceability.
|
|
2081
2159
|
*
|
|
2082
|
-
* - **Structured
|
|
2160
|
+
* - **Structured audit conclusion output**: The output is unified into the structure of `Result.OverallResult` + `Result.Steps[]` + `Result.Evidence`. The overall conclusion is derived from the logical AND of all steps. Each step is independently visible, making it easy to directly drive downstream business systems and support case-level manual review tracing.
|
|
2083
2161
|
*
|
|
2084
|
-
* - **Supported input formats**: Currently supports publicly accessible image URLs.
|
|
2085
|
-
* ## **
|
|
2086
|
-
* - **Synchronous call**:
|
|
2162
|
+
* - **Supported input formats**: Currently supports publicly accessible image URLs. Supports both single-image (Mode B) and dual-image (Mode A) calling formats, with completely identical output structures.
|
|
2163
|
+
* ## **Invoke methods**
|
|
2164
|
+
* - **Synchronous call**: Returns the detection result in a single request without the need for polling. The response uses a unified envelope containing `Code`, `Message`, `RequestId`, `Success`, and `Data`.
|
|
2087
2165
|
*
|
|
2088
|
-
* - **Authentication and signing**: Invoked through the Aidge gateway. Authentication, signing, and common parameters follow the platform
|
|
2166
|
+
* - **Authentication and signing**: Invoked through the Aidge gateway. Authentication, signing, and common parameters follow the unified platform access methods. Refer to the officially published API documentation for the specific request path.
|
|
2089
2167
|
*
|
|
2090
|
-
* - **Timeout settings**: Set the request timeout to no less than the maximum response time of the API
|
|
2168
|
+
* - **Timeout settings**: Set the request timeout to a value no less than the maximum response time of the API operation. Refer to the officially published documentation for the specific value.
|
|
2091
2169
|
*
|
|
2092
2170
|
* @param request - MaterialInspectionRequest
|
|
2093
2171
|
* @returns MaterialInspectionResponse
|
|
2094
2172
|
*/
|
|
2095
2173
|
materialInspection(request: $_model.MaterialInspectionRequest): Promise<$_model.MaterialInspectionResponse>;
|
|
2096
2174
|
/**
|
|
2097
|
-
* Detects
|
|
2175
|
+
* Detects product displays in physical stores based on multimodal large language models (MLLMs) and visual vector recall. This capability is designed for shelf and floor display inspection scenarios in offline retail and channel stores. The service first uses an MLLM to detect the bounding boxes and preliminary names of each product in real-world shelf and floor display photos, and then performs similarity recall against a customer-specific SKU vector database, enabling an exact match for each product to the customer\\"s own SKUs. It outputs item-by-item structured results that can be directly integrated with business systems. This service is suitable for large-scale, highly concurrent visual recognition pipelines such as remote auditing of offline store displays by headquarters, SKU distribution verification, and display compliance inspections.
|
|
2098
2176
|
*
|
|
2099
2177
|
* @remarks
|
|
2100
2178
|
* ## **Product Introduction**
|
|
2101
|
-
* Display detection is an intelligent
|
|
2179
|
+
* Display detection is an intelligent recognition capability for store product displays built on multimodal large language models (MLLMs) and visual vector recall. It is designed for shelf and floor display inspection scenarios in offline retail and channel stores. For real-world shelf and floor display photos taken in stores, the service first uses an MLLM to detect the bounding boxes and preliminary names of each product, and then performs similarity recall against a customer-specific SKU vector database, enabling an exact match for each product to the customer\\"s own SKUs. It outputs item-by-item structured results that can be directly integrated with business systems. This service is suitable for large-scale, highly concurrent visual recognition pipelines such as remote auditing of offline store displays by headquarters, SKU distribution verification, and display compliance inspections.
|
|
2102
2180
|
* ## **Scenarios**
|
|
2103
|
-
* - **Shelf
|
|
2181
|
+
* - **Shelf and floor display recognition and inventory**: Recognizes each product in a shelf or floor display image and matches it to the customer\\"s SKU database. It outputs an item-by-item list (product name, location, and similarity score) to replace manual item-by-item counting.
|
|
2104
2182
|
*
|
|
2105
|
-
* - **Distribution verification
|
|
2183
|
+
* - **Distribution verification and SKU compliance**: Verifies whether stores display specified SKUs as required by headquarters, and checks for out-of-stock or misplaced items. This supports batch automatic verification during sales promotions or new product launches.
|
|
2106
2184
|
*
|
|
2107
|
-
* - **Customer-specific SKU
|
|
2108
|
-
* ## **
|
|
2109
|
-
* - **Two-stage detection
|
|
2185
|
+
* - **Customer-specific SKU database**: Customers can upload their own standard SKU images to create a dedicated vector database (isolated by RagId). During recognition, retrieval is performed only within this customer\\"s database to ensure accurate naming and data isolation between customers.
|
|
2186
|
+
* ## **Features**
|
|
2187
|
+
* - **Two-stage collaboration of detection and retrieval**: The MLLM detects the bounding box and preliminary name of each product in the entire image (semantic-level understanding, adapted for dense displays and partial occlusion). Then, visual embedding vectors are used to perform similarity retrieval within the customer\\"s SKU database. The preliminary name is replaced with the exact SKU name of the top-1 result, balancing the recall rate and naming accuracy.
|
|
2110
2188
|
*
|
|
2111
|
-
* - **Isolated retrieval with dedicated vector
|
|
2189
|
+
* - **Isolated retrieval with dedicated vector databases**: A dedicated SKU vector database is maintained for each customer based on RagId. Recognition retrieves data only within the corresponding database, ensuring strict isolation between customers. Added or updated SKUs take effect in real time.
|
|
2112
2190
|
*
|
|
2113
|
-
* - **
|
|
2191
|
+
* - **Item-by-item structured output**: The output is unified as Result.Items[]. Each product independently provides the bounding box, retrieved SKU name, SKU code, and similarity score. This facilitates direct integration with downstream inventory and verification systems and supports case-level manual review and tracing.
|
|
2114
2192
|
*
|
|
2115
|
-
* - **Supported input formats**: Currently supports image URLs accessible over the Internet or
|
|
2193
|
+
* - **Supported input formats**: Currently supports image URLs accessible over the Internet or from OSS. A single shelf or floor display image is sufficient for recognition, and the output structure is unified.
|
|
2116
2194
|
*
|
|
2117
2195
|
* @param request - MerchandisePlacementDetectionRequest
|
|
2118
2196
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -2120,43 +2198,43 @@ export default class Client extends OpenApi {
|
|
|
2120
2198
|
*/
|
|
2121
2199
|
merchandisePlacementDetectionWithOptions(request: $_model.MerchandisePlacementDetectionRequest, runtime: $dara.RuntimeOptions): Promise<$_model.MerchandisePlacementDetectionResponse>;
|
|
2122
2200
|
/**
|
|
2123
|
-
* Detects
|
|
2201
|
+
* Detects product displays in physical stores based on multimodal large language models (MLLMs) and visual vector recall. This capability is designed for shelf and floor display inspection scenarios in offline retail and channel stores. The service first uses an MLLM to detect the bounding boxes and preliminary names of each product in real-world shelf and floor display photos, and then performs similarity recall against a customer-specific SKU vector database, enabling an exact match for each product to the customer\\"s own SKUs. It outputs item-by-item structured results that can be directly integrated with business systems. This service is suitable for large-scale, highly concurrent visual recognition pipelines such as remote auditing of offline store displays by headquarters, SKU distribution verification, and display compliance inspections.
|
|
2124
2202
|
*
|
|
2125
2203
|
* @remarks
|
|
2126
2204
|
* ## **Product Introduction**
|
|
2127
|
-
* Display detection is an intelligent
|
|
2205
|
+
* Display detection is an intelligent recognition capability for store product displays built on multimodal large language models (MLLMs) and visual vector recall. It is designed for shelf and floor display inspection scenarios in offline retail and channel stores. For real-world shelf and floor display photos taken in stores, the service first uses an MLLM to detect the bounding boxes and preliminary names of each product, and then performs similarity recall against a customer-specific SKU vector database, enabling an exact match for each product to the customer\\"s own SKUs. It outputs item-by-item structured results that can be directly integrated with business systems. This service is suitable for large-scale, highly concurrent visual recognition pipelines such as remote auditing of offline store displays by headquarters, SKU distribution verification, and display compliance inspections.
|
|
2128
2206
|
* ## **Scenarios**
|
|
2129
|
-
* - **Shelf
|
|
2207
|
+
* - **Shelf and floor display recognition and inventory**: Recognizes each product in a shelf or floor display image and matches it to the customer\\"s SKU database. It outputs an item-by-item list (product name, location, and similarity score) to replace manual item-by-item counting.
|
|
2130
2208
|
*
|
|
2131
|
-
* - **Distribution verification
|
|
2209
|
+
* - **Distribution verification and SKU compliance**: Verifies whether stores display specified SKUs as required by headquarters, and checks for out-of-stock or misplaced items. This supports batch automatic verification during sales promotions or new product launches.
|
|
2132
2210
|
*
|
|
2133
|
-
* - **Customer-specific SKU
|
|
2134
|
-
* ## **
|
|
2135
|
-
* - **Two-stage detection
|
|
2211
|
+
* - **Customer-specific SKU database**: Customers can upload their own standard SKU images to create a dedicated vector database (isolated by RagId). During recognition, retrieval is performed only within this customer\\"s database to ensure accurate naming and data isolation between customers.
|
|
2212
|
+
* ## **Features**
|
|
2213
|
+
* - **Two-stage collaboration of detection and retrieval**: The MLLM detects the bounding box and preliminary name of each product in the entire image (semantic-level understanding, adapted for dense displays and partial occlusion). Then, visual embedding vectors are used to perform similarity retrieval within the customer\\"s SKU database. The preliminary name is replaced with the exact SKU name of the top-1 result, balancing the recall rate and naming accuracy.
|
|
2136
2214
|
*
|
|
2137
|
-
* - **Isolated retrieval with dedicated vector
|
|
2215
|
+
* - **Isolated retrieval with dedicated vector databases**: A dedicated SKU vector database is maintained for each customer based on RagId. Recognition retrieves data only within the corresponding database, ensuring strict isolation between customers. Added or updated SKUs take effect in real time.
|
|
2138
2216
|
*
|
|
2139
|
-
* - **
|
|
2217
|
+
* - **Item-by-item structured output**: The output is unified as Result.Items[]. Each product independently provides the bounding box, retrieved SKU name, SKU code, and similarity score. This facilitates direct integration with downstream inventory and verification systems and supports case-level manual review and tracing.
|
|
2140
2218
|
*
|
|
2141
|
-
* - **Supported input formats**: Currently supports image URLs accessible over the Internet or
|
|
2219
|
+
* - **Supported input formats**: Currently supports image URLs accessible over the Internet or from OSS. A single shelf or floor display image is sufficient for recognition, and the output structure is unified.
|
|
2142
2220
|
*
|
|
2143
2221
|
* @param request - MerchandisePlacementDetectionRequest
|
|
2144
2222
|
* @returns MerchandisePlacementDetectionResponse
|
|
2145
2223
|
*/
|
|
2146
2224
|
merchandisePlacementDetection(request: $_model.MerchandisePlacementDetectionRequest): Promise<$_model.MerchandisePlacementDetectionResponse>;
|
|
2147
2225
|
/**
|
|
2148
|
-
* Detects product displays in photos of shelves, endcaps, freezers, display
|
|
2226
|
+
* Detects product displays in photos of shelves, endcaps, freezers, display stands, and dump bins by using product SKU recognition and multimodal large model grounding, aggregates product locations by SKU, and supplements the results with visible single-item grounding and short names to facilitate product location display, inventory counting, and distribution verification.
|
|
2149
2227
|
*
|
|
2150
2228
|
* @remarks
|
|
2151
2229
|
* ## Scenarios
|
|
2152
|
-
* - Display
|
|
2153
|
-
* - Distribution
|
|
2230
|
+
* - Display inventory: Aggregates recognized product bounding boxes by SKU for business system statistics.
|
|
2231
|
+
* - Distribution checklist verification: Compares the recognized SKU list with the target checklist on the business side.
|
|
2154
2232
|
* - Single-item location review: Assists in checking recognition results by combining product bounding boxes and visible names.
|
|
2155
2233
|
* ## Features
|
|
2156
|
-
* - Aggregation by SKU: Aggregates multiple
|
|
2157
|
-
* - Supplementary single-item grounding: The multimodal model
|
|
2234
|
+
* - Aggregation by SKU: Aggregates multiple bounding boxes for the same SkuId in Products, and returns a deduplicated list of SKU codes in skuIds.
|
|
2235
|
+
* - Supplementary single-item grounding: The multimodal model locates each recognizable sales package and provides a confirmable short name.
|
|
2158
2236
|
* - Independent use of two result sets: Products comes from SKU recognition, and grounding comes from supplementary grounding. Grounding does not return SKU codes and does not guarantee item-by-item correspondence with Products.
|
|
2159
|
-
* - Supports single HTTPS image input. Supplementary grounding returns up to 12 targets
|
|
2237
|
+
* - Supports a single HTTPS image as input. Supplementary grounding returns up to 12 targets. Each target includes a category, a bounding box, and visible text of up to 24 characters. The coverage field indicates whether the grounding is complete.
|
|
2160
2238
|
*
|
|
2161
2239
|
* @param request - MerchandisePlacementDetectionLiteRequest
|
|
2162
2240
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -2164,36 +2242,36 @@ export default class Client extends OpenApi {
|
|
|
2164
2242
|
*/
|
|
2165
2243
|
merchandisePlacementDetectionLiteWithOptions(request: $_model.MerchandisePlacementDetectionLiteRequest, runtime: $dara.RuntimeOptions): Promise<$_model.MerchandisePlacementDetectionLiteResponse>;
|
|
2166
2244
|
/**
|
|
2167
|
-
* Detects product displays in photos of shelves, endcaps, freezers, display
|
|
2245
|
+
* Detects product displays in photos of shelves, endcaps, freezers, display stands, and dump bins by using product SKU recognition and multimodal large model grounding, aggregates product locations by SKU, and supplements the results with visible single-item grounding and short names to facilitate product location display, inventory counting, and distribution verification.
|
|
2168
2246
|
*
|
|
2169
2247
|
* @remarks
|
|
2170
2248
|
* ## Scenarios
|
|
2171
|
-
* - Display
|
|
2172
|
-
* - Distribution
|
|
2249
|
+
* - Display inventory: Aggregates recognized product bounding boxes by SKU for business system statistics.
|
|
2250
|
+
* - Distribution checklist verification: Compares the recognized SKU list with the target checklist on the business side.
|
|
2173
2251
|
* - Single-item location review: Assists in checking recognition results by combining product bounding boxes and visible names.
|
|
2174
2252
|
* ## Features
|
|
2175
|
-
* - Aggregation by SKU: Aggregates multiple
|
|
2176
|
-
* - Supplementary single-item grounding: The multimodal model
|
|
2253
|
+
* - Aggregation by SKU: Aggregates multiple bounding boxes for the same SkuId in Products, and returns a deduplicated list of SKU codes in skuIds.
|
|
2254
|
+
* - Supplementary single-item grounding: The multimodal model locates each recognizable sales package and provides a confirmable short name.
|
|
2177
2255
|
* - Independent use of two result sets: Products comes from SKU recognition, and grounding comes from supplementary grounding. Grounding does not return SKU codes and does not guarantee item-by-item correspondence with Products.
|
|
2178
|
-
* - Supports single HTTPS image input. Supplementary grounding returns up to 12 targets
|
|
2256
|
+
* - Supports a single HTTPS image as input. Supplementary grounding returns up to 12 targets. Each target includes a category, a bounding box, and visible text of up to 24 characters. The coverage field indicates whether the grounding is complete.
|
|
2179
2257
|
*
|
|
2180
2258
|
* @param request - MerchandisePlacementDetectionLiteRequest
|
|
2181
2259
|
* @returns MerchandisePlacementDetectionLiteResponse
|
|
2182
2260
|
*/
|
|
2183
2261
|
merchandisePlacementDetectionLite(request: $_model.MerchandisePlacementDetectionLiteRequest): Promise<$_model.MerchandisePlacementDetectionLiteResponse>;
|
|
2184
2262
|
/**
|
|
2185
|
-
* Detects the positions and names of visible products in an image
|
|
2263
|
+
* Detects the positions and names of visible products in an image. Built on a dedicated visual model, this product display detection service supports default recognition rules for the Genki Forest business type and allows the caller to invoke custom rules. It outputs the position and name of each product, and is applicable to beverage display inspection and product positioning.
|
|
2186
2264
|
*
|
|
2187
2265
|
* @remarks
|
|
2188
2266
|
* ## Scenarios
|
|
2189
|
-
* - Beverage display recognition: Uses default rules for the Genki Forest business type to recognize visible beverage products.
|
|
2190
|
-
* - Custom detection rules: Specifies product recognition
|
|
2191
|
-
* - Product
|
|
2267
|
+
* - Beverage display recognition: Uses the default rules for the Genki Forest business type to recognize visible beverage products.
|
|
2268
|
+
* - Custom detection rules: Specifies a product recognition task that meets output constraints by using the rule parameter.
|
|
2269
|
+
* - Product positioning display: Uses the name and bounding box of each product for display, statistics, or manual review.
|
|
2192
2270
|
* ## Features
|
|
2193
|
-
* - Direct product recognition:
|
|
2194
|
-
* - Two rule
|
|
2195
|
-
* - Unified result validation:
|
|
2196
|
-
* - Result scope: Currently outputs detected names and positions
|
|
2271
|
+
* - Direct product recognition: Outputs a bounding box and a name for each product. If the name cannot be determined, unknown is returned.
|
|
2272
|
+
* - Two rule entries: A non-empty rule takes precedence. If no valid rule is provided, the type must be Genki Forest.
|
|
2273
|
+
* - Unified result validation: Converts bounding box coordinates to integers and limits them to 0-1000, and swaps reverse coordinates. Uses unknown when the name is missing. The entire batch fails if any item is not a valid product object, the bounding box is invalid, or the bounding box has no area.
|
|
2274
|
+
* - Result scope: Currently outputs the detected names and positions, and does not include vector database recall, SKU codes, or similarity scores.
|
|
2197
2275
|
*
|
|
2198
2276
|
* @param request - MerchandisePlacementDetectionProRequest
|
|
2199
2277
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -2201,36 +2279,36 @@ export default class Client extends OpenApi {
|
|
|
2201
2279
|
*/
|
|
2202
2280
|
merchandisePlacementDetectionProWithOptions(request: $_model.MerchandisePlacementDetectionProRequest, runtime: $dara.RuntimeOptions): Promise<$_model.MerchandisePlacementDetectionProResponse>;
|
|
2203
2281
|
/**
|
|
2204
|
-
* Detects the positions and names of visible products in an image
|
|
2282
|
+
* Detects the positions and names of visible products in an image. Built on a dedicated visual model, this product display detection service supports default recognition rules for the Genki Forest business type and allows the caller to invoke custom rules. It outputs the position and name of each product, and is applicable to beverage display inspection and product positioning.
|
|
2205
2283
|
*
|
|
2206
2284
|
* @remarks
|
|
2207
2285
|
* ## Scenarios
|
|
2208
|
-
* - Beverage display recognition: Uses default rules for the Genki Forest business type to recognize visible beverage products.
|
|
2209
|
-
* - Custom detection rules: Specifies product recognition
|
|
2210
|
-
* - Product
|
|
2286
|
+
* - Beverage display recognition: Uses the default rules for the Genki Forest business type to recognize visible beverage products.
|
|
2287
|
+
* - Custom detection rules: Specifies a product recognition task that meets output constraints by using the rule parameter.
|
|
2288
|
+
* - Product positioning display: Uses the name and bounding box of each product for display, statistics, or manual review.
|
|
2211
2289
|
* ## Features
|
|
2212
|
-
* - Direct product recognition:
|
|
2213
|
-
* - Two rule
|
|
2214
|
-
* - Unified result validation:
|
|
2215
|
-
* - Result scope: Currently outputs detected names and positions
|
|
2290
|
+
* - Direct product recognition: Outputs a bounding box and a name for each product. If the name cannot be determined, unknown is returned.
|
|
2291
|
+
* - Two rule entries: A non-empty rule takes precedence. If no valid rule is provided, the type must be Genki Forest.
|
|
2292
|
+
* - Unified result validation: Converts bounding box coordinates to integers and limits them to 0-1000, and swaps reverse coordinates. Uses unknown when the name is missing. The entire batch fails if any item is not a valid product object, the bounding box is invalid, or the bounding box has no area.
|
|
2293
|
+
* - Result scope: Currently outputs the detected names and positions, and does not include vector database recall, SKU codes, or similarity scores.
|
|
2216
2294
|
*
|
|
2217
2295
|
* @param request - MerchandisePlacementDetectionProRequest
|
|
2218
2296
|
* @returns MerchandisePlacementDetectionProResponse
|
|
2219
2297
|
*/
|
|
2220
2298
|
merchandisePlacementDetectionPro(request: $_model.MerchandisePlacementDetectionProRequest): Promise<$_model.MerchandisePlacementDetectionProResponse>;
|
|
2221
2299
|
/**
|
|
2222
|
-
* Detects display price tags based on price tag recognition and multimodal large model
|
|
2300
|
+
* Detects display price tags based on price tag recognition and multimodal large model grounding. This operation extracts product information, selling prices, original prices, and locations from price tags, and provides visible bounding boxes for paper price tags, electronic price tags, and promotional price tags. It is applicable to store price collection, price tag inspection, and business-side price verification.
|
|
2223
2301
|
*
|
|
2224
2302
|
* @remarks
|
|
2225
2303
|
* ## Scenarios
|
|
2226
|
-
* - Store price collection: Reads the
|
|
2304
|
+
* - Store price collection: Reads and recognizes the selling prices and available original prices of price tags.
|
|
2227
2305
|
* - Price execution verification: Compares the recognized prices with the business-side price list.
|
|
2228
|
-
* - Manual price tag review: Locates paper, electronic, and promotional price tags
|
|
2306
|
+
* - Manual price tag review: Locates paper, electronic, and promotional price tags for easy review of the original images.
|
|
2229
2307
|
* ## Features
|
|
2230
2308
|
* - Structured price output: Returns the product name, code, price, and location item by item. Prices are retained as strings.
|
|
2231
|
-
* - Multi-type price tag
|
|
2232
|
-
* - Original text and location-assisted review: Prioritizes extracting clear selling prices
|
|
2233
|
-
* - Supports single HTTPS image input. Supplementary
|
|
2309
|
+
* - Multi-type price tag grounding: Covers ordinary paper price tags, electronic price tags, and promotional tags with clear selling prices.
|
|
2310
|
+
* - Original text and location-assisted review: Prioritizes extracting clear selling prices based on located text. Leaves the field empty if the text is unreadable. Supplementary grounding does not infer that a price tag necessarily corresponds to a specific SKU based on its location.
|
|
2311
|
+
* - Supports single HTTPS image input. Supplementary grounding returns up to 12 targets. Each target includes a category, a bounding box, and up to 24 characters of visible text, and uses the coverage field to indicate whether the grounding is complete.
|
|
2234
2312
|
*
|
|
2235
2313
|
* @param request - MerchandisePriceTagDetectionRequest
|
|
2236
2314
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -2238,36 +2316,36 @@ export default class Client extends OpenApi {
|
|
|
2238
2316
|
*/
|
|
2239
2317
|
merchandisePriceTagDetectionWithOptions(request: $_model.MerchandisePriceTagDetectionRequest, runtime: $dara.RuntimeOptions): Promise<$_model.MerchandisePriceTagDetectionResponse>;
|
|
2240
2318
|
/**
|
|
2241
|
-
* Detects display price tags based on price tag recognition and multimodal large model
|
|
2319
|
+
* Detects display price tags based on price tag recognition and multimodal large model grounding. This operation extracts product information, selling prices, original prices, and locations from price tags, and provides visible bounding boxes for paper price tags, electronic price tags, and promotional price tags. It is applicable to store price collection, price tag inspection, and business-side price verification.
|
|
2242
2320
|
*
|
|
2243
2321
|
* @remarks
|
|
2244
2322
|
* ## Scenarios
|
|
2245
|
-
* - Store price collection: Reads the
|
|
2323
|
+
* - Store price collection: Reads and recognizes the selling prices and available original prices of price tags.
|
|
2246
2324
|
* - Price execution verification: Compares the recognized prices with the business-side price list.
|
|
2247
|
-
* - Manual price tag review: Locates paper, electronic, and promotional price tags
|
|
2325
|
+
* - Manual price tag review: Locates paper, electronic, and promotional price tags for easy review of the original images.
|
|
2248
2326
|
* ## Features
|
|
2249
2327
|
* - Structured price output: Returns the product name, code, price, and location item by item. Prices are retained as strings.
|
|
2250
|
-
* - Multi-type price tag
|
|
2251
|
-
* - Original text and location-assisted review: Prioritizes extracting clear selling prices
|
|
2252
|
-
* - Supports single HTTPS image input. Supplementary
|
|
2328
|
+
* - Multi-type price tag grounding: Covers ordinary paper price tags, electronic price tags, and promotional tags with clear selling prices.
|
|
2329
|
+
* - Original text and location-assisted review: Prioritizes extracting clear selling prices based on located text. Leaves the field empty if the text is unreadable. Supplementary grounding does not infer that a price tag necessarily corresponds to a specific SKU based on its location.
|
|
2330
|
+
* - Supports single HTTPS image input. Supplementary grounding returns up to 12 targets. Each target includes a category, a bounding box, and up to 24 characters of visible text, and uses the coverage field to indicate whether the grounding is complete.
|
|
2253
2331
|
*
|
|
2254
2332
|
* @param request - MerchandisePriceTagDetectionRequest
|
|
2255
2333
|
* @returns MerchandisePriceTagDetectionResponse
|
|
2256
2334
|
*/
|
|
2257
2335
|
merchandisePriceTagDetection(request: $_model.MerchandisePriceTagDetectionRequest): Promise<$_model.MerchandisePriceTagDetectionResponse>;
|
|
2258
2336
|
/**
|
|
2259
|
-
* Detects store displays based on display scene recognition and holistic positioning
|
|
2337
|
+
* Detects store displays based on display scene recognition and holistic positioning of multimodal large models. Identifies display areas such as shelves, refrigerators, and floor displays, outputs available scene names, locations, and display metrics, and supplements overall facility bounding boxes for display facility inspection, area visualization, and display metric verification.
|
|
2260
2338
|
*
|
|
2261
2339
|
* @remarks
|
|
2262
2340
|
* ## Scenarios
|
|
2263
|
-
* - Display facility inspection:
|
|
2264
|
-
* - Display metric verification:
|
|
2265
|
-
* - Display area visualization:
|
|
2341
|
+
* - Display facility inspection: Identifies facilities such as shelves, endcaps, floor displays, upright refrigerators, and chest freezers.
|
|
2342
|
+
* - Display metric verification: Reads active metrics such as proportion, purity, and fullness for further evaluation by business systems.
|
|
2343
|
+
* - Display area visualization: Displays area locations and overall facility bounding boxes on the original image.
|
|
2266
2344
|
* ## Features
|
|
2267
|
-
* - Scene structured output:
|
|
2268
|
-
* - Holistic facility positioning:
|
|
2269
|
-
* - Retains two types of coordinates:
|
|
2270
|
-
* - Supports
|
|
2345
|
+
* - Scene structured output: Returns scene names, center points, area contours, and active metrics.
|
|
2346
|
+
* - Holistic facility positioning: Uses one bounding box for an independent facility or promotional display, which is suitable for overall area review.
|
|
2347
|
+
* - Retains two types of coordinates: The positions in scenes retain the original normalization coordinates of the recognition service, while grounding uses 0-1000 integer bounding boxes.
|
|
2348
|
+
* - Supports single HTTPS image input. The supplementary positioning returns up to 12 targets. Each target includes a category, a bounding box, and up to 24 characters of visible text, and uses coverage to indicate whether the positioning is complete.
|
|
2271
2349
|
*
|
|
2272
2350
|
* @param request - MerchandiseSceneDetectionRequest
|
|
2273
2351
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -2275,34 +2353,34 @@ export default class Client extends OpenApi {
|
|
|
2275
2353
|
*/
|
|
2276
2354
|
merchandiseSceneDetectionWithOptions(request: $_model.MerchandiseSceneDetectionRequest, runtime: $dara.RuntimeOptions): Promise<$_model.MerchandiseSceneDetectionResponse>;
|
|
2277
2355
|
/**
|
|
2278
|
-
* Detects store displays based on display scene recognition and holistic positioning
|
|
2356
|
+
* Detects store displays based on display scene recognition and holistic positioning of multimodal large models. Identifies display areas such as shelves, refrigerators, and floor displays, outputs available scene names, locations, and display metrics, and supplements overall facility bounding boxes for display facility inspection, area visualization, and display metric verification.
|
|
2279
2357
|
*
|
|
2280
2358
|
* @remarks
|
|
2281
2359
|
* ## Scenarios
|
|
2282
|
-
* - Display facility inspection:
|
|
2283
|
-
* - Display metric verification:
|
|
2284
|
-
* - Display area visualization:
|
|
2360
|
+
* - Display facility inspection: Identifies facilities such as shelves, endcaps, floor displays, upright refrigerators, and chest freezers.
|
|
2361
|
+
* - Display metric verification: Reads active metrics such as proportion, purity, and fullness for further evaluation by business systems.
|
|
2362
|
+
* - Display area visualization: Displays area locations and overall facility bounding boxes on the original image.
|
|
2285
2363
|
* ## Features
|
|
2286
|
-
* - Scene structured output:
|
|
2287
|
-
* - Holistic facility positioning:
|
|
2288
|
-
* - Retains two types of coordinates:
|
|
2289
|
-
* - Supports
|
|
2364
|
+
* - Scene structured output: Returns scene names, center points, area contours, and active metrics.
|
|
2365
|
+
* - Holistic facility positioning: Uses one bounding box for an independent facility or promotional display, which is suitable for overall area review.
|
|
2366
|
+
* - Retains two types of coordinates: The positions in scenes retain the original normalization coordinates of the recognition service, while grounding uses 0-1000 integer bounding boxes.
|
|
2367
|
+
* - Supports single HTTPS image input. The supplementary positioning returns up to 12 targets. Each target includes a category, a bounding box, and up to 24 characters of visible text, and uses coverage to indicate whether the positioning is complete.
|
|
2290
2368
|
*
|
|
2291
2369
|
* @param request - MerchandiseSceneDetectionRequest
|
|
2292
2370
|
* @returns MerchandiseSceneDetectionResponse
|
|
2293
2371
|
*/
|
|
2294
2372
|
merchandiseSceneDetection(request: $_model.MerchandiseSceneDetectionRequest): Promise<$_model.MerchandiseSceneDetectionResponse>;
|
|
2295
2373
|
/**
|
|
2296
|
-
*
|
|
2374
|
+
* Detects recaptured images of milk powder can bottom codes and localizes elements based on recapture recognition and multimodal large model capabilities. The operation determines whether an uploaded photo is recaptured and localizes visible milk powder products, can bottoms, and bottom code areas. It applies to milk powder channel inspections, bottom code photo reviews, and manual verifications.
|
|
2297
2375
|
*
|
|
2298
2376
|
* @remarks
|
|
2299
2377
|
* ## Features
|
|
2300
|
-
* - Recapture binary classification: isFake=true indicates a
|
|
2301
|
-
* - Milk powder subject and bottom code localization: Prioritizes the localization of the milk powder subject. Adds
|
|
2378
|
+
* - Recapture binary classification: isFake=true indicates a recaptured image, and false indicates a non-recaptured image. Element localization is performed for both results.
|
|
2379
|
+
* - Milk powder subject and bottom code localization: Prioritizes the localization of the milk powder subject. Adds bounding boxes for the can bottom, spray code, batch code, or traceability code areas when they are clear.
|
|
2302
2380
|
* - Visible information output: Outputs only confirmed short names or text without guessing blurred code values. Localization results do not change the recapture conclusion.
|
|
2303
|
-
* - Supports a single HTTPS image input.
|
|
2304
|
-
* ## Scenarios
|
|
2305
|
-
* -
|
|
2381
|
+
* - Supports a single HTTPS image input. Supplementary localization returns up to 12 targets. Each target includes a category, a bounding box, and up to 24 characters of visible text. The coverage field indicates whether the localization is complete.
|
|
2382
|
+
* ## Scenarios
|
|
2383
|
+
* - Bottom code photo review: Determines whether a photo of a milk powder can bottom code has a recapture risk.
|
|
2306
2384
|
* - Milk powder product inspection: Localizes canned, boxed, or bagged milk powder, as well as clearly visible can bottoms and bottom codes.
|
|
2307
2385
|
* - Review result playback: Displays target bounding boxes on the original image to assist personnel in verifying the photo content.
|
|
2308
2386
|
*
|
|
@@ -2312,16 +2390,16 @@ export default class Client extends OpenApi {
|
|
|
2312
2390
|
*/
|
|
2313
2391
|
milkPowderCanBottomCodeRephotographyDetectionWithOptions(request: $_model.MilkPowderCanBottomCodeRephotographyDetectionRequest, runtime: $dara.RuntimeOptions): Promise<$_model.MilkPowderCanBottomCodeRephotographyDetectionResponse>;
|
|
2314
2392
|
/**
|
|
2315
|
-
*
|
|
2393
|
+
* Detects recaptured images of milk powder can bottom codes and localizes elements based on recapture recognition and multimodal large model capabilities. The operation determines whether an uploaded photo is recaptured and localizes visible milk powder products, can bottoms, and bottom code areas. It applies to milk powder channel inspections, bottom code photo reviews, and manual verifications.
|
|
2316
2394
|
*
|
|
2317
2395
|
* @remarks
|
|
2318
2396
|
* ## Features
|
|
2319
|
-
* - Recapture binary classification: isFake=true indicates a
|
|
2320
|
-
* - Milk powder subject and bottom code localization: Prioritizes the localization of the milk powder subject. Adds
|
|
2397
|
+
* - Recapture binary classification: isFake=true indicates a recaptured image, and false indicates a non-recaptured image. Element localization is performed for both results.
|
|
2398
|
+
* - Milk powder subject and bottom code localization: Prioritizes the localization of the milk powder subject. Adds bounding boxes for the can bottom, spray code, batch code, or traceability code areas when they are clear.
|
|
2321
2399
|
* - Visible information output: Outputs only confirmed short names or text without guessing blurred code values. Localization results do not change the recapture conclusion.
|
|
2322
|
-
* - Supports a single HTTPS image input.
|
|
2323
|
-
* ## Scenarios
|
|
2324
|
-
* -
|
|
2400
|
+
* - Supports a single HTTPS image input. Supplementary localization returns up to 12 targets. Each target includes a category, a bounding box, and up to 24 characters of visible text. The coverage field indicates whether the localization is complete.
|
|
2401
|
+
* ## Scenarios
|
|
2402
|
+
* - Bottom code photo review: Determines whether a photo of a milk powder can bottom code has a recapture risk.
|
|
2325
2403
|
* - Milk powder product inspection: Localizes canned, boxed, or bagged milk powder, as well as clearly visible can bottoms and bottom codes.
|
|
2326
2404
|
* - Review result playback: Displays target bounding boxes on the original image to assist personnel in verifying the photo content.
|
|
2327
2405
|
*
|
|
@@ -2330,16 +2408,16 @@ export default class Client extends OpenApi {
|
|
|
2330
2408
|
*/
|
|
2331
2409
|
milkPowderCanBottomCodeRephotographyDetection(request: $_model.MilkPowderCanBottomCodeRephotographyDetectionRequest): Promise<$_model.MilkPowderCanBottomCodeRephotographyDetectionResponse>;
|
|
2332
2410
|
/**
|
|
2333
|
-
*
|
|
2411
|
+
* Analyzes milk powder box code images for channel inspection by using recapture detection and multimodal large model element grounding. Outputs non-recapture, recapture, or suspected recapture conclusions, and locates visible milk powder products, outer boxes, and code areas to provide a structured basis for photo review and manual verification.
|
|
2334
2412
|
*
|
|
2335
2413
|
* @remarks
|
|
2336
2414
|
* ## Features
|
|
2337
|
-
* - Three-state recapture detection: When photoStatus is 0, 1, or 2, it indicates non-recapture, recapture, or suspected recapture, respectively. The isFake, isSuspect, and score
|
|
2338
|
-
* - Subject and code area grounding: Prioritizes
|
|
2339
|
-
* - Result
|
|
2340
|
-
* - Supports a single HTTPS image as input. The supplementary grounding returns up to 12 targets
|
|
2415
|
+
* - Three-state recapture detection: When photoStatus is 0, 1, or 2, it indicates non-recapture, recapture, or suspected recapture, respectively. The operation also outputs isFake, isSuspect, and score.
|
|
2416
|
+
* - Subject and code area grounding: Prioritizes grounding of individual milk powder products and outer boxes, and supplements clear box codes, barcodes, and QR code areas. If no box code is present, the milk powder subject can still be grounded.
|
|
2417
|
+
* - Result synergy: Element grounding supplements visible targets without changing the recapture detection conclusion. It does not decode QR codes or provide product authenticity verification.
|
|
2418
|
+
* - Supports a single HTTPS image as input. The supplementary grounding returns up to 12 targets, each containing a category, bounding box, and up to 24 characters of visible text. The coverage field indicates whether the grounding is complete.
|
|
2341
2419
|
* ## Scenarios
|
|
2342
|
-
* - Box code photo review: Checks
|
|
2420
|
+
* - Box code photo review: Checks milk powder outer box photos uploaded by stores or channels for recapture risks.
|
|
2343
2421
|
* - Milk powder display inspection: Locates visible individual milk powder products, full boxes, and clear code areas in photos.
|
|
2344
2422
|
* - Suspected sample review: Filters images that require manual verification based on the suspected status, algorithm score, and bounding boxes.
|
|
2345
2423
|
*
|
|
@@ -2349,16 +2427,16 @@ export default class Client extends OpenApi {
|
|
|
2349
2427
|
*/
|
|
2350
2428
|
milkPowderCartonCodeRephotographyDetectionWithOptions(request: $_model.MilkPowderCartonCodeRephotographyDetectionRequest, runtime: $dara.RuntimeOptions): Promise<$_model.MilkPowderCartonCodeRephotographyDetectionResponse>;
|
|
2351
2429
|
/**
|
|
2352
|
-
*
|
|
2430
|
+
* Analyzes milk powder box code images for channel inspection by using recapture detection and multimodal large model element grounding. Outputs non-recapture, recapture, or suspected recapture conclusions, and locates visible milk powder products, outer boxes, and code areas to provide a structured basis for photo review and manual verification.
|
|
2353
2431
|
*
|
|
2354
2432
|
* @remarks
|
|
2355
2433
|
* ## Features
|
|
2356
|
-
* - Three-state recapture detection: When photoStatus is 0, 1, or 2, it indicates non-recapture, recapture, or suspected recapture, respectively. The isFake, isSuspect, and score
|
|
2357
|
-
* - Subject and code area grounding: Prioritizes
|
|
2358
|
-
* - Result
|
|
2359
|
-
* - Supports a single HTTPS image as input. The supplementary grounding returns up to 12 targets
|
|
2434
|
+
* - Three-state recapture detection: When photoStatus is 0, 1, or 2, it indicates non-recapture, recapture, or suspected recapture, respectively. The operation also outputs isFake, isSuspect, and score.
|
|
2435
|
+
* - Subject and code area grounding: Prioritizes grounding of individual milk powder products and outer boxes, and supplements clear box codes, barcodes, and QR code areas. If no box code is present, the milk powder subject can still be grounded.
|
|
2436
|
+
* - Result synergy: Element grounding supplements visible targets without changing the recapture detection conclusion. It does not decode QR codes or provide product authenticity verification.
|
|
2437
|
+
* - Supports a single HTTPS image as input. The supplementary grounding returns up to 12 targets, each containing a category, bounding box, and up to 24 characters of visible text. The coverage field indicates whether the grounding is complete.
|
|
2360
2438
|
* ## Scenarios
|
|
2361
|
-
* - Box code photo review: Checks
|
|
2439
|
+
* - Box code photo review: Checks milk powder outer box photos uploaded by stores or channels for recapture risks.
|
|
2362
2440
|
* - Milk powder display inspection: Locates visible individual milk powder products, full boxes, and clear code areas in photos.
|
|
2363
2441
|
* - Suspected sample review: Filters images that require manual verification based on the suspected status, algorithm score, and bounding boxes.
|
|
2364
2442
|
*
|
|
@@ -2427,28 +2505,28 @@ export default class Client extends OpenApi {
|
|
|
2427
2505
|
*/
|
|
2428
2506
|
petHealthAnalysis(request: $_model.PetHealthAnalysisRequest): Promise<$_model.PetHealthAnalysisResponse>;
|
|
2429
2507
|
/**
|
|
2430
|
-
* Maas-MT
|
|
2508
|
+
* Provides Maas-MT, an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs, which is continuously optimized for e-commerce-specific terms such as brands, models, materials, and attributes. Supports translation across more than 400 language pairs, including bridged pairs, with a focus on Chinese-English, Chinese-multilingual, and English-multilingual translations. Supports language detection for 24 language pairs and automatically detects the source language if it is not specified.
|
|
2431
2509
|
*
|
|
2432
2510
|
* @remarks
|
|
2433
|
-
* ## Product
|
|
2434
|
-
* Marco MT is an e-commerce translation model trained on over 1 billion
|
|
2435
|
-
* ##
|
|
2436
|
-
* - Product titles: Marco MT large model translation accurately
|
|
2437
|
-
* - Product descriptions: Product descriptions are
|
|
2438
|
-
* - Product attributes: Product attribute terms are
|
|
2439
|
-
* - Customer service conversations: In customer service scenarios,
|
|
2440
|
-
* Marco MT large model translation can also be used for general
|
|
2511
|
+
* ## Product introduction
|
|
2512
|
+
* Marco MT is an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs, continuously optimized for e-commerce-specific terms such as brands, models, materials, and attributes. It supports translation across more than 100 language pairs, including bridged pairs, especially between Chinese and English, Chinese and multiple languages, and English and multiple languages. It supports language detection for 24 language pairs and automatically detects the source language if it is not specified.
|
|
2513
|
+
* ## Scenarios
|
|
2514
|
+
* - Product titles: Marco MT large model translation can accurately translate phrases, keywords, and trending words in product titles into the target language, increasing product exposure on e-commerce platforms.
|
|
2515
|
+
* - Product descriptions: Product descriptions are generally long and have diverse and complex formats. Marco MT large model translation supports long-text translation and HTML format, delivering excellent translation quality and format restoration.
|
|
2516
|
+
* - Product attributes: Product attribute terms are short and contain e-commerce-specific words, such as models and parameters.
|
|
2517
|
+
* - Customer service conversations: In customer service scenarios, it can optimize issues such as missing context and typos, and supports polite expressions in some language pairs.
|
|
2518
|
+
* Additionally, Marco MT large model translation can also be used for translation in general scenarios, such as office work, meetings, and daily conversations.
|
|
2441
2519
|
* ## Features
|
|
2442
|
-
* - **Supported language
|
|
2443
|
-
* - **Ultra-low hallucination rate and high-speed inference
|
|
2444
|
-
* - **Supported text
|
|
2445
|
-
* - **Translation intervention
|
|
2520
|
+
* - **Supported language pairs**: Marco MT large model translation supports translation between more than 100 languages and language detection for 23 languages. For specific language pairs, refer to the language mapping table in Section 5.6.
|
|
2521
|
+
* - **Ultra-low hallucination rate and high-speed inference**: Marco MT large model translation is a large language model aligned with preferences for translation scenarios. Compared with general large language models, it features faster translation inference speed and an extremely low hallucination rate, making it especially suitable for large-scale invocation scenarios.
|
|
2522
|
+
* - **Supported text formats**: Currently supports text and HTML formats.
|
|
2523
|
+
* - **Translation intervention**: Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and skip translation (ABC-null). This is commonly used for brand word protection. You only need to pass the corresponding intervention glossary ID when calling the API. This meets your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention terms. If you need more, contact the platform.
|
|
2446
2524
|
* ## Translation quality comparison
|
|
2447
|
-
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation
|
|
2525
|
+
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation advantages** |
|
|
2448
2526
|
* |----------|---------------|-----------------------|-----------------------|---------------------|
|
|
2449
2527
|
* | 75mm 4Pin 0.38A GA81S2U 12V GTX 960 Cooling Fan for Zotac GTX960 Graphics Card Cooling Fan | 75mm 4Pin 0.38A GA81S2U 12V GTX 960, ventilador de enfriamiento para tarjeta gráfica Zotac GTX960. | Ventilador de refrigeración de 75mm 4Pin 0.38A GA81S2U 12V para la tarjeta gráfica Zotac GTX960 Ventilador de enfriamiento GTX 960. | Ventilador de refrigeración para tarjeta gráfica Zotac GTX960, 75mm, 4 pines, 0,38A, GA81S2U, 12V, GTX 960 | Clearer product subject |
|
|
2450
|
-
* | New Arrival Classic Style Luxury Brand 6 Hands Swiss Automatic Mechanical Men\\"s Business Steel Watch | Nueva llegada, reloj mecánico automático de lujo con 6 manecillas, estilo clásico, de acero para hombres de negocios | Nueva Llegada Reloj De Acero de Negocios para Hombre con Mecanismo Automático Suizo y 6 Agujas de Estilo Clásico de Marca de Lujo. | Reloj de acero de negocios para hombre, mecánico automático suizo, marca de lujo, estilo clásico, 6 manos, nueva llegada | More complete sentence structure, clearer expression, and more reasonable
|
|
2451
|
-
* | Men Key Bag Genuine Cow Leather Buckets Key Cases Pouch Zipper Keychain Auto Car Key Case Women Home Key Holder Wallet | Sac à clés pour hommes en cuir de vache véritable, étuis à clés, pochette à fermeture éclair, porte-clés, étui à clé de voiture, porte-clés pour femmes, organisateur de portefeuille | Porte-clés sac en cuir de vache véritable, étuis à clés en forme de seau, pochette à fermeture éclair, porte-clés auto pour voiture, étui à clés pour femmes, organisateur de clés de maison, portefeuille. | Hommes porte-clés en cuir de vache véritable sac/pochette fermature éclair porte-clés Auto voiture porte-clés femmes maison porte-clés organisateur portefeuille | Clearer and more
|
|
2528
|
+
* | New Arrival Classic Style Luxury Brand 6 Hands Swiss Automatic Mechanical Men\\"s Business Steel Watch | Nueva llegada, reloj mecánico automático de lujo con 6 manecillas, estilo clásico, de acero para hombres de negocios | Nueva Llegada Reloj De Acero de Negocios para Hombre con Mecanismo Automático Suizo y 6 Agujas de Estilo Clásico de Marca de Lujo. | Reloj de acero de negocios para hombre, mecánico automático suizo, marca de lujo, estilo clásico, 6 manos, nueva llegada | More complete sentence structure, clearer expression, and more reasonable punctuation |
|
|
2529
|
+
* | Men Key Bag Genuine Cow Leather Buckets Key Cases Pouch Zipper Keychain Auto Car Key Case Women Home Key Holder Wallet | Sac à clés pour hommes en cuir de vache véritable, étuis à clés, pochette à fermeture éclair, porte-clés, étui à clé de voiture, porte-clés pour femmes, organisateur de portefeuille | Porte-clés sac en cuir de vache véritable, étuis à clés en forme de seau, pochette à fermeture éclair, porte-clés auto pour voiture, étui à clés pour femmes, organisateur de clés de maison, portefeuille. | Hommes porte-clés en cuir de vache véritable sac/pochette fermature éclair porte-clés Auto voiture porte-clés femmes maison porte-clés organisateur portefeuille | Clearer and more explicit product subject expression, identifying it as a "key bag" rather than a "keychain", whereas other translations may cause ambiguity regarding the product subject |
|
|
2452
2530
|
*
|
|
2453
2531
|
* @param tmpReq - PrepaidTextTranslateRequest
|
|
2454
2532
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -2456,28 +2534,28 @@ export default class Client extends OpenApi {
|
|
|
2456
2534
|
*/
|
|
2457
2535
|
prepaidTextTranslateWithOptions(tmpReq: $_model.PrepaidTextTranslateRequest, runtime: $dara.RuntimeOptions): Promise<$_model.PrepaidTextTranslateResponse>;
|
|
2458
2536
|
/**
|
|
2459
|
-
* Maas-MT
|
|
2537
|
+
* Provides Maas-MT, an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs, which is continuously optimized for e-commerce-specific terms such as brands, models, materials, and attributes. Supports translation across more than 400 language pairs, including bridged pairs, with a focus on Chinese-English, Chinese-multilingual, and English-multilingual translations. Supports language detection for 24 language pairs and automatically detects the source language if it is not specified.
|
|
2460
2538
|
*
|
|
2461
2539
|
* @remarks
|
|
2462
|
-
* ## Product
|
|
2463
|
-
* Marco MT is an e-commerce translation model trained on over 1 billion
|
|
2464
|
-
* ##
|
|
2465
|
-
* - Product titles: Marco MT large model translation accurately
|
|
2466
|
-
* - Product descriptions: Product descriptions are
|
|
2467
|
-
* - Product attributes: Product attribute terms are
|
|
2468
|
-
* - Customer service conversations: In customer service scenarios,
|
|
2469
|
-
* Marco MT large model translation can also be used for general
|
|
2540
|
+
* ## Product introduction
|
|
2541
|
+
* Marco MT is an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs, continuously optimized for e-commerce-specific terms such as brands, models, materials, and attributes. It supports translation across more than 100 language pairs, including bridged pairs, especially between Chinese and English, Chinese and multiple languages, and English and multiple languages. It supports language detection for 24 language pairs and automatically detects the source language if it is not specified.
|
|
2542
|
+
* ## Scenarios
|
|
2543
|
+
* - Product titles: Marco MT large model translation can accurately translate phrases, keywords, and trending words in product titles into the target language, increasing product exposure on e-commerce platforms.
|
|
2544
|
+
* - Product descriptions: Product descriptions are generally long and have diverse and complex formats. Marco MT large model translation supports long-text translation and HTML format, delivering excellent translation quality and format restoration.
|
|
2545
|
+
* - Product attributes: Product attribute terms are short and contain e-commerce-specific words, such as models and parameters.
|
|
2546
|
+
* - Customer service conversations: In customer service scenarios, it can optimize issues such as missing context and typos, and supports polite expressions in some language pairs.
|
|
2547
|
+
* Additionally, Marco MT large model translation can also be used for translation in general scenarios, such as office work, meetings, and daily conversations.
|
|
2470
2548
|
* ## Features
|
|
2471
|
-
* - **Supported language
|
|
2472
|
-
* - **Ultra-low hallucination rate and high-speed inference
|
|
2473
|
-
* - **Supported text
|
|
2474
|
-
* - **Translation intervention
|
|
2549
|
+
* - **Supported language pairs**: Marco MT large model translation supports translation between more than 100 languages and language detection for 23 languages. For specific language pairs, refer to the language mapping table in Section 5.6.
|
|
2550
|
+
* - **Ultra-low hallucination rate and high-speed inference**: Marco MT large model translation is a large language model aligned with preferences for translation scenarios. Compared with general large language models, it features faster translation inference speed and an extremely low hallucination rate, making it especially suitable for large-scale invocation scenarios.
|
|
2551
|
+
* - **Supported text formats**: Currently supports text and HTML formats.
|
|
2552
|
+
* - **Translation intervention**: Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and skip translation (ABC-null). This is commonly used for brand word protection. You only need to pass the corresponding intervention glossary ID when calling the API. This meets your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention terms. If you need more, contact the platform.
|
|
2475
2553
|
* ## Translation quality comparison
|
|
2476
|
-
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation
|
|
2554
|
+
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation advantages** |
|
|
2477
2555
|
* |----------|---------------|-----------------------|-----------------------|---------------------|
|
|
2478
2556
|
* | 75mm 4Pin 0.38A GA81S2U 12V GTX 960 Cooling Fan for Zotac GTX960 Graphics Card Cooling Fan | 75mm 4Pin 0.38A GA81S2U 12V GTX 960, ventilador de enfriamiento para tarjeta gráfica Zotac GTX960. | Ventilador de refrigeración de 75mm 4Pin 0.38A GA81S2U 12V para la tarjeta gráfica Zotac GTX960 Ventilador de enfriamiento GTX 960. | Ventilador de refrigeración para tarjeta gráfica Zotac GTX960, 75mm, 4 pines, 0,38A, GA81S2U, 12V, GTX 960 | Clearer product subject |
|
|
2479
|
-
* | New Arrival Classic Style Luxury Brand 6 Hands Swiss Automatic Mechanical Men\\"s Business Steel Watch | Nueva llegada, reloj mecánico automático de lujo con 6 manecillas, estilo clásico, de acero para hombres de negocios | Nueva Llegada Reloj De Acero de Negocios para Hombre con Mecanismo Automático Suizo y 6 Agujas de Estilo Clásico de Marca de Lujo. | Reloj de acero de negocios para hombre, mecánico automático suizo, marca de lujo, estilo clásico, 6 manos, nueva llegada | More complete sentence structure, clearer expression, and more reasonable
|
|
2480
|
-
* | Men Key Bag Genuine Cow Leather Buckets Key Cases Pouch Zipper Keychain Auto Car Key Case Women Home Key Holder Wallet | Sac à clés pour hommes en cuir de vache véritable, étuis à clés, pochette à fermeture éclair, porte-clés, étui à clé de voiture, porte-clés pour femmes, organisateur de portefeuille | Porte-clés sac en cuir de vache véritable, étuis à clés en forme de seau, pochette à fermeture éclair, porte-clés auto pour voiture, étui à clés pour femmes, organisateur de clés de maison, portefeuille. | Hommes porte-clés en cuir de vache véritable sac/pochette fermature éclair porte-clés Auto voiture porte-clés femmes maison porte-clés organisateur portefeuille | Clearer and more
|
|
2557
|
+
* | New Arrival Classic Style Luxury Brand 6 Hands Swiss Automatic Mechanical Men\\"s Business Steel Watch | Nueva llegada, reloj mecánico automático de lujo con 6 manecillas, estilo clásico, de acero para hombres de negocios | Nueva Llegada Reloj De Acero de Negocios para Hombre con Mecanismo Automático Suizo y 6 Agujas de Estilo Clásico de Marca de Lujo. | Reloj de acero de negocios para hombre, mecánico automático suizo, marca de lujo, estilo clásico, 6 manos, nueva llegada | More complete sentence structure, clearer expression, and more reasonable punctuation |
|
|
2558
|
+
* | Men Key Bag Genuine Cow Leather Buckets Key Cases Pouch Zipper Keychain Auto Car Key Case Women Home Key Holder Wallet | Sac à clés pour hommes en cuir de vache véritable, étuis à clés, pochette à fermeture éclair, porte-clés, étui à clé de voiture, porte-clés pour femmes, organisateur de portefeuille | Porte-clés sac en cuir de vache véritable, étuis à clés en forme de seau, pochette à fermeture éclair, porte-clés auto pour voiture, étui à clés pour femmes, organisateur de clés de maison, portefeuille. | Hommes porte-clés en cuir de vache véritable sac/pochette fermature éclair porte-clés Auto voiture porte-clés femmes maison porte-clés organisateur portefeuille | Clearer and more explicit product subject expression, identifying it as a "key bag" rather than a "keychain", whereas other translations may cause ambiguity regarding the product subject |
|
|
2481
2559
|
*
|
|
2482
2560
|
* @param request - PrepaidTextTranslateRequest
|
|
2483
2561
|
* @returns PrepaidTextTranslateResponse
|
|
@@ -2520,6 +2598,51 @@ export default class Client extends OpenApi {
|
|
|
2520
2598
|
* @returns ProductHotspotDetectionResponse
|
|
2521
2599
|
*/
|
|
2522
2600
|
productHotspotDetection(request: $_model.ProductHotspotDetectionRequest): Promise<$_model.ProductHotspotDetectionResponse>;
|
|
2601
|
+
/**
|
|
2602
|
+
* Generates a single-product showcase video for e-commerce merchants and platforms based on the product title and multiple images of the same product. This API optionally accepts a storyboard script, automatically selects reference images, plans a three-shot storyboard, and generates the video. It uses asynchronous tasks, supports 720p and 1080p resolutions and four aspect ratios, and is suitable for content production of non-apparel products. For apparel products, use the E-commerce Video Enhanced Edition.
|
|
2603
|
+
*
|
|
2604
|
+
* @remarks
|
|
2605
|
+
* # Product introduction
|
|
2606
|
+
* The basic e-commerce video edition is designed for e-commerce merchants and platforms. It generates a single-product showcase video based on the product title and multiple images of the same product. You can optionally provide a storyboard script. The system automatically selects reference images, plans a three-shot storyboard, and generates the video. The API uses asynchronous tasks, supports 720p and 1080p resolutions and four aspect ratios, and is suitable for content production of non-apparel products. For apparel products, use the e-commerce enhanced edition.
|
|
2607
|
+
* # Scenarios
|
|
2608
|
+
* - New product material generation: Provide the product title and images to automatically plan storyboard shots such as product debut, details, or usage demonstrations.
|
|
2609
|
+
* - Video production with existing scripts: Provide a storyboard script or creative description. The system optimizes the storyboard script based on the product images and retains shot intentions that are supported by the images.
|
|
2610
|
+
* - Adaptation to different video placements: Use the aspect ratio parameter to adapt to vertical short videos, main product images, detail pages, and horizontal displays. For batch production, each request corresponds to one product and one video.
|
|
2611
|
+
* # Features
|
|
2612
|
+
* - Automatic image selection and storyboard planning: When no script is provided, the system generates a storyboard based on the product title and images. When a script is provided, the system still performs image selection and planning, eliminating the need for callers to organize video prompts.
|
|
2613
|
+
* - Product appearance consistency constraint: The system uses the selected complete product image as the appearance baseline. It checks the color scheme, structure, proportions, texture, version, and specifications of other images, and selects only reference images that can be confirmed to belong to the same SKU.
|
|
2614
|
+
* - Flexible video specifications: Without a script, the duration is 5 to 15 seconds. With a script, the duration is 5 to 30 seconds. The system supports four aspect ratios (16:9, 1:1, 3:4, and 9:16) and two resolutions (720p and 1080p).
|
|
2615
|
+
* - Asynchronous generation and task query: After a task is created, a task ID is returned. The caller queries the result by using the query API. The final video includes background music, no voiceover, and no additional subtitles or marketing text.
|
|
2616
|
+
* # Examples
|
|
2617
|
+
* [View the attachment "Digital_040_WiFi6_Gigabit_Router.mp4" in the DingTalk document.](https://alidocs.dingtalk.com/i/nodes/gwva2dxOW4vRkd9DUn1g1p6kJbkz3BRL?cid=6760411388:7016395022&corpId=dingd8e1123006514592&iframeQuery=anchorId%3DX02mvsyycduj3nepwoeush&utm_medium=im_card&utm_scene=person_space&utm_source=im)
|
|
2618
|
+
*
|
|
2619
|
+
* @param tmpReq - ProductVideoGenerationRequest
|
|
2620
|
+
* @param runtime - runtime options for this request RuntimeOptions
|
|
2621
|
+
* @returns ProductVideoGenerationResponse
|
|
2622
|
+
*/
|
|
2623
|
+
productVideoGenerationWithOptions(tmpReq: $_model.ProductVideoGenerationRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ProductVideoGenerationResponse>;
|
|
2624
|
+
/**
|
|
2625
|
+
* Generates a single-product showcase video for e-commerce merchants and platforms based on the product title and multiple images of the same product. This API optionally accepts a storyboard script, automatically selects reference images, plans a three-shot storyboard, and generates the video. It uses asynchronous tasks, supports 720p and 1080p resolutions and four aspect ratios, and is suitable for content production of non-apparel products. For apparel products, use the E-commerce Video Enhanced Edition.
|
|
2626
|
+
*
|
|
2627
|
+
* @remarks
|
|
2628
|
+
* # Product introduction
|
|
2629
|
+
* The basic e-commerce video edition is designed for e-commerce merchants and platforms. It generates a single-product showcase video based on the product title and multiple images of the same product. You can optionally provide a storyboard script. The system automatically selects reference images, plans a three-shot storyboard, and generates the video. The API uses asynchronous tasks, supports 720p and 1080p resolutions and four aspect ratios, and is suitable for content production of non-apparel products. For apparel products, use the e-commerce enhanced edition.
|
|
2630
|
+
* # Scenarios
|
|
2631
|
+
* - New product material generation: Provide the product title and images to automatically plan storyboard shots such as product debut, details, or usage demonstrations.
|
|
2632
|
+
* - Video production with existing scripts: Provide a storyboard script or creative description. The system optimizes the storyboard script based on the product images and retains shot intentions that are supported by the images.
|
|
2633
|
+
* - Adaptation to different video placements: Use the aspect ratio parameter to adapt to vertical short videos, main product images, detail pages, and horizontal displays. For batch production, each request corresponds to one product and one video.
|
|
2634
|
+
* # Features
|
|
2635
|
+
* - Automatic image selection and storyboard planning: When no script is provided, the system generates a storyboard based on the product title and images. When a script is provided, the system still performs image selection and planning, eliminating the need for callers to organize video prompts.
|
|
2636
|
+
* - Product appearance consistency constraint: The system uses the selected complete product image as the appearance baseline. It checks the color scheme, structure, proportions, texture, version, and specifications of other images, and selects only reference images that can be confirmed to belong to the same SKU.
|
|
2637
|
+
* - Flexible video specifications: Without a script, the duration is 5 to 15 seconds. With a script, the duration is 5 to 30 seconds. The system supports four aspect ratios (16:9, 1:1, 3:4, and 9:16) and two resolutions (720p and 1080p).
|
|
2638
|
+
* - Asynchronous generation and task query: After a task is created, a task ID is returned. The caller queries the result by using the query API. The final video includes background music, no voiceover, and no additional subtitles or marketing text.
|
|
2639
|
+
* # Examples
|
|
2640
|
+
* [View the attachment "Digital_040_WiFi6_Gigabit_Router.mp4" in the DingTalk document.](https://alidocs.dingtalk.com/i/nodes/gwva2dxOW4vRkd9DUn1g1p6kJbkz3BRL?cid=6760411388:7016395022&corpId=dingd8e1123006514592&iframeQuery=anchorId%3DX02mvsyycduj3nepwoeush&utm_medium=im_card&utm_scene=person_space&utm_source=im)
|
|
2641
|
+
*
|
|
2642
|
+
* @param request - ProductVideoGenerationRequest
|
|
2643
|
+
* @returns ProductVideoGenerationResponse
|
|
2644
|
+
*/
|
|
2645
|
+
productVideoGeneration(request: $_model.ProductVideoGenerationRequest): Promise<$_model.ProductVideoGenerationResponse>;
|
|
2523
2646
|
/**
|
|
2524
2647
|
* Queries the result of an asynchronous task. The API name in the POP gateway is QueryAsyncTaskResult.
|
|
2525
2648
|
*
|
|
@@ -2855,105 +2978,105 @@ export default class Client extends OpenApi {
|
|
|
2855
2978
|
*/
|
|
2856
2979
|
sizeChartExtract(request: $_model.SizeChartExtractRequest): Promise<$_model.SizeChartExtractResponse>;
|
|
2857
2980
|
/**
|
|
2858
|
-
* Extracts structured information such as size charts and
|
|
2981
|
+
* Extracts structured information such as size charts and package weight and dimensions from images by using a multimodal large language model in asynchronous mode.
|
|
2859
2982
|
*
|
|
2860
2983
|
* @remarks
|
|
2861
2984
|
* ## Scenarios
|
|
2862
2985
|
* Size charts: Extracts size charts of apparel categories into text.
|
|
2863
|
-
*
|
|
2986
|
+
* Package weight and dimensions: Extracts package weight and dimension information from images.
|
|
2864
2987
|
* ## Features
|
|
2865
|
-
* The size chart extraction service is based on a multimodal large model. It automatically recognizes size charts or
|
|
2866
|
-
* Core capabilities: You input an image URL and optional column name configurations, and the system outputs the structured data of the size chart or
|
|
2867
|
-
* ## Comparison
|
|
2988
|
+
* The size chart extraction service is based on a multimodal large language model. It automatically recognizes size charts or package weight and dimension information in images and converts the information into structured text output. You provide an image URL, and the system processes the request as an asynchronous task and returns the extracted structured data. You can specify the column names to be recognized, such as Size, Bust, and Length, by using ColumnNameList to achieve precise and targeted extraction. You can also control the output language by using the LanguageModel parameter. Valid values: cn for Chinese and en for English. If you do not specify this parameter, the original language is retained. This service is applicable to scenarios such as text conversion of size charts for apparel categories and batch structuring of package weight and dimension information for commodities.
|
|
2989
|
+
* Core capabilities: You input an image URL and optional column name configurations, and the system outputs the structured data of the size chart or package weight and dimensions in the image. The API operation uses the asynchronous task mode (background: true). After you submit the task, a task ID is returned. You must poll the task to obtain the final result. This mode is suitable for processing complex images or handling large-scale calls.
|
|
2990
|
+
* ## Comparison of results
|
|
2868
2991
|
* | Input image | Output result |
|
|
2869
2992
|
* | --- | --- |
|
|
2870
2993
|
* |  | {
|
|
2871
2994
|
* "SizeChart": [
|
|
2872
2995
|
* {
|
|
2873
|
-
* "
|
|
2996
|
+
* "Size": {
|
|
2874
2997
|
* "value": "S"
|
|
2875
2998
|
* },
|
|
2876
|
-
* "
|
|
2999
|
+
* "Waist": {
|
|
2877
3000
|
* "unit": "CM",
|
|
2878
3001
|
* "value": 58
|
|
2879
3002
|
* },
|
|
2880
|
-
* "
|
|
3003
|
+
* "Skirt length": {
|
|
2881
3004
|
* "unit": "CM",
|
|
2882
3005
|
* "value": 81
|
|
2883
3006
|
* },
|
|
2884
|
-
* "
|
|
3007
|
+
* "Recommended weight": {
|
|
2885
3008
|
* "unit": "kg",
|
|
2886
3009
|
* "lower_value": 40,
|
|
2887
3010
|
* "upper_value": 47.5
|
|
2888
3011
|
* }
|
|
2889
3012
|
* },
|
|
2890
3013
|
* {
|
|
2891
|
-
* "
|
|
3014
|
+
* "Size": {
|
|
2892
3015
|
* "value": "M"
|
|
2893
3016
|
* },
|
|
2894
|
-
* "
|
|
3017
|
+
* "Waist": {
|
|
2895
3018
|
* "unit": "CM",
|
|
2896
3019
|
* "value": 59
|
|
2897
3020
|
* },
|
|
2898
|
-
* "
|
|
3021
|
+
* "Skirt length": {
|
|
2899
3022
|
* "unit": "CM",
|
|
2900
3023
|
* "value": 82
|
|
2901
3024
|
* },
|
|
2902
|
-
* "
|
|
3025
|
+
* "Recommended weight": {
|
|
2903
3026
|
* "unit": "kg",
|
|
2904
3027
|
* "lower_value": 45,
|
|
2905
3028
|
* "upper_value": 52.5
|
|
2906
3029
|
* }
|
|
2907
3030
|
* },
|
|
2908
3031
|
* {
|
|
2909
|
-
* "
|
|
3032
|
+
* "Size": {
|
|
2910
3033
|
* "value": "L"
|
|
2911
3034
|
* },
|
|
2912
|
-
* "
|
|
3035
|
+
* "Waist": {
|
|
2913
3036
|
* "unit": "CM",
|
|
2914
3037
|
* "value": 60
|
|
2915
3038
|
* },
|
|
2916
|
-
* "
|
|
3039
|
+
* "Skirt length": {
|
|
2917
3040
|
* "unit": "CM",
|
|
2918
3041
|
* "value": 83
|
|
2919
3042
|
* },
|
|
2920
|
-
* "
|
|
3043
|
+
* "Recommended weight": {
|
|
2921
3044
|
* "unit": "kg",
|
|
2922
3045
|
* "lower_value": 50,
|
|
2923
3046
|
* "upper_value": 57.5
|
|
2924
3047
|
* }
|
|
2925
3048
|
* },
|
|
2926
3049
|
* {
|
|
2927
|
-
* "
|
|
3050
|
+
* "Size": {
|
|
2928
3051
|
* "value": "XL"
|
|
2929
3052
|
* },
|
|
2930
|
-
* "
|
|
3053
|
+
* "Waist": {
|
|
2931
3054
|
* "unit": "CM",
|
|
2932
3055
|
* "value": 61
|
|
2933
3056
|
* },
|
|
2934
|
-
* "
|
|
3057
|
+
* "Skirt length": {
|
|
2935
3058
|
* "unit": "CM",
|
|
2936
3059
|
* "value": 84
|
|
2937
3060
|
* },
|
|
2938
|
-
* "
|
|
3061
|
+
* "Recommended weight": {
|
|
2939
3062
|
* "unit": "kg",
|
|
2940
3063
|
* "lower_value": 55,
|
|
2941
3064
|
* "upper_value": 62.5
|
|
2942
3065
|
* }
|
|
2943
3066
|
* },
|
|
2944
3067
|
* {
|
|
2945
|
-
* "
|
|
3068
|
+
* "Size": {
|
|
2946
3069
|
* "value": "2XL"
|
|
2947
3070
|
* },
|
|
2948
|
-
* "
|
|
3071
|
+
* "Waist": {
|
|
2949
3072
|
* "unit": "CM",
|
|
2950
3073
|
* "value": 62
|
|
2951
3074
|
* },
|
|
2952
|
-
* "
|
|
3075
|
+
* "Skirt length": {
|
|
2953
3076
|
* "unit": "CM",
|
|
2954
3077
|
* "value": 85
|
|
2955
3078
|
* },
|
|
2956
|
-
* "
|
|
3079
|
+
* "Recommended weight": {
|
|
2957
3080
|
* "unit": "kg",
|
|
2958
3081
|
* "lower_value": 60,
|
|
2959
3082
|
* "upper_value": 67.5
|
|
@@ -2964,13 +3087,13 @@ export default class Client extends OpenApi {
|
|
|
2964
3087
|
* "Size",
|
|
2965
3088
|
* "Skirt length",
|
|
2966
3089
|
* "Waist",
|
|
2967
|
-
* "
|
|
3090
|
+
* "Recommended weight"
|
|
2968
3091
|
* \\],
|
|
2969
3092
|
* "IntersectionAttributes": [
|
|
2970
3093
|
* "Size",
|
|
2971
3094
|
* "Skirt length",
|
|
2972
|
-
* "Waist (
|
|
2973
|
-
* "
|
|
3095
|
+
* "Waist (stretched)",
|
|
3096
|
+
* "Recommended weight"
|
|
2974
3097
|
* \\]
|
|
2975
3098
|
* } |
|
|
2976
3099
|
*
|
|
@@ -2980,105 +3103,105 @@ export default class Client extends OpenApi {
|
|
|
2980
3103
|
*/
|
|
2981
3104
|
sizeChartExtractAsyncWithOptions(tmpReq: $_model.SizeChartExtractAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.SizeChartExtractAsyncResponse>;
|
|
2982
3105
|
/**
|
|
2983
|
-
* Extracts structured information such as size charts and
|
|
3106
|
+
* Extracts structured information such as size charts and package weight and dimensions from images by using a multimodal large language model in asynchronous mode.
|
|
2984
3107
|
*
|
|
2985
3108
|
* @remarks
|
|
2986
3109
|
* ## Scenarios
|
|
2987
3110
|
* Size charts: Extracts size charts of apparel categories into text.
|
|
2988
|
-
*
|
|
3111
|
+
* Package weight and dimensions: Extracts package weight and dimension information from images.
|
|
2989
3112
|
* ## Features
|
|
2990
|
-
* The size chart extraction service is based on a multimodal large model. It automatically recognizes size charts or
|
|
2991
|
-
* Core capabilities: You input an image URL and optional column name configurations, and the system outputs the structured data of the size chart or
|
|
2992
|
-
* ## Comparison
|
|
3113
|
+
* The size chart extraction service is based on a multimodal large language model. It automatically recognizes size charts or package weight and dimension information in images and converts the information into structured text output. You provide an image URL, and the system processes the request as an asynchronous task and returns the extracted structured data. You can specify the column names to be recognized, such as Size, Bust, and Length, by using ColumnNameList to achieve precise and targeted extraction. You can also control the output language by using the LanguageModel parameter. Valid values: cn for Chinese and en for English. If you do not specify this parameter, the original language is retained. This service is applicable to scenarios such as text conversion of size charts for apparel categories and batch structuring of package weight and dimension information for commodities.
|
|
3114
|
+
* Core capabilities: You input an image URL and optional column name configurations, and the system outputs the structured data of the size chart or package weight and dimensions in the image. The API operation uses the asynchronous task mode (background: true). After you submit the task, a task ID is returned. You must poll the task to obtain the final result. This mode is suitable for processing complex images or handling large-scale calls.
|
|
3115
|
+
* ## Comparison of results
|
|
2993
3116
|
* | Input image | Output result |
|
|
2994
3117
|
* | --- | --- |
|
|
2995
3118
|
* |  | {
|
|
2996
3119
|
* "SizeChart": [
|
|
2997
3120
|
* {
|
|
2998
|
-
* "
|
|
3121
|
+
* "Size": {
|
|
2999
3122
|
* "value": "S"
|
|
3000
3123
|
* },
|
|
3001
|
-
* "
|
|
3124
|
+
* "Waist": {
|
|
3002
3125
|
* "unit": "CM",
|
|
3003
3126
|
* "value": 58
|
|
3004
3127
|
* },
|
|
3005
|
-
* "
|
|
3128
|
+
* "Skirt length": {
|
|
3006
3129
|
* "unit": "CM",
|
|
3007
3130
|
* "value": 81
|
|
3008
3131
|
* },
|
|
3009
|
-
* "
|
|
3132
|
+
* "Recommended weight": {
|
|
3010
3133
|
* "unit": "kg",
|
|
3011
3134
|
* "lower_value": 40,
|
|
3012
3135
|
* "upper_value": 47.5
|
|
3013
3136
|
* }
|
|
3014
3137
|
* },
|
|
3015
3138
|
* {
|
|
3016
|
-
* "
|
|
3139
|
+
* "Size": {
|
|
3017
3140
|
* "value": "M"
|
|
3018
3141
|
* },
|
|
3019
|
-
* "
|
|
3142
|
+
* "Waist": {
|
|
3020
3143
|
* "unit": "CM",
|
|
3021
3144
|
* "value": 59
|
|
3022
3145
|
* },
|
|
3023
|
-
* "
|
|
3146
|
+
* "Skirt length": {
|
|
3024
3147
|
* "unit": "CM",
|
|
3025
3148
|
* "value": 82
|
|
3026
3149
|
* },
|
|
3027
|
-
* "
|
|
3150
|
+
* "Recommended weight": {
|
|
3028
3151
|
* "unit": "kg",
|
|
3029
3152
|
* "lower_value": 45,
|
|
3030
3153
|
* "upper_value": 52.5
|
|
3031
3154
|
* }
|
|
3032
3155
|
* },
|
|
3033
3156
|
* {
|
|
3034
|
-
* "
|
|
3157
|
+
* "Size": {
|
|
3035
3158
|
* "value": "L"
|
|
3036
3159
|
* },
|
|
3037
|
-
* "
|
|
3160
|
+
* "Waist": {
|
|
3038
3161
|
* "unit": "CM",
|
|
3039
3162
|
* "value": 60
|
|
3040
3163
|
* },
|
|
3041
|
-
* "
|
|
3164
|
+
* "Skirt length": {
|
|
3042
3165
|
* "unit": "CM",
|
|
3043
3166
|
* "value": 83
|
|
3044
3167
|
* },
|
|
3045
|
-
* "
|
|
3168
|
+
* "Recommended weight": {
|
|
3046
3169
|
* "unit": "kg",
|
|
3047
3170
|
* "lower_value": 50,
|
|
3048
3171
|
* "upper_value": 57.5
|
|
3049
3172
|
* }
|
|
3050
3173
|
* },
|
|
3051
3174
|
* {
|
|
3052
|
-
* "
|
|
3175
|
+
* "Size": {
|
|
3053
3176
|
* "value": "XL"
|
|
3054
3177
|
* },
|
|
3055
|
-
* "
|
|
3178
|
+
* "Waist": {
|
|
3056
3179
|
* "unit": "CM",
|
|
3057
3180
|
* "value": 61
|
|
3058
3181
|
* },
|
|
3059
|
-
* "
|
|
3182
|
+
* "Skirt length": {
|
|
3060
3183
|
* "unit": "CM",
|
|
3061
3184
|
* "value": 84
|
|
3062
3185
|
* },
|
|
3063
|
-
* "
|
|
3186
|
+
* "Recommended weight": {
|
|
3064
3187
|
* "unit": "kg",
|
|
3065
3188
|
* "lower_value": 55,
|
|
3066
3189
|
* "upper_value": 62.5
|
|
3067
3190
|
* }
|
|
3068
3191
|
* },
|
|
3069
3192
|
* {
|
|
3070
|
-
* "
|
|
3193
|
+
* "Size": {
|
|
3071
3194
|
* "value": "2XL"
|
|
3072
3195
|
* },
|
|
3073
|
-
* "
|
|
3196
|
+
* "Waist": {
|
|
3074
3197
|
* "unit": "CM",
|
|
3075
3198
|
* "value": 62
|
|
3076
3199
|
* },
|
|
3077
|
-
* "
|
|
3200
|
+
* "Skirt length": {
|
|
3078
3201
|
* "unit": "CM",
|
|
3079
3202
|
* "value": 85
|
|
3080
3203
|
* },
|
|
3081
|
-
* "
|
|
3204
|
+
* "Recommended weight": {
|
|
3082
3205
|
* "unit": "kg",
|
|
3083
3206
|
* "lower_value": 60,
|
|
3084
3207
|
* "upper_value": 67.5
|
|
@@ -3089,13 +3212,13 @@ export default class Client extends OpenApi {
|
|
|
3089
3212
|
* "Size",
|
|
3090
3213
|
* "Skirt length",
|
|
3091
3214
|
* "Waist",
|
|
3092
|
-
* "
|
|
3215
|
+
* "Recommended weight"
|
|
3093
3216
|
* \\],
|
|
3094
3217
|
* "IntersectionAttributes": [
|
|
3095
3218
|
* "Size",
|
|
3096
3219
|
* "Skirt length",
|
|
3097
|
-
* "Waist (
|
|
3098
|
-
* "
|
|
3220
|
+
* "Waist (stretched)",
|
|
3221
|
+
* "Recommended weight"
|
|
3099
3222
|
* \\]
|
|
3100
3223
|
* } |
|
|
3101
3224
|
*
|
|
@@ -3104,18 +3227,18 @@ export default class Client extends OpenApi {
|
|
|
3104
3227
|
*/
|
|
3105
3228
|
sizeChartExtractAsync(request: $_model.SizeChartExtractAsyncRequest): Promise<$_model.SizeChartExtractAsyncResponse>;
|
|
3106
3229
|
/**
|
|
3107
|
-
*
|
|
3230
|
+
* Audits store photos based on storefront scene recognition and multimodal large model element localization. The API outputs storefront scene classifications and confidence details, and localizes storefronts, signboards, entrances, and business signs. It is applicable to store data collection, storefront photo classification, and inspection reviews.
|
|
3108
3231
|
*
|
|
3109
3232
|
* @remarks
|
|
3110
|
-
* ##
|
|
3233
|
+
* ## Scenarios
|
|
3111
3234
|
* - Storefront photo classification: Distinguishes storefront-related photos from non-storefront photos.
|
|
3112
3235
|
* - Store data verification: Localizes signboards and entrances, and extracts clear and readable short text.
|
|
3113
3236
|
* - Multi-store photo review: Localizes visible storefronts and signs of adjacent stores separately.
|
|
3114
3237
|
* ## Features
|
|
3115
|
-
* - Scene classification and details: Returns
|
|
3238
|
+
* - Scene classification and details: Returns a scenes string array and classification details. Non-storefront photos are also valid classification results.
|
|
3116
3239
|
* - Storefront key element localization: Covers storefronts, signboards, store entrances, and business-related signs.
|
|
3117
|
-
* - Readable text extraction: Extracts only clear short text.
|
|
3118
|
-
* - Supports single HTTPS image input. Supplementary localization returns up to 12 targets, each containing a category,
|
|
3240
|
+
* - Readable text extraction: Extracts only clear short text. Does not infer business status based on whether the door is open or closed, and does not infer addresses or store ownership.
|
|
3241
|
+
* - Supports single HTTPS image input. Supplementary localization returns up to 12 targets, each containing a category, bounding box, and up to 24 characters of visible text, with coverage indicating whether the localization is complete.
|
|
3119
3242
|
*
|
|
3120
3243
|
* @param request - StorefrontSceneRecognitionRequest
|
|
3121
3244
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3123,25 +3246,25 @@ export default class Client extends OpenApi {
|
|
|
3123
3246
|
*/
|
|
3124
3247
|
storefrontSceneRecognitionWithOptions(request: $_model.StorefrontSceneRecognitionRequest, runtime: $dara.RuntimeOptions): Promise<$_model.StorefrontSceneRecognitionResponse>;
|
|
3125
3248
|
/**
|
|
3126
|
-
*
|
|
3249
|
+
* Audits store photos based on storefront scene recognition and multimodal large model element localization. The API outputs storefront scene classifications and confidence details, and localizes storefronts, signboards, entrances, and business signs. It is applicable to store data collection, storefront photo classification, and inspection reviews.
|
|
3127
3250
|
*
|
|
3128
3251
|
* @remarks
|
|
3129
|
-
* ##
|
|
3252
|
+
* ## Scenarios
|
|
3130
3253
|
* - Storefront photo classification: Distinguishes storefront-related photos from non-storefront photos.
|
|
3131
3254
|
* - Store data verification: Localizes signboards and entrances, and extracts clear and readable short text.
|
|
3132
3255
|
* - Multi-store photo review: Localizes visible storefronts and signs of adjacent stores separately.
|
|
3133
3256
|
* ## Features
|
|
3134
|
-
* - Scene classification and details: Returns
|
|
3257
|
+
* - Scene classification and details: Returns a scenes string array and classification details. Non-storefront photos are also valid classification results.
|
|
3135
3258
|
* - Storefront key element localization: Covers storefronts, signboards, store entrances, and business-related signs.
|
|
3136
|
-
* - Readable text extraction: Extracts only clear short text.
|
|
3137
|
-
* - Supports single HTTPS image input. Supplementary localization returns up to 12 targets, each containing a category,
|
|
3259
|
+
* - Readable text extraction: Extracts only clear short text. Does not infer business status based on whether the door is open or closed, and does not infer addresses or store ownership.
|
|
3260
|
+
* - Supports single HTTPS image input. Supplementary localization returns up to 12 targets, each containing a category, bounding box, and up to 24 characters of visible text, with coverage indicating whether the localization is complete.
|
|
3138
3261
|
*
|
|
3139
3262
|
* @param request - StorefrontSceneRecognitionRequest
|
|
3140
3263
|
* @returns StorefrontSceneRecognitionResponse
|
|
3141
3264
|
*/
|
|
3142
3265
|
storefrontSceneRecognition(request: $_model.StorefrontSceneRecognitionRequest): Promise<$_model.StorefrontSceneRecognitionResponse>;
|
|
3143
3266
|
/**
|
|
3144
|
-
* Generates product detail page
|
|
3267
|
+
* Generates product detail page materials automatically based on a multimodal large language model (MLLM) and structured image-text extraction to help e-commerce platforms and brands supplement product detail pages. After the caller pushes product information such as the product ID, title, brand, main image, and shop name, the service automatically locates identical products, performs consistency checks, extracts size information and product attributes, renders them into SVG size and attribute charts for direct use on the detail page, and returns structured detail copy classifications and processing remarks.
|
|
3145
3268
|
*
|
|
3146
3269
|
* @param request - SubmitProductMatchRequest
|
|
3147
3270
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3149,7 +3272,7 @@ export default class Client extends OpenApi {
|
|
|
3149
3272
|
*/
|
|
3150
3273
|
submitProductMatchWithOptions(request: $_model.SubmitProductMatchRequest, runtime: $dara.RuntimeOptions): Promise<$_model.SubmitProductMatchResponse>;
|
|
3151
3274
|
/**
|
|
3152
|
-
* Generates product detail page
|
|
3275
|
+
* Generates product detail page materials automatically based on a multimodal large language model (MLLM) and structured image-text extraction to help e-commerce platforms and brands supplement product detail pages. After the caller pushes product information such as the product ID, title, brand, main image, and shop name, the service automatically locates identical products, performs consistency checks, extracts size information and product attributes, renders them into SVG size and attribute charts for direct use on the detail page, and returns structured detail copy classifications and processing remarks.
|
|
3153
3276
|
*
|
|
3154
3277
|
* @param request - SubmitProductMatchRequest
|
|
3155
3278
|
* @returns SubmitProductMatchResponse
|
|
@@ -3280,7 +3403,7 @@ export default class Client extends OpenApi {
|
|
|
3280
3403
|
*/
|
|
3281
3404
|
textTranslate(request: $_model.TextTranslateRequest): Promise<$_model.TextTranslateResponse>;
|
|
3282
3405
|
/**
|
|
3283
|
-
* Translates text by using the Maas MT e-commerce translation model
|
|
3406
|
+
* Translates text asynchronously by using the Maas MT model, an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs. The model is continuously optimized for e-commerce-specific terms such as brands, models, materials, and attributes. It supports 156 languages with over 400 language pairs and supports automatic language detection for source languages.
|
|
3284
3407
|
*
|
|
3285
3408
|
* @remarks
|
|
3286
3409
|
* ## Scenarios
|
|
@@ -3294,22 +3417,22 @@ export default class Client extends OpenApi {
|
|
|
3294
3417
|
*
|
|
3295
3418
|
* The Maas MT large language model can also be used for translation in general scenarios, such as office work, meetings, and daily conversations.
|
|
3296
3419
|
* ## Features
|
|
3297
|
-
* * **Ultra-low hallucination rate and high-speed inference
|
|
3420
|
+
* * **Ultra-low hallucination rate and high-speed inference** The Maas MT large language model is aligned with preferences for translation scenarios. Compared with general-purpose large language models, it features faster translation inference and an extremely low hallucination rate, making it especially suitable for large-scale invocation scenarios.
|
|
3298
3421
|
*
|
|
3299
|
-
* * **Supported text formats
|
|
3422
|
+
* * **Supported text formats** The model supports text and HTML formats.
|
|
3300
3423
|
*
|
|
3301
|
-
* * **Translation intervention
|
|
3424
|
+
* * **Translation intervention** You can customize translation results, including keeping words untranslated (ABC-ABC), specifying translations (ABC-DEF), and omitting translations (ABC-null value). This is commonly used for brand word protection. You only need to pass the corresponding intervention glossary ID when calling the API. This meets your translation needs in different scenarios. You can upload up to 100,000 intervention words. If you need more, contact the platform.
|
|
3302
3425
|
*
|
|
3303
|
-
* * **Translation
|
|
3426
|
+
* * **Translation quality comparison**
|
|
3304
3427
|
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation advantages** |
|
|
3305
3428
|
* | --- | --- | --- | --- | --- |
|
|
3306
3429
|
* | 75mm 4Pin 0.38A GA81S2U 12V GTX 960 Cooling Fan for Zotac GTX960 Graphics Card Cooling Fan | 75mm 4Pin 0.38A GA81S2U 12V GTX 960, ventilador de enfriamiento para tarjeta gráfica Zotac GTX960. | Ventilador de refrigeración de 75mm 4Pin 0.38A GA81S2U 12V para la tarjeta gráfica Zotac GTX960 Ventilador de enfriamiento GTX 960. | Ventilador de refrigeración para tarjeta gráfica Zotac GTX960, 75mm, 4 pines, 0,38A, GA81S2U, 12V, GTX 960 | Clearer product subject |
|
|
3307
3430
|
* | New Arrival Classic Style Luxury Brand 6 Hands Swiss Automatic Mechanical Men\\"s Business Steel Watch | Nueva llegada, reloj mecánico automático de lujo con 6 manecillas, estilo clásico, de acero para hombres de negocios | Nueva Llegada Reloj De Acero de Negocios para Hombre con Mecanismo Automático Suizo y 6 Agujas de Estilo Clásico de Marca de Lujo. | Reloj de acero de negocios para hombre, mecánico automático suizo, marca de lujo, estilo clásico, 6 manos, nueva llegada | More complete sentence structure, clearer expression, and more reasonable punctuation |
|
|
3308
|
-
* | Men Key Bag Genuine Cow Leather Buckets Key Cases Pouch Zipper Keychain Auto Car Key Case Women Home Key Holder Wallet | Sac à clés pour hommes en cuir de vache véritable, étuis à clés, pochette à fermeture éclair, porte-clés, étui à clé de voiture, porte-clés pour femmes, organisateur de portefeuille | Porte-clés sac en cuir de vache véritable, étuis à clés en forme de seau, pochette à fermeture éclair, porte-clés auto pour voiture, étui à clés pour femmes, organisateur de clés de maison, portefeuille. | Hommes porte-clés en cuir de vache véritable sac/pochette
|
|
3309
|
-
* ## Preparations and
|
|
3310
|
-
* Text translation supports both synchronization and asynchronous
|
|
3431
|
+
* | Men Key Bag Genuine Cow Leather Buckets Key Cases Pouch Zipper Keychain Auto Car Key Case Women Home Key Holder Wallet | Sac à clés pour hommes en cuir de vache véritable, étuis à clés, pochette à fermeture éclair, porte-clés, étui à clé de voiture, porte-clés pour femmes, organisateur de portefeuille | Porte-clés sac en cuir de vache véritable, étuis à clés en forme de seau, pochette à fermeture éclair, porte-clés auto pour voiture, étui à clés pour femmes, organisateur de clés de maison, portefeuille. | Hommes porte-clés en cuir de vache véritable sac/pochette fermeture éclair porte-clés Auto voiture porte-clés femmes maison porte-clés organisateur portefeuille | Clearer and more explicit product subject. It translates to "key bag" rather than "keychain", avoiding ambiguity in other translations |
|
|
3432
|
+
* ## Preparations and invoke flow
|
|
3433
|
+
* Text translation supports both synchronization and asynchronous invoke methods. This topic describes the asynchronous invoke API. If you need to use synchronous call, see [Text translation - Synchronous API](https://api.aliyun.com/document/Aidge/2026-04-28/TextTranslate).
|
|
3311
3434
|
* The asynchronous APIs for text translation and other capabilities share the same result retrieval flow, RocketMQ subscribe rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
3312
|
-
* For the asynchronous
|
|
3435
|
+
* For the asynchronous invoke integration flow, subscribe rules, message formats and encryption protocols, and detailed integration solutions, see [Asynchronous API invoke instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
3313
3436
|
*
|
|
3314
3437
|
* @param tmpReq - TextTranslateAsyncRequest
|
|
3315
3438
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3317,7 +3440,7 @@ export default class Client extends OpenApi {
|
|
|
3317
3440
|
*/
|
|
3318
3441
|
textTranslateAsyncWithOptions(tmpReq: $_model.TextTranslateAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.TextTranslateAsyncResponse>;
|
|
3319
3442
|
/**
|
|
3320
|
-
* Translates text by using the Maas MT e-commerce translation model
|
|
3443
|
+
* Translates text asynchronously by using the Maas MT model, an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs. The model is continuously optimized for e-commerce-specific terms such as brands, models, materials, and attributes. It supports 156 languages with over 400 language pairs and supports automatic language detection for source languages.
|
|
3321
3444
|
*
|
|
3322
3445
|
* @remarks
|
|
3323
3446
|
* ## Scenarios
|
|
@@ -3331,22 +3454,22 @@ export default class Client extends OpenApi {
|
|
|
3331
3454
|
*
|
|
3332
3455
|
* The Maas MT large language model can also be used for translation in general scenarios, such as office work, meetings, and daily conversations.
|
|
3333
3456
|
* ## Features
|
|
3334
|
-
* * **Ultra-low hallucination rate and high-speed inference
|
|
3457
|
+
* * **Ultra-low hallucination rate and high-speed inference** The Maas MT large language model is aligned with preferences for translation scenarios. Compared with general-purpose large language models, it features faster translation inference and an extremely low hallucination rate, making it especially suitable for large-scale invocation scenarios.
|
|
3335
3458
|
*
|
|
3336
|
-
* * **Supported text formats
|
|
3459
|
+
* * **Supported text formats** The model supports text and HTML formats.
|
|
3337
3460
|
*
|
|
3338
|
-
* * **Translation intervention
|
|
3461
|
+
* * **Translation intervention** You can customize translation results, including keeping words untranslated (ABC-ABC), specifying translations (ABC-DEF), and omitting translations (ABC-null value). This is commonly used for brand word protection. You only need to pass the corresponding intervention glossary ID when calling the API. This meets your translation needs in different scenarios. You can upload up to 100,000 intervention words. If you need more, contact the platform.
|
|
3339
3462
|
*
|
|
3340
|
-
* * **Translation
|
|
3463
|
+
* * **Translation quality comparison**
|
|
3341
3464
|
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation advantages** |
|
|
3342
3465
|
* | --- | --- | --- | --- | --- |
|
|
3343
3466
|
* | 75mm 4Pin 0.38A GA81S2U 12V GTX 960 Cooling Fan for Zotac GTX960 Graphics Card Cooling Fan | 75mm 4Pin 0.38A GA81S2U 12V GTX 960, ventilador de enfriamiento para tarjeta gráfica Zotac GTX960. | Ventilador de refrigeración de 75mm 4Pin 0.38A GA81S2U 12V para la tarjeta gráfica Zotac GTX960 Ventilador de enfriamiento GTX 960. | Ventilador de refrigeración para tarjeta gráfica Zotac GTX960, 75mm, 4 pines, 0,38A, GA81S2U, 12V, GTX 960 | Clearer product subject |
|
|
3344
3467
|
* | New Arrival Classic Style Luxury Brand 6 Hands Swiss Automatic Mechanical Men\\"s Business Steel Watch | Nueva llegada, reloj mecánico automático de lujo con 6 manecillas, estilo clásico, de acero para hombres de negocios | Nueva Llegada Reloj De Acero de Negocios para Hombre con Mecanismo Automático Suizo y 6 Agujas de Estilo Clásico de Marca de Lujo. | Reloj de acero de negocios para hombre, mecánico automático suizo, marca de lujo, estilo clásico, 6 manos, nueva llegada | More complete sentence structure, clearer expression, and more reasonable punctuation |
|
|
3345
|
-
* | Men Key Bag Genuine Cow Leather Buckets Key Cases Pouch Zipper Keychain Auto Car Key Case Women Home Key Holder Wallet | Sac à clés pour hommes en cuir de vache véritable, étuis à clés, pochette à fermeture éclair, porte-clés, étui à clé de voiture, porte-clés pour femmes, organisateur de portefeuille | Porte-clés sac en cuir de vache véritable, étuis à clés en forme de seau, pochette à fermeture éclair, porte-clés auto pour voiture, étui à clés pour femmes, organisateur de clés de maison, portefeuille. | Hommes porte-clés en cuir de vache véritable sac/pochette
|
|
3346
|
-
* ## Preparations and
|
|
3347
|
-
* Text translation supports both synchronization and asynchronous
|
|
3468
|
+
* | Men Key Bag Genuine Cow Leather Buckets Key Cases Pouch Zipper Keychain Auto Car Key Case Women Home Key Holder Wallet | Sac à clés pour hommes en cuir de vache véritable, étuis à clés, pochette à fermeture éclair, porte-clés, étui à clé de voiture, porte-clés pour femmes, organisateur de portefeuille | Porte-clés sac en cuir de vache véritable, étuis à clés en forme de seau, pochette à fermeture éclair, porte-clés auto pour voiture, étui à clés pour femmes, organisateur de clés de maison, portefeuille. | Hommes porte-clés en cuir de vache véritable sac/pochette fermeture éclair porte-clés Auto voiture porte-clés femmes maison porte-clés organisateur portefeuille | Clearer and more explicit product subject. It translates to "key bag" rather than "keychain", avoiding ambiguity in other translations |
|
|
3469
|
+
* ## Preparations and invoke flow
|
|
3470
|
+
* Text translation supports both synchronization and asynchronous invoke methods. This topic describes the asynchronous invoke API. If you need to use synchronous call, see [Text translation - Synchronous API](https://api.aliyun.com/document/Aidge/2026-04-28/TextTranslate).
|
|
3348
3471
|
* The asynchronous APIs for text translation and other capabilities share the same result retrieval flow, RocketMQ subscribe rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
3349
|
-
* For the asynchronous
|
|
3472
|
+
* For the asynchronous invoke integration flow, subscribe rules, message formats and encryption protocols, and detailed integration solutions, see [Asynchronous API invoke instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
3350
3473
|
*
|
|
3351
3474
|
* @param request - TextTranslateAsyncRequest
|
|
3352
3475
|
* @returns TextTranslateAsyncResponse
|
|
@@ -3368,25 +3491,40 @@ export default class Client extends OpenApi {
|
|
|
3368
3491
|
*/
|
|
3369
3492
|
updateDisplayKnowledge(request: $_model.UpdateDisplayKnowledgeRequest): Promise<$_model.UpdateDisplayKnowledgeResponse>;
|
|
3370
3493
|
/**
|
|
3371
|
-
*
|
|
3494
|
+
* Detects vacancies (asynchronous commit).
|
|
3495
|
+
*
|
|
3496
|
+
* @param request - VacancyDetectionRequest
|
|
3497
|
+
* @param runtime - runtime options for this request RuntimeOptions
|
|
3498
|
+
* @returns VacancyDetectionResponse
|
|
3499
|
+
*/
|
|
3500
|
+
vacancyDetectionWithOptions(request: $_model.VacancyDetectionRequest, runtime: $dara.RuntimeOptions): Promise<$_model.VacancyDetectionResponse>;
|
|
3501
|
+
/**
|
|
3502
|
+
* Detects vacancies (asynchronous commit).
|
|
3503
|
+
*
|
|
3504
|
+
* @param request - VacancyDetectionRequest
|
|
3505
|
+
* @returns VacancyDetectionResponse
|
|
3506
|
+
*/
|
|
3507
|
+
vacancyDetection(request: $_model.VacancyDetectionRequest): Promise<$_model.VacancyDetectionResponse>;
|
|
3508
|
+
/**
|
|
3509
|
+
* Generates 5- to 30-second product showcase short videos through the e-commerce AI video generation agent for e-commerce merchants and platforms based on product main images, titles, and selling points, helping customers efficiently produce and distribute e-commerce content. The product supports multiple resolutions such as 720P and 1080P, and allows you to invoke single products quickly and generate multiple products in batches, meeting the needs of daily operations and large-scale product content production. Current capabilities overwrite all clothing categories (tops, pants, skirts, suits, underwear, swimwear, etc.), and the service is gradually expanding to core e-commerce categories such as skincare, cosmetics, food and beverages, and home appliances.
|
|
3372
3510
|
*
|
|
3373
3511
|
* @remarks
|
|
3374
3512
|
* # Scenarios
|
|
3375
|
-
* - Batch generation of product short videos for sellers and platforms: Supports multiple video aspect ratios and sizes (3:4, 9:16), adapting to product detail page video slots, product homepage displays, information feed placements, short video promotions, and event venue materials.
|
|
3376
|
-
* - Quick generation of the first batch of video materials for new product launches: When merchants have a large number of new products to launch, they only need to upload basic information such as product images and titles to quickly generate product showcase videos, model wearing videos, and
|
|
3377
|
-
* - High-fidelity clothing display: Generates model display videos that are closer to real commercial shooting effects
|
|
3378
|
-
* - Generation of high-quality commercial shooting models: Built-in target audience model library, covering plus-size women, plus-size men, swimwear,
|
|
3513
|
+
* - Batch generation of product short videos for sellers and platforms: Supports multiple video aspect ratios and sizes (3:4, 9:16), adapting to scenarios such as product detail page video slots, product homepage displays, information feed placements, short video promotions, and event venue materials.
|
|
3514
|
+
* - Quick generation of the first batch of video materials for new product launches: When merchants have a large number of new products to launch at once, they only need to upload basic information such as product images and titles to quickly generate product showcase videos, model wearing videos, and voiceover explanation videos, helping merchants quickly complete material deployment during the launch phase.
|
|
3515
|
+
* - High-fidelity clothing display: Generates model display videos based on product main images that are closer to real commercial shooting effects, focusing on optimizing capabilities such as pattern restoration, fabric texture retention, accurate color presentation, and stable and consistent details. It supports common e-commerce display methods such as wearing, turning, walking, close-up shots, and multi-angle switching.
|
|
3516
|
+
* - Generation of high-quality commercial shooting models: Built-in target audience model library, covering plus-size women, plus-size men, swimwear, girly style, light mature commuting, youth casual, business menswear, sports and fitness, and other body types, skin colors, and races. It supports various commercial shooting expressions such as standing display, side display, walking display, and partial close-ups.
|
|
3379
3517
|
* - High-frequency e-commerce scenarios such as standard product explanations: Applicable to standardized product categories such as skincare, cosmetics, personal care small appliances, food and beverages, home cleaning daily necessities, and 3C digital products. It can quickly generate product explanation videos based on product main images, titles, selling point information, and explanation scripts.
|
|
3380
|
-
* - Multi-product and multi-selling point testing to improve delivery efficiency: For information feed advertising, short video
|
|
3518
|
+
* - Multi-product and multi-selling point testing to improve delivery efficiency: For information feed advertising, short video placement, and content promotion scenarios, it can quickly generate multiple versions of video materials, making it easy for enterprises to verify the conversion effects of different selling points and presentation forms at a low cost, and improve delivery ROI.
|
|
3381
3519
|
* # Features
|
|
3382
|
-
* - Fully automatic end-to-end batch generation with zero prompt threshold: Callers only need to pass in the product image URL and title, and the system automatically completes the entire process from product understanding
|
|
3383
|
-
* - Highly stable generation with a low waste rate: Adopts a deterministic generation process and multi-layer quality control mechanism to output usable materials with fewer retries, reducing invalid generation and resource waste, and making the overall production cost more controllable.
|
|
3384
|
-
* - E-commerce exclusive product fidelity capability: Built-in multi-round quality inspection
|
|
3385
|
-
* - Reference image first + 6-axis consistency check: Adopts the Reference-Image-First generation paradigm, using the original product image as the only visual source of truth, and automatically performs 6-dimensional VL diagnosis (color drift, pattern missing, contour deviation, structure addition
|
|
3386
|
-
* - Flexible storyboard arrangement and duration control: Supports adjustable video duration of 5 to 30 seconds
|
|
3387
|
-
* - Cinematic camera movement capabilities: Built-in advanced camera movement modes such as bullet time, Grammy slow motion, 360° surround rotation, and
|
|
3520
|
+
* - Fully automatic end-to-end batch generation with zero prompt threshold: Callers only need to pass in the product image URL and title, and the system automatically completes the entire process from product understanding and storyboard planning to video generation, without the need to manually write prompts, select templates, or repeatedly adjust parameters. Built-in multiple agents such as product understanding, image quality inspection, script planning, and director camera movement greatly lower the threshold for use.
|
|
3521
|
+
* - Highly stable generation with a low waste rate: Adopts a deterministic generation process and a multi-layer quality control mechanism to output usable materials with fewer retries, reducing invalid generation and resource waste, and making the overall production cost more controllable.
|
|
3522
|
+
* - E-commerce exclusive product fidelity capability: Built-in multi-round quality inspection agents lock the product state throughout the video generation process (such as zippers will not be pulled open, sleeves will not be rolled down, and prints will not disappear), ensuring product consistency through multi-layer defense of script rewriting, explicit constraint injection, and failure-aware retry.
|
|
3523
|
+
* - Reference image first + 6-axis consistency check: Adopts the Reference-Image-First generation paradigm, using the original product image as the only visual source of truth, and automatically performs 6-dimensional VL diagnosis (color drift, pattern missing, contour deviation, structure addition or reduction, model matching, and dirt detection) to fundamentally eliminate the problem of generated images not looking like the product.
|
|
3524
|
+
* - Flexible storyboard arrangement and duration control: Supports adjustable video duration of 5 to 30 seconds. Agents independently plan independent storyboards to display the product effects in different scenarios. It also supports fixed scene mode to deeply display product tonality under a unified visual style.
|
|
3525
|
+
* - Cinematic camera movement capabilities: Built-in advanced camera movement modes such as bullet time, Grammy slow motion, 360° surround rotation, and full-body model rotation display, achieving deterministic output through precise segmented control.
|
|
3388
3526
|
* - Model library and customization services: Built-in multi-type model resource library, supporting merchants to specify fixed models, customize exclusive model images, and bind brand visual personas for a long time to ensure brand visual consistency.
|
|
3389
|
-
* -
|
|
3527
|
+
* - Adaptation to high-frequency e-commerce content scenarios: Supports multiple resolutions such as 720P and 1080P and multiple aspect ratios such as 3:4 and 9:16, adapting to product detail page video slots, product homepage video displays, waterfall or information feed placements, event venue materials, and new product and promotional video generation.
|
|
3390
3528
|
*
|
|
3391
3529
|
* @param tmpReq - VideoGenerationRequest
|
|
3392
3530
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3394,25 +3532,25 @@ export default class Client extends OpenApi {
|
|
|
3394
3532
|
*/
|
|
3395
3533
|
videoGenerationWithOptions(tmpReq: $_model.VideoGenerationRequest, runtime: $dara.RuntimeOptions): Promise<$_model.VideoGenerationResponse>;
|
|
3396
3534
|
/**
|
|
3397
|
-
*
|
|
3535
|
+
* Generates 5- to 30-second product showcase short videos through the e-commerce AI video generation agent for e-commerce merchants and platforms based on product main images, titles, and selling points, helping customers efficiently produce and distribute e-commerce content. The product supports multiple resolutions such as 720P and 1080P, and allows you to invoke single products quickly and generate multiple products in batches, meeting the needs of daily operations and large-scale product content production. Current capabilities overwrite all clothing categories (tops, pants, skirts, suits, underwear, swimwear, etc.), and the service is gradually expanding to core e-commerce categories such as skincare, cosmetics, food and beverages, and home appliances.
|
|
3398
3536
|
*
|
|
3399
3537
|
* @remarks
|
|
3400
3538
|
* # Scenarios
|
|
3401
|
-
* - Batch generation of product short videos for sellers and platforms: Supports multiple video aspect ratios and sizes (3:4, 9:16), adapting to product detail page video slots, product homepage displays, information feed placements, short video promotions, and event venue materials.
|
|
3402
|
-
* - Quick generation of the first batch of video materials for new product launches: When merchants have a large number of new products to launch, they only need to upload basic information such as product images and titles to quickly generate product showcase videos, model wearing videos, and
|
|
3403
|
-
* - High-fidelity clothing display: Generates model display videos that are closer to real commercial shooting effects
|
|
3404
|
-
* - Generation of high-quality commercial shooting models: Built-in target audience model library, covering plus-size women, plus-size men, swimwear,
|
|
3539
|
+
* - Batch generation of product short videos for sellers and platforms: Supports multiple video aspect ratios and sizes (3:4, 9:16), adapting to scenarios such as product detail page video slots, product homepage displays, information feed placements, short video promotions, and event venue materials.
|
|
3540
|
+
* - Quick generation of the first batch of video materials for new product launches: When merchants have a large number of new products to launch at once, they only need to upload basic information such as product images and titles to quickly generate product showcase videos, model wearing videos, and voiceover explanation videos, helping merchants quickly complete material deployment during the launch phase.
|
|
3541
|
+
* - High-fidelity clothing display: Generates model display videos based on product main images that are closer to real commercial shooting effects, focusing on optimizing capabilities such as pattern restoration, fabric texture retention, accurate color presentation, and stable and consistent details. It supports common e-commerce display methods such as wearing, turning, walking, close-up shots, and multi-angle switching.
|
|
3542
|
+
* - Generation of high-quality commercial shooting models: Built-in target audience model library, covering plus-size women, plus-size men, swimwear, girly style, light mature commuting, youth casual, business menswear, sports and fitness, and other body types, skin colors, and races. It supports various commercial shooting expressions such as standing display, side display, walking display, and partial close-ups.
|
|
3405
3543
|
* - High-frequency e-commerce scenarios such as standard product explanations: Applicable to standardized product categories such as skincare, cosmetics, personal care small appliances, food and beverages, home cleaning daily necessities, and 3C digital products. It can quickly generate product explanation videos based on product main images, titles, selling point information, and explanation scripts.
|
|
3406
|
-
* - Multi-product and multi-selling point testing to improve delivery efficiency: For information feed advertising, short video
|
|
3544
|
+
* - Multi-product and multi-selling point testing to improve delivery efficiency: For information feed advertising, short video placement, and content promotion scenarios, it can quickly generate multiple versions of video materials, making it easy for enterprises to verify the conversion effects of different selling points and presentation forms at a low cost, and improve delivery ROI.
|
|
3407
3545
|
* # Features
|
|
3408
|
-
* - Fully automatic end-to-end batch generation with zero prompt threshold: Callers only need to pass in the product image URL and title, and the system automatically completes the entire process from product understanding
|
|
3409
|
-
* - Highly stable generation with a low waste rate: Adopts a deterministic generation process and multi-layer quality control mechanism to output usable materials with fewer retries, reducing invalid generation and resource waste, and making the overall production cost more controllable.
|
|
3410
|
-
* - E-commerce exclusive product fidelity capability: Built-in multi-round quality inspection
|
|
3411
|
-
* - Reference image first + 6-axis consistency check: Adopts the Reference-Image-First generation paradigm, using the original product image as the only visual source of truth, and automatically performs 6-dimensional VL diagnosis (color drift, pattern missing, contour deviation, structure addition
|
|
3412
|
-
* - Flexible storyboard arrangement and duration control: Supports adjustable video duration of 5 to 30 seconds
|
|
3413
|
-
* - Cinematic camera movement capabilities: Built-in advanced camera movement modes such as bullet time, Grammy slow motion, 360° surround rotation, and
|
|
3546
|
+
* - Fully automatic end-to-end batch generation with zero prompt threshold: Callers only need to pass in the product image URL and title, and the system automatically completes the entire process from product understanding and storyboard planning to video generation, without the need to manually write prompts, select templates, or repeatedly adjust parameters. Built-in multiple agents such as product understanding, image quality inspection, script planning, and director camera movement greatly lower the threshold for use.
|
|
3547
|
+
* - Highly stable generation with a low waste rate: Adopts a deterministic generation process and a multi-layer quality control mechanism to output usable materials with fewer retries, reducing invalid generation and resource waste, and making the overall production cost more controllable.
|
|
3548
|
+
* - E-commerce exclusive product fidelity capability: Built-in multi-round quality inspection agents lock the product state throughout the video generation process (such as zippers will not be pulled open, sleeves will not be rolled down, and prints will not disappear), ensuring product consistency through multi-layer defense of script rewriting, explicit constraint injection, and failure-aware retry.
|
|
3549
|
+
* - Reference image first + 6-axis consistency check: Adopts the Reference-Image-First generation paradigm, using the original product image as the only visual source of truth, and automatically performs 6-dimensional VL diagnosis (color drift, pattern missing, contour deviation, structure addition or reduction, model matching, and dirt detection) to fundamentally eliminate the problem of generated images not looking like the product.
|
|
3550
|
+
* - Flexible storyboard arrangement and duration control: Supports adjustable video duration of 5 to 30 seconds. Agents independently plan independent storyboards to display the product effects in different scenarios. It also supports fixed scene mode to deeply display product tonality under a unified visual style.
|
|
3551
|
+
* - Cinematic camera movement capabilities: Built-in advanced camera movement modes such as bullet time, Grammy slow motion, 360° surround rotation, and full-body model rotation display, achieving deterministic output through precise segmented control.
|
|
3414
3552
|
* - Model library and customization services: Built-in multi-type model resource library, supporting merchants to specify fixed models, customize exclusive model images, and bind brand visual personas for a long time to ensure brand visual consistency.
|
|
3415
|
-
* -
|
|
3553
|
+
* - Adaptation to high-frequency e-commerce content scenarios: Supports multiple resolutions such as 720P and 1080P and multiple aspect ratios such as 3:4 and 9:16, adapting to product detail page video slots, product homepage video displays, waterfall or information feed placements, event venue materials, and new product and promotional video generation.
|
|
3416
3554
|
*
|
|
3417
3555
|
* @param request - VideoGenerationRequest
|
|
3418
3556
|
* @returns VideoGenerationResponse
|
|
@@ -3424,23 +3562,23 @@ export default class Client extends OpenApi {
|
|
|
3424
3562
|
* @remarks
|
|
3425
3563
|
* ## Product introduction
|
|
3426
3564
|
* The video translation API translates the speech and on-screen text in a video into a target language. You can select speech subtitle translation, on-screen text translation, or both. This API applies to scenarios such as multilingual distribution of e-commerce videos, international social media marketing, and global brand advertising.
|
|
3427
|
-
* The API uses an asynchronous invocation mode. After you submit a translation task, you can obtain the TaskId and poll the task status by calling the query API until the task is completed and the result is returned.
|
|
3565
|
+
* The API uses an asynchronous invocation mode. After you submit a translation task, you can obtain the `TaskId` and poll the task status by calling the query API until the task is completed and the result is returned.
|
|
3428
3566
|
* ## Scenarios
|
|
3429
|
-
* * **Cross-border e-commerce video localization**: Translates the speech subtitles and selling point text in product introduction videos into the language of the target market to
|
|
3567
|
+
* * **Cross-border e-commerce video localization**: Translates the speech subtitles and selling point text in product introduction videos into the language of the target market to promote products on overseas platforms.
|
|
3430
3568
|
*
|
|
3431
3569
|
* * **International social media marketing**: Localizes speech subtitles and on-screen text for platforms such as TikTok, Instagram, and YouTube with one click to improve comprehension and conversion rates among overseas users.
|
|
3432
3570
|
*
|
|
3433
|
-
* * **Global brand advertising**: Automatically generates video versions in the languages
|
|
3571
|
+
* * **Global brand advertising**: Automatically generates video versions in the corresponding languages based on the target regions to reduce manual production costs.
|
|
3434
3572
|
*
|
|
3435
3573
|
* * **Training and product instructions**: Translates the speech subtitles and on-screen text in training courses or product demo videos into multiple languages for global teams.
|
|
3436
3574
|
* ## Features
|
|
3437
|
-
* |
|
|
3575
|
+
* | Capability | Identifier | Description |
|
|
3438
3576
|
* | --- | --- | --- |
|
|
3439
|
-
* | Speech subtitle translation | speech | Translates the video speech into target language dubbing. You can choose to
|
|
3440
|
-
* | On-screen text translation | visual | Translates the source language text in the video frames, or only erases the on-screen text without translation. You can choose to erase brand logos. |
|
|
3441
|
-
* Speech subtitle translation (speech) generates target language dubbing based on the spoken content in the video, processes the subtitles
|
|
3442
|
-
* On-screen text translation (visual) targets recognizable original video language text in the video frames, such as titles, product selling points, and descriptive text. It can be used independently without selecting speech subtitle translation first, and does not require the text to appear in the speech. Original subtitles within the processing scope may also be processed.
|
|
3443
|
-
* When both speech and visual are selected, the speech subtitle translation is completed and the video is synthesized first
|
|
3577
|
+
* | Speech subtitle translation | `speech` | Translates the video speech into target language dubbing. You can choose to erase the original subtitles only or replace them with translated subtitles. By default, the original subtitles are not processed and no new subtitles are added. |
|
|
3578
|
+
* | On-screen text translation | `visual` | Translates the source language text in the video frames, or only erases the on-screen text without translation. You can choose to erase brand logos. |
|
|
3579
|
+
* Speech subtitle translation (speech) generates target language dubbing based on the spoken content in the video, processes the subtitles based on the original subtitle processing option, and synthesizes the final video. Original subtitles refer to the existing subtitles in the video frames that correspond to the spoken content. Replacing with translated subtitles erases the original subtitles first and then adds subtitles synchronized with the translated speech.
|
|
3580
|
+
* On-screen text translation (visual) targets the recognizable original video language text in the video frames, such as titles, product selling points, and descriptive text. It can be used independently without selecting speech subtitle translation first, and does not require the text to appear in the speech. Original subtitles within the processing scope may also be processed.
|
|
3581
|
+
* When both speech and visual are selected, the speech subtitle translation is completed and the video is synthesized first, and then the on-screen text processing is performed on this video. The translated dubbing is retained, and a final video is output. The order of capabilities in the array does not affect the execution order. Therefore, not processing original subtitles only means that no subtitles are erased or added during the speech subtitle phase, and subsequent on-screen text processing may still change the original subtitles. Subtitles that have been replaced with translated subtitles are retained during subsequent on-screen text processing.
|
|
3444
3582
|
*
|
|
3445
3583
|
* @param tmpReq - VideoTranslationRequest
|
|
3446
3584
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3453,58 +3591,61 @@ export default class Client extends OpenApi {
|
|
|
3453
3591
|
* @remarks
|
|
3454
3592
|
* ## Product introduction
|
|
3455
3593
|
* The video translation API translates the speech and on-screen text in a video into a target language. You can select speech subtitle translation, on-screen text translation, or both. This API applies to scenarios such as multilingual distribution of e-commerce videos, international social media marketing, and global brand advertising.
|
|
3456
|
-
* The API uses an asynchronous invocation mode. After you submit a translation task, you can obtain the TaskId and poll the task status by calling the query API until the task is completed and the result is returned.
|
|
3594
|
+
* The API uses an asynchronous invocation mode. After you submit a translation task, you can obtain the `TaskId` and poll the task status by calling the query API until the task is completed and the result is returned.
|
|
3457
3595
|
* ## Scenarios
|
|
3458
|
-
* * **Cross-border e-commerce video localization**: Translates the speech subtitles and selling point text in product introduction videos into the language of the target market to
|
|
3596
|
+
* * **Cross-border e-commerce video localization**: Translates the speech subtitles and selling point text in product introduction videos into the language of the target market to promote products on overseas platforms.
|
|
3459
3597
|
*
|
|
3460
3598
|
* * **International social media marketing**: Localizes speech subtitles and on-screen text for platforms such as TikTok, Instagram, and YouTube with one click to improve comprehension and conversion rates among overseas users.
|
|
3461
3599
|
*
|
|
3462
|
-
* * **Global brand advertising**: Automatically generates video versions in the languages
|
|
3600
|
+
* * **Global brand advertising**: Automatically generates video versions in the corresponding languages based on the target regions to reduce manual production costs.
|
|
3463
3601
|
*
|
|
3464
3602
|
* * **Training and product instructions**: Translates the speech subtitles and on-screen text in training courses or product demo videos into multiple languages for global teams.
|
|
3465
3603
|
* ## Features
|
|
3466
|
-
* |
|
|
3604
|
+
* | Capability | Identifier | Description |
|
|
3467
3605
|
* | --- | --- | --- |
|
|
3468
|
-
* | Speech subtitle translation | speech | Translates the video speech into target language dubbing. You can choose to
|
|
3469
|
-
* | On-screen text translation | visual | Translates the source language text in the video frames, or only erases the on-screen text without translation. You can choose to erase brand logos. |
|
|
3470
|
-
* Speech subtitle translation (speech) generates target language dubbing based on the spoken content in the video, processes the subtitles
|
|
3471
|
-
* On-screen text translation (visual) targets recognizable original video language text in the video frames, such as titles, product selling points, and descriptive text. It can be used independently without selecting speech subtitle translation first, and does not require the text to appear in the speech. Original subtitles within the processing scope may also be processed.
|
|
3472
|
-
* When both speech and visual are selected, the speech subtitle translation is completed and the video is synthesized first
|
|
3606
|
+
* | Speech subtitle translation | `speech` | Translates the video speech into target language dubbing. You can choose to erase the original subtitles only or replace them with translated subtitles. By default, the original subtitles are not processed and no new subtitles are added. |
|
|
3607
|
+
* | On-screen text translation | `visual` | Translates the source language text in the video frames, or only erases the on-screen text without translation. You can choose to erase brand logos. |
|
|
3608
|
+
* Speech subtitle translation (speech) generates target language dubbing based on the spoken content in the video, processes the subtitles based on the original subtitle processing option, and synthesizes the final video. Original subtitles refer to the existing subtitles in the video frames that correspond to the spoken content. Replacing with translated subtitles erases the original subtitles first and then adds subtitles synchronized with the translated speech.
|
|
3609
|
+
* On-screen text translation (visual) targets the recognizable original video language text in the video frames, such as titles, product selling points, and descriptive text. It can be used independently without selecting speech subtitle translation first, and does not require the text to appear in the speech. Original subtitles within the processing scope may also be processed.
|
|
3610
|
+
* When both speech and visual are selected, the speech subtitle translation is completed and the video is synthesized first, and then the on-screen text processing is performed on this video. The translated dubbing is retained, and a final video is output. The order of capabilities in the array does not affect the execution order. Therefore, not processing original subtitles only means that no subtitles are erased or added during the speech subtitle phase, and subsequent on-screen text processing may still change the original subtitles. Subtitles that have been replaced with translated subtitles are retained during subsequent on-screen text processing.
|
|
3473
3611
|
*
|
|
3474
3612
|
* @param request - VideoTranslationRequest
|
|
3475
3613
|
* @returns VideoTranslationResponse
|
|
3476
3614
|
*/
|
|
3477
3615
|
videoTranslation(request: $_model.VideoTranslationRequest): Promise<$_model.VideoTranslationResponse>;
|
|
3478
3616
|
/**
|
|
3479
|
-
* Generates virtual try-on images by using AI algorithms
|
|
3617
|
+
* Generates virtual try-on images by using AI algorithms to replace a model\\"s clothing with a specified garment. The service preserves the model\\"s pose, facial features, and background details while ensuring a realistic and well-fitted appearance. Users only need to provide the URLs of the original model and garment images to obtain the processed images.
|
|
3480
3618
|
*
|
|
3481
3619
|
* @remarks
|
|
3620
|
+
* *Note:**
|
|
3621
|
+
* VirtualTryOn is an early version that supports only single-item try-on and is scheduled to be deprecated soon.
|
|
3622
|
+
* New features such as multi-item outfit matching, model replacement, and pose replacement are now available in [Virtual try-on (AiTryOn)](https://api.aliyun.com/document/Aidge/2026-04-28/AiTryOn). Refer to the new API for integration.
|
|
3482
3623
|
* ## Scenarios
|
|
3483
|
-
* - **Virtual try-on for
|
|
3484
|
-
* Supports various
|
|
3485
|
-
* - **Virtual try-on for
|
|
3486
|
-
* Supports virtual try-on for
|
|
3624
|
+
* - **Virtual try-on for apparel:**
|
|
3625
|
+
* Supports various apparel categories such as tops, bottoms, jumpsuits, and dresses. After users upload a model image and a product image, the service generates natural and realistic try-on effects to intuitively display how the garment looks on the model.
|
|
3626
|
+
* - **Virtual try-on for footwear and headwear:**
|
|
3627
|
+
* Supports virtual try-on for products such as shoes and hats. The service intelligently matches the product position and proportion based on the model\\"s pose and body parts to present a coordinated and realistic wearing effect.
|
|
3487
3628
|
* - **E-commerce product display and marketing:**
|
|
3488
|
-
*
|
|
3629
|
+
* Helps merchants quickly generate model try-on images for different products. This reduces the costs of traditional photography, outfit changes, and post-production, and improves the production efficiency of product images.
|
|
3489
3630
|
* - **Online shopping experience optimization:**
|
|
3490
|
-
* Allows consumers to preview the wearing effect of products through virtual try-on
|
|
3631
|
+
* Allows consumers to preview the wearing effect of products through virtual try-on. This provides a more intuitive understanding of the product style, matching, and overall effect to assist in purchase decisions and enhance the shopping experience.
|
|
3491
3632
|
* ## Features
|
|
3492
|
-
* - **First,
|
|
3493
|
-
* - a. Model image:
|
|
3494
|
-
* - b. Product image:
|
|
3495
|
-
* - **Second,
|
|
3496
|
-
* - a. Specify product type:
|
|
3497
|
-
* - b. Automatic type recognition:
|
|
3498
|
-
* - **Finally, the system combines the model image, product image, and product type to generate a virtual try-on image,
|
|
3499
|
-
* - a. Preserve model details:
|
|
3500
|
-
* - b. Maintain image consistency:
|
|
3501
|
-
* - c. Generate try-on effect:
|
|
3633
|
+
* - **First, users need to input a model image and a product image. The system uses the model image as the try-on subject and applies the garment from the product image to the model:**
|
|
3634
|
+
* - a. Model image: The image of the person for the virtual try-on.
|
|
3635
|
+
* - b. Product image: The image of the garment, shoes, or hat to be worn by the model.
|
|
3636
|
+
* - **Second, users can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
3637
|
+
* - a. Specify product type: Users can directly input the type of the current product. The system will process it according to the specified type.
|
|
3638
|
+
* - b. Automatic type recognition: If users do not input the product type, the system will automatically recognize the product category in the product image and perform the virtual try-on based on the recognition result.
|
|
3639
|
+
* - **Finally, the system combines the model image, product image, and product type to generate a virtual try-on image, displaying the wearing effect of the product on the model:**
|
|
3640
|
+
* - a. Preserve model details: The generation process does not alter the appearance, hairstyle, pose, body shape, or other details of the person in the original model image.
|
|
3641
|
+
* - b. Maintain image consistency: The background, composition, lighting, and overall visual effect of the original model image remain unchanged. Only the wearing area corresponding to the product is processed.
|
|
3642
|
+
* - c. Generate try-on effect: The product is naturally applied to the model, fitting the pose and body structure of the person to generate a coordinated and realistic virtual try-on image.
|
|
3502
3643
|
* ## Examples
|
|
3503
3644
|
* | **Type** | **Model image** | **Garment image** | **Try-on result** |
|
|
3504
3645
|
* | --- | --- | --- | --- |
|
|
3505
|
-
* | Tops |  |  |  |  |
|
|
3506
3647
|
* | Bottoms |  |  |  |
|
|
3507
|
-
* | Shoes |  |  |  |  |
|
|
3508
3649
|
* | Jumpsuits |  |  |  |
|
|
3509
3650
|
* | Dresses |  |  |  |
|
|
3510
3651
|
* | Hats |  |  |  |
|
|
@@ -3515,35 +3656,38 @@ export default class Client extends OpenApi {
|
|
|
3515
3656
|
*/
|
|
3516
3657
|
virtualTryOnWithOptions(request: $_model.VirtualTryOnRequest, runtime: $dara.RuntimeOptions): Promise<$_model.VirtualTryOnResponse>;
|
|
3517
3658
|
/**
|
|
3518
|
-
* Generates virtual try-on images by using AI algorithms
|
|
3659
|
+
* Generates virtual try-on images by using AI algorithms to replace a model\\"s clothing with a specified garment. The service preserves the model\\"s pose, facial features, and background details while ensuring a realistic and well-fitted appearance. Users only need to provide the URLs of the original model and garment images to obtain the processed images.
|
|
3519
3660
|
*
|
|
3520
3661
|
* @remarks
|
|
3662
|
+
* *Note:**
|
|
3663
|
+
* VirtualTryOn is an early version that supports only single-item try-on and is scheduled to be deprecated soon.
|
|
3664
|
+
* New features such as multi-item outfit matching, model replacement, and pose replacement are now available in [Virtual try-on (AiTryOn)](https://api.aliyun.com/document/Aidge/2026-04-28/AiTryOn). Refer to the new API for integration.
|
|
3521
3665
|
* ## Scenarios
|
|
3522
|
-
* - **Virtual try-on for
|
|
3523
|
-
* Supports various
|
|
3524
|
-
* - **Virtual try-on for
|
|
3525
|
-
* Supports virtual try-on for
|
|
3666
|
+
* - **Virtual try-on for apparel:**
|
|
3667
|
+
* Supports various apparel categories such as tops, bottoms, jumpsuits, and dresses. After users upload a model image and a product image, the service generates natural and realistic try-on effects to intuitively display how the garment looks on the model.
|
|
3668
|
+
* - **Virtual try-on for footwear and headwear:**
|
|
3669
|
+
* Supports virtual try-on for products such as shoes and hats. The service intelligently matches the product position and proportion based on the model\\"s pose and body parts to present a coordinated and realistic wearing effect.
|
|
3526
3670
|
* - **E-commerce product display and marketing:**
|
|
3527
|
-
*
|
|
3671
|
+
* Helps merchants quickly generate model try-on images for different products. This reduces the costs of traditional photography, outfit changes, and post-production, and improves the production efficiency of product images.
|
|
3528
3672
|
* - **Online shopping experience optimization:**
|
|
3529
|
-
* Allows consumers to preview the wearing effect of products through virtual try-on
|
|
3673
|
+
* Allows consumers to preview the wearing effect of products through virtual try-on. This provides a more intuitive understanding of the product style, matching, and overall effect to assist in purchase decisions and enhance the shopping experience.
|
|
3530
3674
|
* ## Features
|
|
3531
|
-
* - **First,
|
|
3532
|
-
* - a. Model image:
|
|
3533
|
-
* - b. Product image:
|
|
3534
|
-
* - **Second,
|
|
3535
|
-
* - a. Specify product type:
|
|
3536
|
-
* - b. Automatic type recognition:
|
|
3537
|
-
* - **Finally, the system combines the model image, product image, and product type to generate a virtual try-on image,
|
|
3538
|
-
* - a. Preserve model details:
|
|
3539
|
-
* - b. Maintain image consistency:
|
|
3540
|
-
* - c. Generate try-on effect:
|
|
3675
|
+
* - **First, users need to input a model image and a product image. The system uses the model image as the try-on subject and applies the garment from the product image to the model:**
|
|
3676
|
+
* - a. Model image: The image of the person for the virtual try-on.
|
|
3677
|
+
* - b. Product image: The image of the garment, shoes, or hat to be worn by the model.
|
|
3678
|
+
* - **Second, users can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
3679
|
+
* - a. Specify product type: Users can directly input the type of the current product. The system will process it according to the specified type.
|
|
3680
|
+
* - b. Automatic type recognition: If users do not input the product type, the system will automatically recognize the product category in the product image and perform the virtual try-on based on the recognition result.
|
|
3681
|
+
* - **Finally, the system combines the model image, product image, and product type to generate a virtual try-on image, displaying the wearing effect of the product on the model:**
|
|
3682
|
+
* - a. Preserve model details: The generation process does not alter the appearance, hairstyle, pose, body shape, or other details of the person in the original model image.
|
|
3683
|
+
* - b. Maintain image consistency: The background, composition, lighting, and overall visual effect of the original model image remain unchanged. Only the wearing area corresponding to the product is processed.
|
|
3684
|
+
* - c. Generate try-on effect: The product is naturally applied to the model, fitting the pose and body structure of the person to generate a coordinated and realistic virtual try-on image.
|
|
3541
3685
|
* ## Examples
|
|
3542
3686
|
* | **Type** | **Model image** | **Garment image** | **Try-on result** |
|
|
3543
3687
|
* | --- | --- | --- | --- |
|
|
3544
|
-
* | Tops |  |  |  |  |
|
|
3545
3689
|
* | Bottoms |  |  |  |
|
|
3546
|
-
* | Shoes |  |  |  |  |
|
|
3547
3691
|
* | Jumpsuits |  |  |  |
|
|
3548
3692
|
* | Dresses |  |  |  |
|
|
3549
3693
|
* | Hats |  |  |  |
|