@alicloud/aidge20260428 5.11.0 → 5.12.0
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 +803 -674
- package/dist/client.js +830 -674
- package/dist/client.js.map +1 -1
- package/dist/models/AddDisplayKnowledgeRequest.d.ts +2 -2
- package/dist/models/AddDisplayKnowledgeResponseBody.d.ts +7 -7
- package/dist/models/AiTryOnRequest.d.ts +3 -3
- package/dist/models/AiTryOnResponseBody.d.ts +2 -4
- package/dist/models/AiTryOnResponseBody.js.map +1 -1
- package/dist/models/AssetOptimizeLiteRequest.d.ts +1 -1
- package/dist/models/AssetOptimizeLiteResponseBody.d.ts +2 -2
- package/dist/models/AssetOptimizeProRequest.d.ts +12 -12
- package/dist/models/AssetOptimizeProResponseBody.d.ts +6 -6
- package/dist/models/AssetOptimizeProShrinkRequest.d.ts +12 -12
- package/dist/models/CategoryAttributeMatchRequest.d.ts +9 -9
- package/dist/models/CategoryAttributeMatchResponseBody.d.ts +13 -13
- package/dist/models/CategoryAttributeMatchShrinkRequest.d.ts +9 -9
- package/dist/models/CategoryMatchRequest.d.ts +10 -10
- package/dist/models/CategoryMatchResponseBody.d.ts +12 -12
- package/dist/models/DeleteDisplayKnowledgeRequest.d.ts +1 -1
- package/dist/models/DeleteDisplayKnowledgeResponseBody.d.ts +8 -8
- package/dist/models/DeleteDisplayKnowledgeShrinkRequest.d.ts +1 -1
- package/dist/models/DiduiAreaDeductionProResponseBody.d.ts +4 -4
- package/dist/models/DiduiAreaDeductionRequest.d.ts +8 -8
- package/dist/models/DiduiAreaDeductionResponseBody.d.ts +6 -6
- package/dist/models/DiduiAreaDeductionShrinkRequest.d.ts +3 -3
- package/dist/models/DocumentTranslateRequest.d.ts +6 -7
- package/dist/models/DocumentTranslateRequest.js.map +1 -1
- package/dist/models/DocumentTranslateResponseBody.d.ts +8 -6
- package/dist/models/DocumentTranslateResponseBody.js.map +1 -1
- package/dist/models/EcomVideoRecreationRequest.d.ts +15 -15
- package/dist/models/EcomVideoRecreationResponseBody.d.ts +1 -1
- package/dist/models/EcomVideoRecreationShrinkRequest.d.ts +2 -2
- package/dist/models/GeneralRephotographyDetectionRequest.d.ts +1 -1
- package/dist/models/GeneralRephotographyDetectionResponseBody.d.ts +11 -11
- package/dist/models/GenerateProductContentRequest.d.ts +37 -3
- package/dist/models/GenerateProductContentRequest.js.map +1 -1
- package/dist/models/GenerateProductContentResponseBody.d.ts +40 -0
- package/dist/models/GenerateProductContentResponseBody.js.map +1 -1
- package/dist/models/ImageCroppingRequest.d.ts +1 -1
- package/dist/models/ImageCroppingResponseBody.d.ts +1 -3
- package/dist/models/ImageCroppingResponseBody.js.map +1 -1
- package/dist/models/ImageMattingAsyncRequest.d.ts +2 -2
- package/dist/models/ImageMattingAsyncResponseBody.d.ts +4 -6
- package/dist/models/ImageMattingAsyncResponseBody.js.map +1 -1
- package/dist/models/ImageMattingRequest.d.ts +5 -6
- package/dist/models/ImageMattingRequest.js.map +1 -1
- package/dist/models/ImageMattingResponseBody.d.ts +26 -7
- package/dist/models/ImageMattingResponseBody.js +2 -0
- package/dist/models/ImageMattingResponseBody.js.map +1 -1
- package/dist/models/ImageRecognitionAsyncRequest.d.ts +10 -35
- package/dist/models/ImageRecognitionAsyncRequest.js.map +1 -1
- package/dist/models/ImageRecognitionAsyncResponseBody.d.ts +5 -7
- package/dist/models/ImageRecognitionAsyncResponseBody.js.map +1 -1
- package/dist/models/ImageRecognitionAsyncShrinkRequest.d.ts +10 -35
- package/dist/models/ImageRecognitionAsyncShrinkRequest.js.map +1 -1
- package/dist/models/ImageRecognitionRequest.d.ts +4 -4
- package/dist/models/ImageRecognitionResponseBody.d.ts +7 -7
- package/dist/models/ImageRecognitionShrinkRequest.d.ts +4 -4
- package/dist/models/ImageRemovalProAsyncRequest.d.ts +2 -3
- package/dist/models/ImageRemovalProAsyncRequest.js.map +1 -1
- package/dist/models/ImageRemovalProAsyncResponseBody.d.ts +5 -5
- package/dist/models/ImageRemovalProRequest.d.ts +2 -3
- package/dist/models/ImageRemovalProRequest.js.map +1 -1
- package/dist/models/ImageRemovalProResponseBody.d.ts +6 -6
- package/dist/models/ImageRemoveAsyncRequest.d.ts +7 -18
- package/dist/models/ImageRemoveAsyncRequest.js.map +1 -1
- package/dist/models/ImageRemoveAsyncResponseBody.d.ts +5 -7
- package/dist/models/ImageRemoveAsyncResponseBody.js.map +1 -1
- package/dist/models/ImageRemoveAsyncShrinkRequest.d.ts +7 -18
- package/dist/models/ImageRemoveAsyncShrinkRequest.js.map +1 -1
- package/dist/models/ImageTranslationPlusAsyncRequest.d.ts +10 -10
- package/dist/models/ImageTranslationPlusAsyncResponseBody.d.ts +6 -6
- package/dist/models/ImageTranslationPlusRequest.d.ts +2 -2
- package/dist/models/ImageTranslationPlusResponseBody.d.ts +5 -5
- package/dist/models/ImageTranslationProAsyncRequest.d.ts +6 -6
- package/dist/models/ImageTranslationProAsyncResponseBody.d.ts +5 -5
- package/dist/models/ImageTranslationProRequest.d.ts +16 -17
- package/dist/models/ImageTranslationProRequest.js.map +1 -1
- package/dist/models/ImageTranslationProResponseBody.d.ts +24 -26
- package/dist/models/ImageTranslationProResponseBody.js.map +1 -1
- package/dist/models/ImageTranslationStandardAsyncRequest.d.ts +2 -2
- package/dist/models/ImageTranslationStandardAsyncResponseBody.d.ts +3 -3
- package/dist/models/ImageTranslationStandardRequest.d.ts +12 -12
- package/dist/models/ImageTranslationStandardResponseBody.d.ts +54 -9
- package/dist/models/ImageTranslationStandardResponseBody.js.map +1 -1
- package/dist/models/ImageUpscaleRequest.d.ts +31 -0
- package/dist/models/ImageUpscaleRequest.js +60 -0
- package/dist/models/ImageUpscaleRequest.js.map +1 -0
- package/dist/models/ImageUpscaleResponse.d.ts +19 -0
- package/dist/models/ImageUpscaleResponse.js +69 -0
- package/dist/models/ImageUpscaleResponse.js.map +1 -0
- package/dist/models/ImageUpscaleResponseBody.d.ts +160 -0
- package/dist/models/ImageUpscaleResponseBody.js +146 -0
- package/dist/models/ImageUpscaleResponseBody.js.map +1 -0
- package/dist/models/QueryDisplayKnowledgeRequest.d.ts +1 -1
- package/dist/models/QueryDisplayKnowledgeResponseBody.d.ts +11 -11
- package/dist/models/QueryDisplayKnowledgeShrinkRequest.d.ts +1 -1
- package/dist/models/SizeChartExtractAsyncRequest.d.ts +3 -3
- package/dist/models/SizeChartExtractAsyncResponseBody.d.ts +2 -2
- package/dist/models/SizeChartExtractAsyncShrinkRequest.d.ts +3 -3
- package/dist/models/TextTranslateAsyncRequest.d.ts +12 -12
- package/dist/models/TextTranslateAsyncResponseBody.d.ts +3 -3
- package/dist/models/TextTranslateAsyncShrinkRequest.d.ts +12 -12
- package/dist/models/UpdateDisplayKnowledgeRequest.d.ts +1 -1
- package/dist/models/UpdateDisplayKnowledgeResponseBody.d.ts +6 -6
- package/dist/models/UpdateDisplayKnowledgeShrinkRequest.d.ts +1 -1
- package/dist/models/VideoTranslationRequest.d.ts +17 -8
- package/dist/models/VideoTranslationRequest.js.map +1 -1
- package/dist/models/VideoTranslationResponseBody.d.ts +6 -4
- package/dist/models/VideoTranslationResponseBody.js.map +1 -1
- package/dist/models/VideoTranslationShrinkRequest.d.ts +17 -8
- package/dist/models/VideoTranslationShrinkRequest.js.map +1 -1
- package/dist/models/VirtualTryOnRequest.d.ts +3 -3
- package/dist/models/VirtualTryOnResponseBody.d.ts +7 -5
- package/dist/models/VirtualTryOnResponseBody.js.map +1 -1
- package/dist/models/model.d.ts +6 -0
- package/dist/models/model.js +18 -6
- package/dist/models/model.js.map +1 -1
- package/package.json +1 -1
- package/src/client.ts +834 -674
- package/src/models/AddDisplayKnowledgeRequest.ts +2 -2
- package/src/models/AddDisplayKnowledgeResponseBody.ts +7 -7
- package/src/models/AiTryOnRequest.ts +3 -3
- package/src/models/AiTryOnResponseBody.ts +2 -4
- package/src/models/AssetOptimizeLiteRequest.ts +1 -1
- package/src/models/AssetOptimizeLiteResponseBody.ts +2 -2
- package/src/models/AssetOptimizeProRequest.ts +12 -12
- package/src/models/AssetOptimizeProResponseBody.ts +6 -6
- package/src/models/AssetOptimizeProShrinkRequest.ts +12 -12
- package/src/models/CategoryAttributeMatchRequest.ts +9 -9
- package/src/models/CategoryAttributeMatchResponseBody.ts +13 -13
- package/src/models/CategoryAttributeMatchShrinkRequest.ts +9 -9
- package/src/models/CategoryMatchRequest.ts +10 -10
- package/src/models/CategoryMatchResponseBody.ts +12 -12
- package/src/models/DeleteDisplayKnowledgeRequest.ts +1 -1
- package/src/models/DeleteDisplayKnowledgeResponseBody.ts +8 -8
- package/src/models/DeleteDisplayKnowledgeShrinkRequest.ts +1 -1
- package/src/models/DiduiAreaDeductionProResponseBody.ts +4 -4
- package/src/models/DiduiAreaDeductionRequest.ts +8 -8
- package/src/models/DiduiAreaDeductionResponseBody.ts +6 -6
- package/src/models/DiduiAreaDeductionShrinkRequest.ts +3 -3
- package/src/models/DocumentTranslateRequest.ts +6 -7
- package/src/models/DocumentTranslateResponseBody.ts +8 -6
- package/src/models/EcomVideoRecreationRequest.ts +15 -15
- package/src/models/EcomVideoRecreationResponseBody.ts +1 -1
- package/src/models/EcomVideoRecreationShrinkRequest.ts +2 -2
- package/src/models/GeneralRephotographyDetectionRequest.ts +1 -1
- package/src/models/GeneralRephotographyDetectionResponseBody.ts +11 -11
- package/src/models/GenerateProductContentRequest.ts +37 -3
- package/src/models/GenerateProductContentResponseBody.ts +40 -0
- package/src/models/ImageCroppingRequest.ts +1 -1
- package/src/models/ImageCroppingResponseBody.ts +1 -3
- package/src/models/ImageMattingAsyncRequest.ts +2 -2
- package/src/models/ImageMattingAsyncResponseBody.ts +4 -6
- package/src/models/ImageMattingRequest.ts +5 -6
- package/src/models/ImageMattingResponseBody.ts +28 -7
- package/src/models/ImageRecognitionAsyncRequest.ts +10 -35
- package/src/models/ImageRecognitionAsyncResponseBody.ts +5 -7
- package/src/models/ImageRecognitionAsyncShrinkRequest.ts +10 -35
- package/src/models/ImageRecognitionRequest.ts +4 -4
- package/src/models/ImageRecognitionResponseBody.ts +7 -7
- package/src/models/ImageRecognitionShrinkRequest.ts +4 -4
- package/src/models/ImageRemovalProAsyncRequest.ts +2 -3
- package/src/models/ImageRemovalProAsyncResponseBody.ts +5 -5
- package/src/models/ImageRemovalProRequest.ts +2 -3
- package/src/models/ImageRemovalProResponseBody.ts +6 -6
- package/src/models/ImageRemoveAsyncRequest.ts +7 -18
- package/src/models/ImageRemoveAsyncResponseBody.ts +5 -7
- package/src/models/ImageRemoveAsyncShrinkRequest.ts +7 -18
- package/src/models/ImageTranslationPlusAsyncRequest.ts +10 -10
- package/src/models/ImageTranslationPlusAsyncResponseBody.ts +6 -6
- package/src/models/ImageTranslationPlusRequest.ts +2 -2
- package/src/models/ImageTranslationPlusResponseBody.ts +5 -5
- package/src/models/ImageTranslationProAsyncRequest.ts +6 -6
- package/src/models/ImageTranslationProAsyncResponseBody.ts +5 -5
- package/src/models/ImageTranslationProRequest.ts +17 -18
- package/src/models/ImageTranslationProResponseBody.ts +24 -26
- package/src/models/ImageTranslationStandardAsyncRequest.ts +2 -2
- package/src/models/ImageTranslationStandardAsyncResponseBody.ts +3 -3
- package/src/models/ImageTranslationStandardRequest.ts +12 -12
- package/src/models/ImageTranslationStandardResponseBody.ts +54 -9
- package/src/models/ImageUpscaleRequest.ts +46 -0
- package/src/models/ImageUpscaleResponse.ts +40 -0
- package/src/models/ImageUpscaleResponseBody.ts +234 -0
- package/src/models/QueryDisplayKnowledgeRequest.ts +1 -1
- package/src/models/QueryDisplayKnowledgeResponseBody.ts +11 -11
- package/src/models/QueryDisplayKnowledgeShrinkRequest.ts +1 -1
- package/src/models/SizeChartExtractAsyncRequest.ts +3 -3
- package/src/models/SizeChartExtractAsyncResponseBody.ts +2 -2
- package/src/models/SizeChartExtractAsyncShrinkRequest.ts +3 -3
- package/src/models/TextTranslateAsyncRequest.ts +12 -12
- package/src/models/TextTranslateAsyncResponseBody.ts +3 -3
- package/src/models/TextTranslateAsyncShrinkRequest.ts +12 -12
- package/src/models/UpdateDisplayKnowledgeRequest.ts +1 -1
- package/src/models/UpdateDisplayKnowledgeResponseBody.ts +6 -6
- package/src/models/UpdateDisplayKnowledgeShrinkRequest.ts +1 -1
- package/src/models/VideoTranslationRequest.ts +17 -8
- package/src/models/VideoTranslationResponseBody.ts +6 -4
- package/src/models/VideoTranslationShrinkRequest.ts +17 -8
- package/src/models/VirtualTryOnRequest.ts +3 -3
- package/src/models/VirtualTryOnResponseBody.ts +7 -5
- package/src/models/model.ts +6 -0
package/dist/client.d.ts
CHANGED
|
@@ -24,38 +24,38 @@ export default class Client extends OpenApi {
|
|
|
24
24
|
*/
|
|
25
25
|
addDisplayKnowledge(request: $_model.AddDisplayKnowledgeRequest): Promise<$_model.AddDisplayKnowledgeResponse>;
|
|
26
26
|
/**
|
|
27
|
-
* Generates virtual try-on
|
|
27
|
+
* Generates a virtual try-on image by applying a clothing item to a model based on the provided clothing and model images. This AI-powered image generation API service replaces the model\\"s existing clothing with the specified item while preserving the model\\"s pose, facial features, and other background details. It ensures a realistic and well-fitted appearance of the clothing on the model. You can obtain the processed image by providing the URLs of the original images.
|
|
28
28
|
*
|
|
29
29
|
* @remarks
|
|
30
30
|
* ## Scenarios
|
|
31
31
|
* - **Virtual try-on for clothing:**
|
|
32
|
-
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After you upload a model image and a
|
|
32
|
+
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After you upload a model image and a product image, the service generates a natural and realistic try-on effect to intuitively display how the clothing looks on the model.
|
|
33
33
|
* - **Virtual try-on for shoes and hats:**
|
|
34
|
-
* Supports virtual try-on for
|
|
34
|
+
* Supports virtual try-on for products such as shoes and hats. The service intelligently matches the position and proportion of the product based on the model\\"s pose and body parts to present a coordinated and realistic wearing effect.
|
|
35
35
|
* - **E-commerce product display and marketing:**
|
|
36
|
-
* Helps merchants quickly generate model try-on images for different products
|
|
36
|
+
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional photography, outfit changes, and post-production, and improving the production efficiency of product images.
|
|
37
37
|
* - **Online shopping experience optimization:**
|
|
38
|
-
* Allows consumers to preview the wearing effect of products through virtual try-on
|
|
38
|
+
* Allows consumers to preview the wearing effect of products through virtual try-on, providing a more intuitive understanding of the style, matching, and overall effect of the products, which assists in purchase decisions and enhances the shopping experience.
|
|
39
39
|
* ## Features
|
|
40
|
-
* - **
|
|
41
|
-
* - a. Model image: The image of the person who will
|
|
40
|
+
* - **First, you need to provide a model image and a product image. The system uses the model image as the try-on subject and applies the clothing from the product image to the model:**
|
|
41
|
+
* - a. Model image: The image of the person who will virtually try on the clothing.
|
|
42
42
|
* - b. Product image: The image of the clothing, shoes, or hat to be worn by the model.
|
|
43
|
-
* - **
|
|
44
|
-
* - a. Specify product type: You can directly specify the type of the current product, and the system will process it
|
|
43
|
+
* - **Second, you can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
44
|
+
* - a. Specify product type: You can directly specify the type of the current product, and the system will process it according to the specified type.
|
|
45
45
|
* - b. Automatic type recognition: If you do not specify the product type, the system automatically recognizes the product category in the product image and performs the virtual try-on based on the recognition result.
|
|
46
|
-
* - **
|
|
46
|
+
* - **Finally, the system generates a virtual try-on image by combining the model image, product image, and product type to display the wearing effect of the product on the model:**
|
|
47
47
|
* - 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.
|
|
48
48
|
* - 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.
|
|
49
49
|
* - c. Generate try-on effect: The product is naturally applied to the model, fitting the person\\"s pose and body structure to generate a coordinated and realistic virtual try-on image.
|
|
50
50
|
* ## Examples
|
|
51
|
-
* | **Type** | **Model image** | **
|
|
51
|
+
* | **Type** | **Model image** | **Clothing image** | **Try-on result image** |
|
|
52
52
|
* | --- | --- | --- | --- |
|
|
53
|
-
* | Tops |  |  |  |  |  |  |
|
|
54
|
+
* | Bottoms |  |  |  |
|
|
55
|
+
* | Shoes |  |  |  |
|
|
56
56
|
* | Jumpsuits |  |  |  |
|
|
57
57
|
* | Dresses |  |  |  |
|
|
58
|
-
* | Hats |  |  |  |  |
|
|
59
59
|
*
|
|
60
60
|
* @param request - AiTryOnRequest
|
|
61
61
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -63,58 +63,58 @@ export default class Client extends OpenApi {
|
|
|
63
63
|
*/
|
|
64
64
|
aiTryOnWithOptions(request: $_model.AiTryOnRequest, runtime: $dara.RuntimeOptions): Promise<$_model.AiTryOnResponse>;
|
|
65
65
|
/**
|
|
66
|
-
* Generates virtual try-on
|
|
66
|
+
* Generates a virtual try-on image by applying a clothing item to a model based on the provided clothing and model images. This AI-powered image generation API service replaces the model\\"s existing clothing with the specified item while preserving the model\\"s pose, facial features, and other background details. It ensures a realistic and well-fitted appearance of the clothing on the model. You can obtain the processed image by providing the URLs of the original images.
|
|
67
67
|
*
|
|
68
68
|
* @remarks
|
|
69
69
|
* ## Scenarios
|
|
70
70
|
* - **Virtual try-on for clothing:**
|
|
71
|
-
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After you upload a model image and a
|
|
71
|
+
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After you upload a model image and a product image, the service generates a natural and realistic try-on effect to intuitively display how the clothing looks on the model.
|
|
72
72
|
* - **Virtual try-on for shoes and hats:**
|
|
73
|
-
* Supports virtual try-on for
|
|
73
|
+
* Supports virtual try-on for products such as shoes and hats. The service intelligently matches the position and proportion of the product based on the model\\"s pose and body parts to present a coordinated and realistic wearing effect.
|
|
74
74
|
* - **E-commerce product display and marketing:**
|
|
75
|
-
* Helps merchants quickly generate model try-on images for different products
|
|
75
|
+
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional photography, outfit changes, and post-production, and improving the production efficiency of product images.
|
|
76
76
|
* - **Online shopping experience optimization:**
|
|
77
|
-
* Allows consumers to preview the wearing effect of products through virtual try-on
|
|
77
|
+
* Allows consumers to preview the wearing effect of products through virtual try-on, providing a more intuitive understanding of the style, matching, and overall effect of the products, which assists in purchase decisions and enhances the shopping experience.
|
|
78
78
|
* ## Features
|
|
79
|
-
* - **
|
|
80
|
-
* - a. Model image: The image of the person who will
|
|
79
|
+
* - **First, you need to provide a model image and a product image. The system uses the model image as the try-on subject and applies the clothing from the product image to the model:**
|
|
80
|
+
* - a. Model image: The image of the person who will virtually try on the clothing.
|
|
81
81
|
* - b. Product image: The image of the clothing, shoes, or hat to be worn by the model.
|
|
82
|
-
* - **
|
|
83
|
-
* - a. Specify product type: You can directly specify the type of the current product, and the system will process it
|
|
82
|
+
* - **Second, you can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
83
|
+
* - a. Specify product type: You can directly specify the type of the current product, and the system will process it according to the specified type.
|
|
84
84
|
* - b. Automatic type recognition: If you do not specify the product type, the system automatically recognizes the product category in the product image and performs the virtual try-on based on the recognition result.
|
|
85
|
-
* - **
|
|
85
|
+
* - **Finally, the system generates a virtual try-on image by combining the model image, product image, and product type to display the wearing effect of the product on the model:**
|
|
86
86
|
* - 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.
|
|
87
87
|
* - 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.
|
|
88
88
|
* - c. Generate try-on effect: The product is naturally applied to the model, fitting the person\\"s pose and body structure to generate a coordinated and realistic virtual try-on image.
|
|
89
89
|
* ## Examples
|
|
90
|
-
* | **Type** | **Model image** | **
|
|
90
|
+
* | **Type** | **Model image** | **Clothing image** | **Try-on result image** |
|
|
91
91
|
* | --- | --- | --- | --- |
|
|
92
|
-
* | Tops |  |  |  |  |  |  |
|
|
93
|
+
* | Bottoms |  |  |  |
|
|
94
|
+
* | Shoes |  |  |  |
|
|
95
95
|
* | Jumpsuits |  |  |  |
|
|
96
96
|
* | Dresses |  |  |  |
|
|
97
|
-
* | Hats |  |  |  |  |
|
|
98
98
|
*
|
|
99
99
|
* @param request - AiTryOnRequest
|
|
100
100
|
* @returns AiTryOnResponse
|
|
101
101
|
*/
|
|
102
102
|
aiTryOn(request: $_model.AiTryOnRequest): Promise<$_model.AiTryOnResponse>;
|
|
103
103
|
/**
|
|
104
|
-
*
|
|
104
|
+
* Optimizes cross-platform product materials for cross-border e-commerce sellers with a one-click, cost-effective service. Takes a product link from a source platform and outputs a full set of materials, including titles, attributes, main images, SKU images, detail images, and copy, tailored to the target platform requirements. Uses an official pre-built, lowest-cost workflow that focuses on filtering and lightweight processing without invoking high-cost image translation capabilities, maximizing cost control while ensuring listing compliance. (Asynchronous)
|
|
105
105
|
*
|
|
106
106
|
* @remarks
|
|
107
|
-
* ## Product
|
|
108
|
-
*
|
|
107
|
+
* ## Product introduction
|
|
108
|
+
* Optimizes cross-platform product materials for cross-border e-commerce sellers with a one-click, cost-effective service. Takes a product link from a source platform and outputs a full set of materials, including titles, attributes, main images, SKU images, detail images, and copy, tailored to the target platform requirements. Uses an official pre-built, lowest-cost workflow that focuses on filtering and lightweight processing without invoking high-cost image translation capabilities, maximizing cost control while ensuring listing compliance. (Asynchronous)
|
|
109
109
|
* ## Scenarios
|
|
110
|
-
*
|
|
111
|
-
*
|
|
110
|
+
* Applies to cost-sensitive, cross-platform listing scenarios that prioritize speed, volume, and low cost. Examples include broad listing from 1688 to TEMU, bulk listing of high-SKU inventory, entry-level AI processing capabilities provided by top sellers and ERP or SaaS platforms, and merchants with high daily processing volumes but low requirements for marketing performance.
|
|
111
|
+
* Reduces AI generation steps by filtering images with watermarks or non-compliant elements and prioritizing clean original images. This helps merchants complete cross-platform listing at an extremely low call cost.
|
|
112
112
|
* ## Features
|
|
113
|
-
* This service uses
|
|
114
|
-
* 1. Automatically parses 1688 product links and extracts multiple
|
|
115
|
-
* 2.
|
|
116
|
-
* 3. Intelligently identifies watermarks, logos, and Chinese
|
|
117
|
-
* 4. Completes category matching, attribute filling, and localized rewriting based on target platform
|
|
113
|
+
* This service uses the official pre-built lowest-cost product optimization workflow, covering the entire process from material acquisition, compliance filtering, and text optimization to image processing:
|
|
114
|
+
* 1. Automatically parses 1688 product links and extracts multiple types of materials, including titles, SKUs, main images, detail images, and attributes.
|
|
115
|
+
* 2. Completes text filtering and SEO optimization based on the TEMU platform blacklist and compliance rules.
|
|
116
|
+
* 3. Intelligently identifies watermarks, logos, and Chinese copy in images, and prioritizes filtering and selecting clean original images. SKU images and a small number of main images are processed by using image translation capabilities to meet platform specifications. High-conversion images with marketing copy may be filtered out.
|
|
117
|
+
* 4. Completes category matching, attribute filling, and localized rewriting based on the requirements of the target platform.
|
|
118
118
|
*
|
|
119
119
|
* @param request - AssetOptimizeLiteRequest
|
|
120
120
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -122,40 +122,40 @@ export default class Client extends OpenApi {
|
|
|
122
122
|
*/
|
|
123
123
|
assetOptimizeLiteWithOptions(request: $_model.AssetOptimizeLiteRequest, runtime: $dara.RuntimeOptions): Promise<$_model.AssetOptimizeLiteResponse>;
|
|
124
124
|
/**
|
|
125
|
-
*
|
|
125
|
+
* Optimizes cross-platform product materials for cross-border e-commerce sellers with a one-click, cost-effective service. Takes a product link from a source platform and outputs a full set of materials, including titles, attributes, main images, SKU images, detail images, and copy, tailored to the target platform requirements. Uses an official pre-built, lowest-cost workflow that focuses on filtering and lightweight processing without invoking high-cost image translation capabilities, maximizing cost control while ensuring listing compliance. (Asynchronous)
|
|
126
126
|
*
|
|
127
127
|
* @remarks
|
|
128
|
-
* ## Product
|
|
129
|
-
*
|
|
128
|
+
* ## Product introduction
|
|
129
|
+
* Optimizes cross-platform product materials for cross-border e-commerce sellers with a one-click, cost-effective service. Takes a product link from a source platform and outputs a full set of materials, including titles, attributes, main images, SKU images, detail images, and copy, tailored to the target platform requirements. Uses an official pre-built, lowest-cost workflow that focuses on filtering and lightweight processing without invoking high-cost image translation capabilities, maximizing cost control while ensuring listing compliance. (Asynchronous)
|
|
130
130
|
* ## Scenarios
|
|
131
|
-
*
|
|
132
|
-
*
|
|
131
|
+
* Applies to cost-sensitive, cross-platform listing scenarios that prioritize speed, volume, and low cost. Examples include broad listing from 1688 to TEMU, bulk listing of high-SKU inventory, entry-level AI processing capabilities provided by top sellers and ERP or SaaS platforms, and merchants with high daily processing volumes but low requirements for marketing performance.
|
|
132
|
+
* Reduces AI generation steps by filtering images with watermarks or non-compliant elements and prioritizing clean original images. This helps merchants complete cross-platform listing at an extremely low call cost.
|
|
133
133
|
* ## Features
|
|
134
|
-
* This service uses
|
|
135
|
-
* 1. Automatically parses 1688 product links and extracts multiple
|
|
136
|
-
* 2.
|
|
137
|
-
* 3. Intelligently identifies watermarks, logos, and Chinese
|
|
138
|
-
* 4. Completes category matching, attribute filling, and localized rewriting based on target platform
|
|
134
|
+
* This service uses the official pre-built lowest-cost product optimization workflow, covering the entire process from material acquisition, compliance filtering, and text optimization to image processing:
|
|
135
|
+
* 1. Automatically parses 1688 product links and extracts multiple types of materials, including titles, SKUs, main images, detail images, and attributes.
|
|
136
|
+
* 2. Completes text filtering and SEO optimization based on the TEMU platform blacklist and compliance rules.
|
|
137
|
+
* 3. Intelligently identifies watermarks, logos, and Chinese copy in images, and prioritizes filtering and selecting clean original images. SKU images and a small number of main images are processed by using image translation capabilities to meet platform specifications. High-conversion images with marketing copy may be filtered out.
|
|
138
|
+
* 4. Completes category matching, attribute filling, and localized rewriting based on the requirements of the target platform.
|
|
139
139
|
*
|
|
140
140
|
* @param request - AssetOptimizeLiteRequest
|
|
141
141
|
* @returns AssetOptimizeLiteResponse
|
|
142
142
|
*/
|
|
143
143
|
assetOptimizeLite(request: $_model.AssetOptimizeLiteRequest): Promise<$_model.AssetOptimizeLiteResponse>;
|
|
144
144
|
/**
|
|
145
|
-
* Provides a one-click cross-platform product
|
|
145
|
+
* Provides a one-click cross-platform product material optimization service for cross-border e-commerce sellers (optimal performance edition). This asynchronous operation takes 1688 product links as input and generates a full set of materials tailored to TEMU platform requirements, including titles, attributes, main images, SKU images, detail images, and copy. It uses officially pre-configured optimal workflows to maximize AI capabilities, retains and localizes brand marketing materials, and generates personalized materials such as size charts for categories like apparel.
|
|
146
146
|
*
|
|
147
147
|
* @remarks
|
|
148
|
-
* ## Product
|
|
149
|
-
* A one-click cross-platform product
|
|
150
|
-
* ##
|
|
151
|
-
*
|
|
152
|
-
* ##
|
|
153
|
-
* This service uses
|
|
154
|
-
* 1. Automatically parses 1688 product links to extract
|
|
155
|
-
* 2. Uses
|
|
156
|
-
* 3. Invokes multiple
|
|
157
|
-
* 4.
|
|
158
|
-
* 5.
|
|
148
|
+
* ## Product introduction
|
|
149
|
+
* A one-click cross-platform product material optimization service for cross-border e-commerce sellers (best effect edition). Input a 1688 product link to generate a complete set of materials, including titles, attributes, main images, SKU images, detail images, and copy, tailored to TEMU platform requirements.
|
|
150
|
+
* ## Scenarios
|
|
151
|
+
* Applicable to scenarios with high requirements for the quality and conversion performance of cross-platform product materials. Examples include categories highly dependent on marketing materials such as apparel, accessories, cosmetics, and home goods; brand merchants and high-ticket items that need to retain the tone of marketing images with copy; top sellers and ERP/SaaS platforms conducting localized operations across multiple languages and markets; and scenarios requiring category-specific materials, such as size charts and weight and dimension charts, to improve listing quality and conversion rates.
|
|
152
|
+
* ## Features
|
|
153
|
+
* This service uses the official pre-built best-effect product optimization workflow, covering the entire pipeline from material acquisition, diagnosis, filtering, and optimization to output:
|
|
154
|
+
* 1. Automatically parses 1688 product links to extract a full set of materials, including titles, SKUs, main images, detail images, and attributes, and intelligently diagnoses missing materials and optimization opportunities.
|
|
155
|
+
* 2. Uses LLMs for text compliance filtering, SEO keyword optimization, five-point description generation, and multilingual localization rewriting.
|
|
156
|
+
* 3. Invokes multiple capabilities for images, including intelligent recognition, intelligent background removal, intelligent object removal, Image Translation Pro, image outpainting, intelligent cropping, and high-definition upscaling.
|
|
157
|
+
* 4. Generates category-specific materials, such as size charts and weight and dimension charts for apparel.
|
|
158
|
+
* 5. Outputs a standardized product material package ready for direct listing.
|
|
159
159
|
*
|
|
160
160
|
* @param tmpReq - AssetOptimizeProRequest
|
|
161
161
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -163,64 +163,65 @@ export default class Client extends OpenApi {
|
|
|
163
163
|
*/
|
|
164
164
|
assetOptimizeProWithOptions(tmpReq: $_model.AssetOptimizeProRequest, runtime: $dara.RuntimeOptions): Promise<$_model.AssetOptimizeProResponse>;
|
|
165
165
|
/**
|
|
166
|
-
* Provides a one-click cross-platform product
|
|
166
|
+
* Provides a one-click cross-platform product material optimization service for cross-border e-commerce sellers (optimal performance edition). This asynchronous operation takes 1688 product links as input and generates a full set of materials tailored to TEMU platform requirements, including titles, attributes, main images, SKU images, detail images, and copy. It uses officially pre-configured optimal workflows to maximize AI capabilities, retains and localizes brand marketing materials, and generates personalized materials such as size charts for categories like apparel.
|
|
167
167
|
*
|
|
168
168
|
* @remarks
|
|
169
|
-
* ## Product
|
|
170
|
-
* A one-click cross-platform product
|
|
171
|
-
* ##
|
|
172
|
-
*
|
|
173
|
-
* ##
|
|
174
|
-
* This service uses
|
|
175
|
-
* 1. Automatically parses 1688 product links to extract
|
|
176
|
-
* 2. Uses
|
|
177
|
-
* 3. Invokes multiple
|
|
178
|
-
* 4.
|
|
179
|
-
* 5.
|
|
169
|
+
* ## Product introduction
|
|
170
|
+
* A one-click cross-platform product material optimization service for cross-border e-commerce sellers (best effect edition). Input a 1688 product link to generate a complete set of materials, including titles, attributes, main images, SKU images, detail images, and copy, tailored to TEMU platform requirements.
|
|
171
|
+
* ## Scenarios
|
|
172
|
+
* Applicable to scenarios with high requirements for the quality and conversion performance of cross-platform product materials. Examples include categories highly dependent on marketing materials such as apparel, accessories, cosmetics, and home goods; brand merchants and high-ticket items that need to retain the tone of marketing images with copy; top sellers and ERP/SaaS platforms conducting localized operations across multiple languages and markets; and scenarios requiring category-specific materials, such as size charts and weight and dimension charts, to improve listing quality and conversion rates.
|
|
173
|
+
* ## Features
|
|
174
|
+
* This service uses the official pre-built best-effect product optimization workflow, covering the entire pipeline from material acquisition, diagnosis, filtering, and optimization to output:
|
|
175
|
+
* 1. Automatically parses 1688 product links to extract a full set of materials, including titles, SKUs, main images, detail images, and attributes, and intelligently diagnoses missing materials and optimization opportunities.
|
|
176
|
+
* 2. Uses LLMs for text compliance filtering, SEO keyword optimization, five-point description generation, and multilingual localization rewriting.
|
|
177
|
+
* 3. Invokes multiple capabilities for images, including intelligent recognition, intelligent background removal, intelligent object removal, Image Translation Pro, image outpainting, intelligent cropping, and high-definition upscaling.
|
|
178
|
+
* 4. Generates category-specific materials, such as size charts and weight and dimension charts for apparel.
|
|
179
|
+
* 5. Outputs a standardized product material package ready for direct listing.
|
|
180
180
|
*
|
|
181
181
|
* @param request - AssetOptimizeProRequest
|
|
182
182
|
* @returns AssetOptimizeProResponse
|
|
183
183
|
*/
|
|
184
184
|
assetOptimizePro(request: $_model.AssetOptimizeProRequest): Promise<$_model.AssetOptimizeProResponse>;
|
|
185
185
|
/**
|
|
186
|
-
* Provides
|
|
186
|
+
* Provides an intelligent cross-platform product category attribute filling service based on multimodal large models. Accepts product information from a source platform, automatically matches the category on a target platform, and intelligently fills all required attribute fields under the category to provide a one-stop solution for category selection and attribute filling during product listing. (Synchronous)
|
|
187
187
|
*
|
|
188
188
|
* @remarks
|
|
189
|
-
* #
|
|
190
|
-
* Cross-platform product listing attribute filling: When merchants list products across platforms, the
|
|
191
|
-
* #
|
|
192
|
-
* Users input the product title, source category, product details, SKU, product attributes, and product images (up to 10). The system uses multimodal AI to understand the
|
|
189
|
+
* # Scenarios
|
|
190
|
+
* Cross-platform product listing attribute filling: When merchants list products across platforms, the source platform and the TEMU platform have different attribute fields required for different categories, and there are complex hierarchical associated options (such as material -> wood type -> density). Manual filling is time-consuming and error-prone. This service automatically understands product information and intelligently fills in various attributes. It is suitable for scenarios such as automated batch product listing for top sellers, ERP/SaaS platform integration, and quick product listing for SMB merchants.
|
|
191
|
+
* # Features
|
|
192
|
+
* Users input the product title, source category, product details, SKU, product attributes, and product images (up to 10). The system uses multimodal AI to understand the semantic and visual features of the product and completes two core tasks: 1. Matches the precise category path of the product on the TEMU platform. 2. Automatically fills in the required attributes under the category (such as material, battery properties, size, and connectivity) and returns the confidence level and filling reason for each attribute. The API operates in synchronous mode and returns results immediately after the call.
|
|
193
193
|
* # Comparison
|
|
194
|
-
*
|
|
195
|
-
* | **1688
|
|
194
|
+
* Take the attributes of a USB fan as an example:
|
|
195
|
+
* | **1688 attribute** | **1688 attribute value** | **TEMU attribute** | **TEMU attribute value** | **Is it an existing**
|
|
196
|
+
* **1688 attribute?** |
|
|
196
197
|
* | --- | --- | --- | --- | --- |
|
|
197
|
-
* | Brand | Other | Power
|
|
198
|
-
* | Battery
|
|
199
|
-
* | Additional
|
|
200
|
-
* | Built-in
|
|
201
|
-
* | Item
|
|
202
|
-
* | Main
|
|
203
|
-
* | Has
|
|
204
|
-
* | Dimensions | 65\\*60\\*171 | Fan
|
|
205
|
-
* |
|
|
206
|
-
* | Shell
|
|
207
|
-
* | Package
|
|
208
|
-
* |
|
|
209
|
-
* | Wind
|
|
210
|
-
* | Operation
|
|
211
|
-
* |
|
|
212
|
-
* | Power
|
|
213
|
-
* | Built-in
|
|
214
|
-
* | Patented
|
|
215
|
-
* | Color | X699
|
|
216
|
-
* | Main
|
|
217
|
-
* |
|
|
198
|
+
* | Brand | Other | Power supply method | USB charging (built-in battery) | No |
|
|
199
|
+
* | Battery life | 3-6h (inclusive) | Rechargeable battery | Lithium battery | No |
|
|
200
|
+
* | Additional features | Digital display | Battery capacity (mAh) | 4000 | Yes |
|
|
201
|
+
* | Built-in battery capacity | 2000mAh-4000mAh (inclusive) | Fan features | High-speed features | No |
|
|
202
|
+
* | Item number | X699 | Control method | Button | Yes |
|
|
203
|
+
* | Main downstream platforms | eBay, Amazon, Wish, AliExpress, Independent site, LAZADA, Other | Finish type | Painted | Yes |
|
|
204
|
+
* | Has licensable own brand | No | Recommended use | Cooling | No |
|
|
205
|
+
* | Dimensions | 65\\*60\\*171 | Fan design | Wearable fan | No |
|
|
206
|
+
* | Suitable gift-giving occasions | Personal gifts | Included components | None | No |
|
|
207
|
+
* | Shell craftsmanship | Spraying (UV paint, rubber paint, metallic paint, piano baking paint, pearlescent powder) | Material | Plastic | No |
|
|
208
|
+
* | Package volume | 65\\*60\\*171 | Special features | Portable | No |
|
|
209
|
+
* | Exterior dimensions | 51\\*36\\*34 | Indoor/outdoor use | Both indoor and outdoor | No |
|
|
210
|
+
* | Wind speed gears | 3 gears | Brand name | None | No |
|
|
211
|
+
* | Operation method | Standard button | | | |
|
|
212
|
+
* | Fan blade material | ABS | | | |
|
|
213
|
+
* | Power supply method | USB | | | |
|
|
214
|
+
* | Built-in battery | Built-in battery | | | |
|
|
215
|
+
* | Patented source | No | | | |
|
|
216
|
+
* | Color | X699 fan-yellow, X699 fan-light purple, X699 fan-sky blue, X699 fan-orange, X699 fan-light green, Standard small fan | | | |
|
|
217
|
+
* | Main sales regions | Japan and South Korea, Africa, South Korea, Japan, Europe, South America, Southeast Asia, North America, Northeast Asia, Middle East, Latin America, Europe and America, Other | | | |
|
|
218
|
+
* | Exclusive source for cross-border export | Yes | | | |
|
|
218
219
|
* | Style | Fresh | | | |
|
|
219
|
-
* | Motor
|
|
220
|
+
* | Motor type | Brushless motor | | | |
|
|
220
221
|
* | Noise | 36dB(A)-45dB(A) (inclusive) | | | |
|
|
221
|
-
* | Net
|
|
222
|
-
* | Number of
|
|
223
|
-
* | Fan
|
|
222
|
+
* | Net weight | 125g | | | |
|
|
223
|
+
* | Number of fan blades | 6 or more | | | |
|
|
224
|
+
* | Fan category | Handheld fan | | | |
|
|
224
225
|
*
|
|
225
226
|
* @param tmpReq - CategoryAttributeMatchRequest
|
|
226
227
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -228,65 +229,66 @@ export default class Client extends OpenApi {
|
|
|
228
229
|
*/
|
|
229
230
|
categoryAttributeMatchWithOptions(tmpReq: $_model.CategoryAttributeMatchRequest, runtime: $dara.RuntimeOptions): Promise<$_model.CategoryAttributeMatchResponse>;
|
|
230
231
|
/**
|
|
231
|
-
* Provides
|
|
232
|
+
* Provides an intelligent cross-platform product category attribute filling service based on multimodal large models. Accepts product information from a source platform, automatically matches the category on a target platform, and intelligently fills all required attribute fields under the category to provide a one-stop solution for category selection and attribute filling during product listing. (Synchronous)
|
|
232
233
|
*
|
|
233
234
|
* @remarks
|
|
234
|
-
* #
|
|
235
|
-
* Cross-platform product listing attribute filling: When merchants list products across platforms, the
|
|
236
|
-
* #
|
|
237
|
-
* Users input the product title, source category, product details, SKU, product attributes, and product images (up to 10). The system uses multimodal AI to understand the
|
|
235
|
+
* # Scenarios
|
|
236
|
+
* Cross-platform product listing attribute filling: When merchants list products across platforms, the source platform and the TEMU platform have different attribute fields required for different categories, and there are complex hierarchical associated options (such as material -> wood type -> density). Manual filling is time-consuming and error-prone. This service automatically understands product information and intelligently fills in various attributes. It is suitable for scenarios such as automated batch product listing for top sellers, ERP/SaaS platform integration, and quick product listing for SMB merchants.
|
|
237
|
+
* # Features
|
|
238
|
+
* Users input the product title, source category, product details, SKU, product attributes, and product images (up to 10). The system uses multimodal AI to understand the semantic and visual features of the product and completes two core tasks: 1. Matches the precise category path of the product on the TEMU platform. 2. Automatically fills in the required attributes under the category (such as material, battery properties, size, and connectivity) and returns the confidence level and filling reason for each attribute. The API operates in synchronous mode and returns results immediately after the call.
|
|
238
239
|
* # Comparison
|
|
239
|
-
*
|
|
240
|
-
* | **1688
|
|
240
|
+
* Take the attributes of a USB fan as an example:
|
|
241
|
+
* | **1688 attribute** | **1688 attribute value** | **TEMU attribute** | **TEMU attribute value** | **Is it an existing**
|
|
242
|
+
* **1688 attribute?** |
|
|
241
243
|
* | --- | --- | --- | --- | --- |
|
|
242
|
-
* | Brand | Other | Power
|
|
243
|
-
* | Battery
|
|
244
|
-
* | Additional
|
|
245
|
-
* | Built-in
|
|
246
|
-
* | Item
|
|
247
|
-
* | Main
|
|
248
|
-
* | Has
|
|
249
|
-
* | Dimensions | 65\\*60\\*171 | Fan
|
|
250
|
-
* |
|
|
251
|
-
* | Shell
|
|
252
|
-
* | Package
|
|
253
|
-
* |
|
|
254
|
-
* | Wind
|
|
255
|
-
* | Operation
|
|
256
|
-
* |
|
|
257
|
-
* | Power
|
|
258
|
-
* | Built-in
|
|
259
|
-
* | Patented
|
|
260
|
-
* | Color | X699
|
|
261
|
-
* | Main
|
|
262
|
-
* |
|
|
244
|
+
* | Brand | Other | Power supply method | USB charging (built-in battery) | No |
|
|
245
|
+
* | Battery life | 3-6h (inclusive) | Rechargeable battery | Lithium battery | No |
|
|
246
|
+
* | Additional features | Digital display | Battery capacity (mAh) | 4000 | Yes |
|
|
247
|
+
* | Built-in battery capacity | 2000mAh-4000mAh (inclusive) | Fan features | High-speed features | No |
|
|
248
|
+
* | Item number | X699 | Control method | Button | Yes |
|
|
249
|
+
* | Main downstream platforms | eBay, Amazon, Wish, AliExpress, Independent site, LAZADA, Other | Finish type | Painted | Yes |
|
|
250
|
+
* | Has licensable own brand | No | Recommended use | Cooling | No |
|
|
251
|
+
* | Dimensions | 65\\*60\\*171 | Fan design | Wearable fan | No |
|
|
252
|
+
* | Suitable gift-giving occasions | Personal gifts | Included components | None | No |
|
|
253
|
+
* | Shell craftsmanship | Spraying (UV paint, rubber paint, metallic paint, piano baking paint, pearlescent powder) | Material | Plastic | No |
|
|
254
|
+
* | Package volume | 65\\*60\\*171 | Special features | Portable | No |
|
|
255
|
+
* | Exterior dimensions | 51\\*36\\*34 | Indoor/outdoor use | Both indoor and outdoor | No |
|
|
256
|
+
* | Wind speed gears | 3 gears | Brand name | None | No |
|
|
257
|
+
* | Operation method | Standard button | | | |
|
|
258
|
+
* | Fan blade material | ABS | | | |
|
|
259
|
+
* | Power supply method | USB | | | |
|
|
260
|
+
* | Built-in battery | Built-in battery | | | |
|
|
261
|
+
* | Patented source | No | | | |
|
|
262
|
+
* | Color | X699 fan-yellow, X699 fan-light purple, X699 fan-sky blue, X699 fan-orange, X699 fan-light green, Standard small fan | | | |
|
|
263
|
+
* | Main sales regions | Japan and South Korea, Africa, South Korea, Japan, Europe, South America, Southeast Asia, North America, Northeast Asia, Middle East, Latin America, Europe and America, Other | | | |
|
|
264
|
+
* | Exclusive source for cross-border export | Yes | | | |
|
|
263
265
|
* | Style | Fresh | | | |
|
|
264
|
-
* | Motor
|
|
266
|
+
* | Motor type | Brushless motor | | | |
|
|
265
267
|
* | Noise | 36dB(A)-45dB(A) (inclusive) | | | |
|
|
266
|
-
* | Net
|
|
267
|
-
* | Number of
|
|
268
|
-
* | Fan
|
|
268
|
+
* | Net weight | 125g | | | |
|
|
269
|
+
* | Number of fan blades | 6 or more | | | |
|
|
270
|
+
* | Fan category | Handheld fan | | | |
|
|
269
271
|
*
|
|
270
272
|
* @param request - CategoryAttributeMatchRequest
|
|
271
273
|
* @returns CategoryAttributeMatchResponse
|
|
272
274
|
*/
|
|
273
275
|
categoryAttributeMatch(request: $_model.CategoryAttributeMatchRequest): Promise<$_model.CategoryAttributeMatchResponse>;
|
|
274
276
|
/**
|
|
275
|
-
* Provides an intelligent cross-platform product category matching service based on
|
|
277
|
+
* Provides an intelligent cross-platform product category matching service based on large language models. Accepts product information from a source platform, automatically matches the optimal category on the target platform, and returns a confidence score and matching rationale to help merchants quickly select categories for cross-platform product listing. (Synchronous)
|
|
276
278
|
*
|
|
277
279
|
* @remarks
|
|
278
280
|
* ## Product Introduction
|
|
279
|
-
*
|
|
280
|
-
* ##
|
|
281
|
-
* Cross-platform product listing: After sourcing products,
|
|
282
|
-
* This service
|
|
283
|
-
* The current version supports
|
|
281
|
+
* Provides an intelligent cross-platform product category matching service based on large language models. Accepts product information from a source platform, automatically matches the optimal category on the target platform, and returns a confidence score and matching rationale to help merchants quickly select categories for cross-platform product listing. (Synchronous)
|
|
282
|
+
* ## Scenarios
|
|
283
|
+
* Cross-platform product listing: After sourcing products, merchants list them on a target platform and need to map the products to the correct categories in the target platform\\"s category tree. Manual category selection requires familiarity with the target platform\\"s complete category system, which is time-consuming, labor-intensive, and error-prone. Incorrect category matching can lead to product delisting and other issues.
|
|
284
|
+
* This service automatically completes category mapping and is suitable for scenarios such as batch calls from self-built systems of top sellers, integration of automated product listing workflows into ERP/SaaS platforms, and quick listing of single products by SMB merchants.
|
|
285
|
+
* The current version only supports TEMU as the target platform. It does not currently support directly retrieving product information from the source platform, requiring users to manually input parameters. Future updates will add this capability and expand support for more source and target platforms.
|
|
284
286
|
* ## Features
|
|
285
|
-
* Users
|
|
286
|
-
* ##
|
|
287
|
+
* Users input fields such as the product title, source category, product details, SKU information, and product attributes. The system uses an AI model to understand the product semantics and matches the most appropriate category path from the full category tree of the TEMU platform. The returned results include the complete category path (CategoryPath), category name (CategoryName), confidence score (0-100), and matching rationale. The API operates in synchronous mode and returns results immediately after the call, making it suitable for embedding in real-time business workflows.
|
|
288
|
+
* ## Examples
|
|
287
289
|
* | **Source platform** | **Image** | **Source platform category** | **Target platform** | **Target platform category** |
|
|
288
290
|
* | --- | --- | --- | --- | --- |
|
|
289
|
-
* | 1688 |  | USB
|
|
291
|
+
* | 1688 |  | USB fans, mini fans | TEMU | Home Appliances
|
|
290
292
|
* \\>Heating, Cooling & Air Quality Appliances
|
|
291
293
|
* \\>Electric Fans
|
|
292
294
|
* \\>USB Fans |
|
|
@@ -304,21 +306,21 @@ export default class Client extends OpenApi {
|
|
|
304
306
|
*/
|
|
305
307
|
categoryMatchWithOptions(request: $_model.CategoryMatchRequest, runtime: $dara.RuntimeOptions): Promise<$_model.CategoryMatchResponse>;
|
|
306
308
|
/**
|
|
307
|
-
* Provides an intelligent cross-platform product category matching service based on
|
|
309
|
+
* Provides an intelligent cross-platform product category matching service based on large language models. Accepts product information from a source platform, automatically matches the optimal category on the target platform, and returns a confidence score and matching rationale to help merchants quickly select categories for cross-platform product listing. (Synchronous)
|
|
308
310
|
*
|
|
309
311
|
* @remarks
|
|
310
312
|
* ## Product Introduction
|
|
311
|
-
*
|
|
312
|
-
* ##
|
|
313
|
-
* Cross-platform product listing: After sourcing products,
|
|
314
|
-
* This service
|
|
315
|
-
* The current version supports
|
|
313
|
+
* Provides an intelligent cross-platform product category matching service based on large language models. Accepts product information from a source platform, automatically matches the optimal category on the target platform, and returns a confidence score and matching rationale to help merchants quickly select categories for cross-platform product listing. (Synchronous)
|
|
314
|
+
* ## Scenarios
|
|
315
|
+
* Cross-platform product listing: After sourcing products, merchants list them on a target platform and need to map the products to the correct categories in the target platform\\"s category tree. Manual category selection requires familiarity with the target platform\\"s complete category system, which is time-consuming, labor-intensive, and error-prone. Incorrect category matching can lead to product delisting and other issues.
|
|
316
|
+
* This service automatically completes category mapping and is suitable for scenarios such as batch calls from self-built systems of top sellers, integration of automated product listing workflows into ERP/SaaS platforms, and quick listing of single products by SMB merchants.
|
|
317
|
+
* The current version only supports TEMU as the target platform. It does not currently support directly retrieving product information from the source platform, requiring users to manually input parameters. Future updates will add this capability and expand support for more source and target platforms.
|
|
316
318
|
* ## Features
|
|
317
|
-
* Users
|
|
318
|
-
* ##
|
|
319
|
+
* Users input fields such as the product title, source category, product details, SKU information, and product attributes. The system uses an AI model to understand the product semantics and matches the most appropriate category path from the full category tree of the TEMU platform. The returned results include the complete category path (CategoryPath), category name (CategoryName), confidence score (0-100), and matching rationale. The API operates in synchronous mode and returns results immediately after the call, making it suitable for embedding in real-time business workflows.
|
|
320
|
+
* ## Examples
|
|
319
321
|
* | **Source platform** | **Image** | **Source platform category** | **Target platform** | **Target platform category** |
|
|
320
322
|
* | --- | --- | --- | --- | --- |
|
|
321
|
-
* | 1688 |  | USB
|
|
323
|
+
* | 1688 |  | USB fans, mini fans | TEMU | Home Appliances
|
|
322
324
|
* \\>Heating, Cooling & Air Quality Appliances
|
|
323
325
|
* \\>Electric Fans
|
|
324
326
|
* \\>USB Fans |
|
|
@@ -335,7 +337,7 @@ export default class Client extends OpenApi {
|
|
|
335
337
|
*/
|
|
336
338
|
categoryMatch(request: $_model.CategoryMatchRequest): Promise<$_model.CategoryMatchResponse>;
|
|
337
339
|
/**
|
|
338
|
-
*
|
|
340
|
+
* Synchronously deletes content from a display knowledge base in batches.
|
|
339
341
|
*
|
|
340
342
|
* @param tmpReq - DeleteDisplayKnowledgeRequest
|
|
341
343
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -343,24 +345,24 @@ export default class Client extends OpenApi {
|
|
|
343
345
|
*/
|
|
344
346
|
deleteDisplayKnowledgeWithOptions(tmpReq: $_model.DeleteDisplayKnowledgeRequest, runtime: $dara.RuntimeOptions): Promise<$_model.DeleteDisplayKnowledgeResponse>;
|
|
345
347
|
/**
|
|
346
|
-
*
|
|
348
|
+
* Synchronously deletes content from a display knowledge base in batches.
|
|
347
349
|
*
|
|
348
350
|
* @param request - DeleteDisplayKnowledgeRequest
|
|
349
351
|
* @returns DeleteDisplayKnowledgeResponse
|
|
350
352
|
*/
|
|
351
353
|
deleteDisplayKnowledge(request: $_model.DeleteDisplayKnowledgeRequest): Promise<$_model.DeleteDisplayKnowledgeResponse>;
|
|
352
354
|
/**
|
|
353
|
-
* Calculates the
|
|
355
|
+
* Calculates the side lengths and floor area of a floor display based on the floor display image and product bounding boxes.
|
|
354
356
|
*
|
|
355
357
|
* @remarks
|
|
356
|
-
* ##
|
|
357
|
-
* **Before
|
|
358
|
-
* - This operation infers the actual dimensions (lengths of two
|
|
359
|
-
* - Make sure that the knowledge base corresponding to the
|
|
360
|
-
* - The `Products` array must contain at least one product item, and each product item must
|
|
361
|
-
* - All coordinate values are represented in a normalized coordinate system ranging from 0 to 1000. Make sure that the input satisfies the
|
|
362
|
-
* - Set a reasonable timeout period
|
|
363
|
-
* - For calls in
|
|
358
|
+
* ## Request description
|
|
359
|
+
* **Before calling this operation, make sure that you fully understand the billing methods and [pricing](https://www.aliyun.com/price/product#/ecs/detail) of the floor display area inference product.**
|
|
360
|
+
* - This operation infers the actual dimensions (the lengths of the two sides) and floor area of a floor display based on the provided overall image of the floor display, the SKU knowledge base, and the position information of products in the image.
|
|
361
|
+
* - Make sure that the knowledge base corresponding to the provided `RagId` belongs to the caller and is in the `AVAILABLE` state.
|
|
362
|
+
* - The `Products` array must contain at least one product item, and the `Boxes` array under each product item must contain at least one bounding box.
|
|
363
|
+
* - All coordinate values are represented in a normalized coordinate system ranging from 0 to 1000. Make sure that the input satisfies the `Left < Right` and `Top < Bottom` conditions.
|
|
364
|
+
* - Set a reasonable timeout period (recommended maximum of 300 seconds) when calling this API to prevent failures caused by network latency or high processing complexity.
|
|
365
|
+
* - For calls in the production environment, use the POP Action method for access. Internal REST addresses are mainly used for joint debugging during the development and testing phases.
|
|
364
366
|
*
|
|
365
367
|
* @param tmpReq - DiduiAreaDeductionRequest
|
|
366
368
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -368,35 +370,35 @@ export default class Client extends OpenApi {
|
|
|
368
370
|
*/
|
|
369
371
|
diduiAreaDeductionWithOptions(tmpReq: $_model.DiduiAreaDeductionRequest, runtime: $dara.RuntimeOptions): Promise<$_model.DiduiAreaDeductionResponse>;
|
|
370
372
|
/**
|
|
371
|
-
* Calculates the
|
|
373
|
+
* Calculates the side lengths and floor area of a floor display based on the floor display image and product bounding boxes.
|
|
372
374
|
*
|
|
373
375
|
* @remarks
|
|
374
|
-
* ##
|
|
375
|
-
* **Before
|
|
376
|
-
* - This operation infers the actual dimensions (lengths of two
|
|
377
|
-
* - Make sure that the knowledge base corresponding to the
|
|
378
|
-
* - The `Products` array must contain at least one product item, and each product item must
|
|
379
|
-
* - All coordinate values are represented in a normalized coordinate system ranging from 0 to 1000. Make sure that the input satisfies the
|
|
380
|
-
* - Set a reasonable timeout period
|
|
381
|
-
* - For calls in
|
|
376
|
+
* ## Request description
|
|
377
|
+
* **Before calling this operation, make sure that you fully understand the billing methods and [pricing](https://www.aliyun.com/price/product#/ecs/detail) of the floor display area inference product.**
|
|
378
|
+
* - This operation infers the actual dimensions (the lengths of the two sides) and floor area of a floor display based on the provided overall image of the floor display, the SKU knowledge base, and the position information of products in the image.
|
|
379
|
+
* - Make sure that the knowledge base corresponding to the provided `RagId` belongs to the caller and is in the `AVAILABLE` state.
|
|
380
|
+
* - The `Products` array must contain at least one product item, and the `Boxes` array under each product item must contain at least one bounding box.
|
|
381
|
+
* - All coordinate values are represented in a normalized coordinate system ranging from 0 to 1000. Make sure that the input satisfies the `Left < Right` and `Top < Bottom` conditions.
|
|
382
|
+
* - Set a reasonable timeout period (recommended maximum of 300 seconds) when calling this API to prevent failures caused by network latency or high processing complexity.
|
|
383
|
+
* - For calls in the production environment, use the POP Action method for access. Internal REST addresses are mainly used for joint debugging during the development and testing phases.
|
|
382
384
|
*
|
|
383
385
|
* @param request - DiduiAreaDeductionRequest
|
|
384
386
|
* @returns DiduiAreaDeductionResponse
|
|
385
387
|
*/
|
|
386
388
|
diduiAreaDeduction(request: $_model.DiduiAreaDeductionRequest): Promise<$_model.DiduiAreaDeductionResponse>;
|
|
387
389
|
/**
|
|
388
|
-
* Analyzes the floor
|
|
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 the floor display, reads the actual dimensions and reference images of the corresponding SKUs, and infers the side lengths and area of the bounding rectangle of the floor display. This feature is suitable for evaluating the scale of floor displays in stores and for inspection and review.
|
|
389
391
|
*
|
|
390
392
|
* @remarks
|
|
391
393
|
* *Scenarios**
|
|
392
|
-
* - Floor display area
|
|
393
|
-
* - Multi-SKU mixed
|
|
394
|
-
* - Area result review: Verifies results by combining the original image, product assets, and the returned
|
|
394
|
+
* - 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 the side lengths.
|
|
396
|
+
* - Area result review: Verifies the results by combining the original image, product assets, and the returned side lengths and area.
|
|
395
397
|
* **Features**
|
|
396
|
-
* - SKU asset-driven: Specifies the asset knowledge base
|
|
397
|
-
* - Phased area inference: Sequentially forms decision edges, SKU projections, dimension accumulation, and final area.
|
|
398
|
-
* - Unified units: SKU asset dimensions are stored in centimeters.
|
|
399
|
-
* - Completeness and numerical validation: Returns failure
|
|
398
|
+
* - 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
|
+
* - 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 resulting side lengths are output in meters and the area in square meters.
|
|
401
|
+
* - Completeness and numerical validation: Returns a failure if assets are missing, no valid bounding boxes are found, or the area does not meet product consistency.
|
|
400
402
|
*
|
|
401
403
|
* @param request - DiduiAreaDeductionProRequest
|
|
402
404
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -404,42 +406,40 @@ export default class Client extends OpenApi {
|
|
|
404
406
|
*/
|
|
405
407
|
diduiAreaDeductionProWithOptions(request: $_model.DiduiAreaDeductionProRequest, runtime: $dara.RuntimeOptions): Promise<$_model.DiduiAreaDeductionProResponse>;
|
|
406
408
|
/**
|
|
407
|
-
* Analyzes the floor
|
|
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 the floor display, reads the actual dimensions and reference images of the corresponding SKUs, and infers the side lengths and area of the bounding rectangle of the floor display. This feature is suitable for evaluating the scale of floor displays in stores and for inspection and review.
|
|
408
410
|
*
|
|
409
411
|
* @remarks
|
|
410
412
|
* *Scenarios**
|
|
411
|
-
* - Floor display area
|
|
412
|
-
* - Multi-SKU mixed
|
|
413
|
-
* - Area result review: Verifies results by combining the original image, product assets, and the returned
|
|
413
|
+
* - 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 the side lengths.
|
|
415
|
+
* - Area result review: Verifies the results by combining the original image, product assets, and the returned side lengths and area.
|
|
414
416
|
* **Features**
|
|
415
|
-
* - SKU asset-driven: Specifies the asset knowledge base
|
|
416
|
-
* - Phased area inference: Sequentially forms decision edges, SKU projections, dimension accumulation, and final area.
|
|
417
|
-
* - Unified units: SKU asset dimensions are stored in centimeters.
|
|
418
|
-
* - Completeness and numerical validation: Returns failure
|
|
417
|
+
* - 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
|
+
* - 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 resulting side lengths are output in meters and the area in square meters.
|
|
420
|
+
* - Completeness and numerical validation: Returns a failure if assets are missing, no valid bounding boxes are found, or the area does not meet product consistency.
|
|
419
421
|
*
|
|
420
422
|
* @param request - DiduiAreaDeductionProRequest
|
|
421
423
|
* @returns DiduiAreaDeductionProResponse
|
|
422
424
|
*/
|
|
423
425
|
diduiAreaDeductionPro(request: $_model.DiduiAreaDeductionProRequest): Promise<$_model.DiduiAreaDeductionProResponse>;
|
|
424
426
|
/**
|
|
425
|
-
*
|
|
426
|
-
* - Content accuracy: translation accuracy, parameter and unit accuracy.
|
|
427
|
-
* - Structural integrity: overall layout continuity, page margin and layout restoration.
|
|
427
|
+
* Translates documents across more than 400 language pairs, including bridged pairs, to meet the needs of multi-scenario, multi-page, and high-complexity document translation. Scanned documents are not currently supported. This feature excels in the following aspects: - Content accuracy: Ensures translation accuracy and the accuracy of parameters and units. - Structural integrity: Maintains overall layout continuity and restores page margins and layouts.
|
|
428
428
|
*
|
|
429
429
|
* @remarks
|
|
430
|
-
* ## Product
|
|
431
|
-
* Designed specifically for document translation
|
|
432
|
-
*
|
|
433
|
-
* - Content accuracy: translation accuracy
|
|
434
|
-
* - Structural integrity: overall layout continuity
|
|
435
|
-
* ##
|
|
436
|
-
* Cross-border e-commerce product manuals, contracts, agreements, business proposals, qualification documents,
|
|
437
|
-
* ##
|
|
438
|
-
* - Supports PDF and Word formats
|
|
439
|
-
* - Supports translation of text
|
|
440
|
-
* - Supports
|
|
441
|
-
* -
|
|
442
|
-
* - Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and
|
|
430
|
+
* ## Product introduction
|
|
431
|
+
* Designed specifically for document translation, this feature supports translation across more than 400 language pairs (including bridged pairs) and meets the needs of multi-scenario, multi-page, and high-complexity document translation. Scanned documents are not currently supported.
|
|
432
|
+
* It excels in the following aspects:
|
|
433
|
+
* - Content accuracy: Ensures translation accuracy and the accuracy of parameters and units.
|
|
434
|
+
* - Structural integrity: Maintains overall layout continuity and restores page margins and layouts.
|
|
435
|
+
* ## Scenarios
|
|
436
|
+
* Cross-border e-commerce product manuals, contracts, agreements, business proposals, qualification documents, teaching materials, and courseware.
|
|
437
|
+
* ## Features
|
|
438
|
+
* - Supports PDF and Word formats, and supports source documents containing multiple languages. For the detailed language list, see [Language pair mapping table](https://www.alibabacloud.com/help/en/document_detail/3041883.html).
|
|
439
|
+
* - Supports the translation of text in images within documents, as well as complex translation scenarios such as other charts and special symbols.
|
|
440
|
+
* - Supports highly restored layout after translation.
|
|
441
|
+
* - Supports up to 100 pages for a single PDF file and up to 100 pages for a single Word file.
|
|
442
|
+
* - Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and no 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, which meets your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention words. If you have more requirements, contact the platform for processing.
|
|
443
443
|
*
|
|
444
444
|
* @param request - DocumentTranslateRequest
|
|
445
445
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -447,69 +447,67 @@ export default class Client extends OpenApi {
|
|
|
447
447
|
*/
|
|
448
448
|
documentTranslateWithOptions(request: $_model.DocumentTranslateRequest, runtime: $dara.RuntimeOptions): Promise<$_model.DocumentTranslateResponse>;
|
|
449
449
|
/**
|
|
450
|
-
*
|
|
451
|
-
* - Content accuracy: translation accuracy, parameter and unit accuracy.
|
|
452
|
-
* - Structural integrity: overall layout continuity, page margin and layout restoration.
|
|
450
|
+
* Translates documents across more than 400 language pairs, including bridged pairs, to meet the needs of multi-scenario, multi-page, and high-complexity document translation. Scanned documents are not currently supported. This feature excels in the following aspects: - Content accuracy: Ensures translation accuracy and the accuracy of parameters and units. - Structural integrity: Maintains overall layout continuity and restores page margins and layouts.
|
|
453
451
|
*
|
|
454
452
|
* @remarks
|
|
455
|
-
* ## Product
|
|
456
|
-
* Designed specifically for document translation
|
|
457
|
-
*
|
|
458
|
-
* - Content accuracy: translation accuracy
|
|
459
|
-
* - Structural integrity: overall layout continuity
|
|
460
|
-
* ##
|
|
461
|
-
* Cross-border e-commerce product manuals, contracts, agreements, business proposals, qualification documents,
|
|
462
|
-
* ##
|
|
463
|
-
* - Supports PDF and Word formats
|
|
464
|
-
* - Supports translation of text
|
|
465
|
-
* - Supports
|
|
466
|
-
* -
|
|
467
|
-
* - Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and
|
|
453
|
+
* ## Product introduction
|
|
454
|
+
* Designed specifically for document translation, this feature supports translation across more than 400 language pairs (including bridged pairs) and meets the needs of multi-scenario, multi-page, and high-complexity document translation. Scanned documents are not currently supported.
|
|
455
|
+
* It excels in the following aspects:
|
|
456
|
+
* - Content accuracy: Ensures translation accuracy and the accuracy of parameters and units.
|
|
457
|
+
* - Structural integrity: Maintains overall layout continuity and restores page margins and layouts.
|
|
458
|
+
* ## Scenarios
|
|
459
|
+
* Cross-border e-commerce product manuals, contracts, agreements, business proposals, qualification documents, teaching materials, and courseware.
|
|
460
|
+
* ## Features
|
|
461
|
+
* - Supports PDF and Word formats, and supports source documents containing multiple languages. For the detailed language list, see [Language pair mapping table](https://www.alibabacloud.com/help/en/document_detail/3041883.html).
|
|
462
|
+
* - Supports the translation of text in images within documents, as well as complex translation scenarios such as other charts and special symbols.
|
|
463
|
+
* - Supports highly restored layout after translation.
|
|
464
|
+
* - Supports up to 100 pages for a single PDF file and up to 100 pages for a single Word file.
|
|
465
|
+
* - Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and no 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, which meets your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention words. If you have more requirements, contact the platform for processing.
|
|
468
466
|
*
|
|
469
467
|
* @param request - DocumentTranslateRequest
|
|
470
468
|
* @returns DocumentTranslateResponse
|
|
471
469
|
*/
|
|
472
470
|
documentTranslate(request: $_model.DocumentTranslateRequest): Promise<$_model.DocumentTranslateResponse>;
|
|
473
471
|
/**
|
|
474
|
-
*
|
|
472
|
+
* E-commerce video replication is an AI video service designed 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. By preserving the original actions, camera pacing, and marketing structure, it rapidly generates multiple content versions to reduce shooting, editing, and adaptation costs.
|
|
475
473
|
*
|
|
476
474
|
* @remarks
|
|
477
475
|
* ## **Product introduction**
|
|
478
|
-
* E-commerce video
|
|
476
|
+
* E-commerce video replication is an AI video service designed 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. By preserving the original actions, camera pacing, and marketing structure, it rapidly generates multiple content versions to reduce shooting, editing, and adaptation costs.
|
|
479
477
|
* ## **Scenarios**
|
|
480
|
-
* - **Video
|
|
481
|
-
* - **
|
|
482
|
-
* - **Product explanation and selling point expression:** Suitable for products such as apparel, beauty and personal care, food and beverage, home and daily necessities,
|
|
483
|
-
* - **Multi-selling point and multi-version testing:**
|
|
484
|
-
* ## **
|
|
485
|
-
* ### **Core
|
|
478
|
+
* - **Video material replication:** Uses an existing e-commerce video as a template and replaces only the specified product or person in the video, preserving the original camera work, pacing, and marketing expression as much as possible. This is suitable for producing materials with multiple SKUs, models, regions, and versions.
|
|
479
|
+
* - **Rapid material generation for new products:** For newly launched products, it reduces the need for live-action shooting, studio setup, post-production editing, and repetitive production. It rapidly deploys video materials for new products, helping merchants shorten the launch cycle from spotting a viral video to breaking down the script and shooting new content.
|
|
480
|
+
* - **Product explanation and selling point expression:** Suitable for products such as apparel, beauty and personal care, food and beverage, home and daily necessities, consumer electronics, and small home appliances. It can replicate the explanation structure, demonstration actions, and camera pacing based on the selling points of the original video to generate explanation videos tailored for the conversion of new products.
|
|
481
|
+
* - **Multi-selling point and multi-version testing:** Rapidly generates multiple versions based on different product selling points, target audiences, scripts, camera work, and visual styles, supporting merchants in conducting content testing and iterating on advertising materials.
|
|
482
|
+
* ## **Service capabilities**
|
|
483
|
+
* ### **Core capabilities**
|
|
486
484
|
* * **Supports two replacement modes:**
|
|
487
485
|
*
|
|
488
|
-
* * **Product replacement (**`product_replacement`**)**:
|
|
486
|
+
* * **Product replacement (**`product_replacement`**)**: Preserves the identity, actions, scene, and sales structure of the original video host, and replaces the original product with the target product.
|
|
489
487
|
*
|
|
490
|
-
* * **Person replacement (**`person_replacement`**)**:
|
|
488
|
+
* * **Person replacement (**`person_replacement`**)**: Preserves the product, actions, scene, and sales structure of the original video, and replaces the person on camera with the target person from reference images or descriptions.
|
|
491
489
|
*
|
|
492
490
|
* * **Supports two generation modes:**
|
|
493
491
|
*
|
|
494
|
-
* * **Reference generation (**`reference`**)**: 1:1 replication. Uses the original video as a complete reference to automatically generate a new video with the same duration
|
|
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 pacing, and only performs targeted replacement of specified content such as persons or products.
|
|
495
493
|
*
|
|
496
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 duration of the original video and supports inputting a target duration.
|
|
497
495
|
*
|
|
498
|
-
* * **Fully automated end-to-end generation with zero prompt engineering
|
|
496
|
+
* * **Fully automated end-to-end generation with zero prompt engineering threshold**: Only requires 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.
|
|
499
497
|
*
|
|
500
|
-
* * **Product understanding and information structuring**: Identifies product categories, appearance, materials, colors, structures, and key components, and combines them with the titles, attributes, and selling points provided by
|
|
498
|
+
* * **Product understanding and information structuring**: Identifies product categories, appearance, materials, colors, structures, and key components, and combines them with the titles, attributes, and selling points provided by merchants to generate usable video expression information.
|
|
501
499
|
*
|
|
502
500
|
* * **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.
|
|
503
501
|
*
|
|
504
|
-
* * **Product subject consistency**: Maintains the stability of the product\\"s shape, color, texture, pattern, packaging, and logo
|
|
502
|
+
* * **Product subject consistency**: Maintains the stability of the product\\"s shape, color, texture, pattern, packaging, and logo across different camera shots, angles, actions, and scenes as much as possible.
|
|
505
503
|
*
|
|
506
504
|
* * **Product fidelity**: Multi-round VL quality inspection locks the product state (color, texture, structure, print) throughout the process to prevent product feature drift.
|
|
507
505
|
*
|
|
508
|
-
* * **Selling point script and storyboard replication**: Replicates the selling point planning, video structure, camera sequence,
|
|
506
|
+
* * **Selling point script and storyboard replication**: Replicates the selling point planning, video structure, camera shot sequence, demonstration actions, voiceover content, and ending style based on the original video.
|
|
509
507
|
*
|
|
510
|
-
* * **Commercial model adaptation**: Supports matching
|
|
508
|
+
* * **Commercial model adaptation**: Supports matching corresponding model images and demonstration methods based on product style, fit, target audience, and market demand.
|
|
511
509
|
*
|
|
512
|
-
* * **Quality verification and result feedback**: Performs multi-dimensional checks on the product subject, person,
|
|
510
|
+
* * **Quality verification and result feedback**: Performs multi-dimensional checks on the product subject, person, apparel, text, image integrity, audio, and overall usability, and outputs result information for manual review.
|
|
513
511
|
*
|
|
514
512
|
* @param tmpReq - EcomVideoRecreationRequest
|
|
515
513
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -517,63 +515,63 @@ export default class Client extends OpenApi {
|
|
|
517
515
|
*/
|
|
518
516
|
ecomVideoRecreationWithOptions(tmpReq: $_model.EcomVideoRecreationRequest, runtime: $dara.RuntimeOptions): Promise<$_model.EcomVideoRecreationResponse>;
|
|
519
517
|
/**
|
|
520
|
-
*
|
|
518
|
+
* E-commerce video replication is an AI video service designed 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. By preserving the original actions, camera pacing, and marketing structure, it rapidly generates multiple content versions to reduce shooting, editing, and adaptation costs.
|
|
521
519
|
*
|
|
522
520
|
* @remarks
|
|
523
521
|
* ## **Product introduction**
|
|
524
|
-
* E-commerce video
|
|
522
|
+
* E-commerce video replication is an AI video service designed 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. By preserving the original actions, camera pacing, and marketing structure, it rapidly generates multiple content versions to reduce shooting, editing, and adaptation costs.
|
|
525
523
|
* ## **Scenarios**
|
|
526
|
-
* - **Video
|
|
527
|
-
* - **
|
|
528
|
-
* - **Product explanation and selling point expression:** Suitable for products such as apparel, beauty and personal care, food and beverage, home and daily necessities,
|
|
529
|
-
* - **Multi-selling point and multi-version testing:**
|
|
530
|
-
* ## **
|
|
531
|
-
* ### **Core
|
|
524
|
+
* - **Video material replication:** Uses an existing e-commerce video as a template and replaces only the specified product or person in the video, preserving the original camera work, pacing, and marketing expression as much as possible. This is suitable for producing materials with multiple SKUs, models, regions, and versions.
|
|
525
|
+
* - **Rapid material generation for new products:** For newly launched products, it reduces the need for live-action shooting, studio setup, post-production editing, and repetitive production. It rapidly deploys video materials for new products, helping merchants shorten the launch cycle from spotting a viral video to breaking down the script and shooting new content.
|
|
526
|
+
* - **Product explanation and selling point expression:** Suitable for products such as apparel, beauty and personal care, food and beverage, home and daily necessities, consumer electronics, and small home appliances. It can replicate the explanation structure, demonstration actions, and camera pacing based on the selling points of the original video to generate explanation videos tailored for the conversion of new products.
|
|
527
|
+
* - **Multi-selling point and multi-version testing:** Rapidly generates multiple versions based on different product selling points, target audiences, scripts, camera work, and visual styles, supporting merchants in conducting content testing and iterating on advertising materials.
|
|
528
|
+
* ## **Service capabilities**
|
|
529
|
+
* ### **Core capabilities**
|
|
532
530
|
* * **Supports two replacement modes:**
|
|
533
531
|
*
|
|
534
|
-
* * **Product replacement (**`product_replacement`**)**:
|
|
532
|
+
* * **Product replacement (**`product_replacement`**)**: Preserves the identity, actions, scene, and sales structure of the original video host, and replaces the original product with the target product.
|
|
535
533
|
*
|
|
536
|
-
* * **Person replacement (**`person_replacement`**)**:
|
|
534
|
+
* * **Person replacement (**`person_replacement`**)**: Preserves the product, actions, scene, and sales structure of the original video, and replaces the person on camera with the target person from reference images or descriptions.
|
|
537
535
|
*
|
|
538
536
|
* * **Supports two generation modes:**
|
|
539
537
|
*
|
|
540
|
-
* * **Reference generation (**`reference`**)**: 1:1 replication. Uses the original video as a complete reference to automatically generate a new video with the same duration
|
|
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 pacing, and only performs targeted replacement of specified content such as persons or products.
|
|
541
539
|
*
|
|
542
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 duration of the original video and supports inputting a target duration.
|
|
543
541
|
*
|
|
544
|
-
* * **Fully automated end-to-end generation with zero prompt engineering
|
|
542
|
+
* * **Fully automated end-to-end generation with zero prompt engineering threshold**: Only requires 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.
|
|
545
543
|
*
|
|
546
|
-
* * **Product understanding and information structuring**: Identifies product categories, appearance, materials, colors, structures, and key components, and combines them with the titles, attributes, and selling points provided by
|
|
544
|
+
* * **Product understanding and information structuring**: Identifies product categories, appearance, materials, colors, structures, and key components, and combines them with the titles, attributes, and selling points provided by merchants to generate usable video expression information.
|
|
547
545
|
*
|
|
548
546
|
* * **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.
|
|
549
547
|
*
|
|
550
|
-
* * **Product subject consistency**: Maintains the stability of the product\\"s shape, color, texture, pattern, packaging, and logo
|
|
548
|
+
* * **Product subject consistency**: Maintains the stability of the product\\"s shape, color, texture, pattern, packaging, and logo across different camera shots, angles, actions, and scenes as much as possible.
|
|
551
549
|
*
|
|
552
550
|
* * **Product fidelity**: Multi-round VL quality inspection locks the product state (color, texture, structure, print) throughout the process to prevent product feature drift.
|
|
553
551
|
*
|
|
554
|
-
* * **Selling point script and storyboard replication**: Replicates the selling point planning, video structure, camera sequence,
|
|
552
|
+
* * **Selling point script and storyboard replication**: Replicates the selling point planning, video structure, camera shot sequence, demonstration actions, voiceover content, and ending style based on the original video.
|
|
555
553
|
*
|
|
556
|
-
* * **Commercial model adaptation**: Supports matching
|
|
554
|
+
* * **Commercial model adaptation**: Supports matching corresponding model images and demonstration methods based on product style, fit, target audience, and market demand.
|
|
557
555
|
*
|
|
558
|
-
* * **Quality verification and result feedback**: Performs multi-dimensional checks on the product subject, person,
|
|
556
|
+
* * **Quality verification and result feedback**: Performs multi-dimensional checks on the product subject, person, apparel, text, image integrity, audio, and overall usability, and outputs result information for manual review.
|
|
559
557
|
*
|
|
560
558
|
* @param request - EcomVideoRecreationRequest
|
|
561
559
|
* @returns EcomVideoRecreationResponse
|
|
562
560
|
*/
|
|
563
561
|
ecomVideoRecreation(request: $_model.EcomVideoRecreationRequest): Promise<$_model.EcomVideoRecreationResponse>;
|
|
564
562
|
/**
|
|
565
|
-
*
|
|
563
|
+
* Detects whether an image is recaptured and localizes main physical products, screen display areas, printed photos, and visible recapture clues based on recapture recognition and multimodal large model element localization. It is suitable for risk screening and manual review of store inspection photos across multiple categories.
|
|
566
564
|
*
|
|
567
565
|
* @remarks
|
|
568
566
|
* *Scenarios**
|
|
569
|
-
* 1. Inspection photo review: Screens
|
|
570
|
-
* 2. Screen or printed photo recapture verification:
|
|
571
|
-
* 3. Review clue display: Annotates products and visible clues on the original image to assist
|
|
567
|
+
* 1. Inspection photo review: Screens store-submitted photos for recapture risks.
|
|
568
|
+
* 2. Screen or printed photo recapture verification: Localizes visible screens, printed photos, and other media.
|
|
569
|
+
* 3. Review clue display: Annotates products and visible clues on the original image to assist in manual review.
|
|
572
570
|
* **Features**
|
|
573
|
-
* 1. General recapture detection:
|
|
574
|
-
* 2. Review element localization: Distinguishes physical products, screens, printed photos, and visible recapture clues. Products
|
|
575
|
-
* 3. Separate presentation of clues and conclusions: Localization text describes
|
|
576
|
-
* Supports a single HTTPS image
|
|
571
|
+
* 1. General recapture detection: Outputs a Boolean result for isFake.
|
|
572
|
+
* 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
|
+
* 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 a single HTTPS image input. The supplementary localization 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 localization is complete.
|
|
577
575
|
*
|
|
578
576
|
* @param request - GeneralRephotographyDetectionRequest
|
|
579
577
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -581,25 +579,63 @@ export default class Client extends OpenApi {
|
|
|
581
579
|
*/
|
|
582
580
|
generalRephotographyDetectionWithOptions(request: $_model.GeneralRephotographyDetectionRequest, runtime: $dara.RuntimeOptions): Promise<$_model.GeneralRephotographyDetectionResponse>;
|
|
583
581
|
/**
|
|
584
|
-
*
|
|
582
|
+
* Detects whether an image is recaptured and localizes main physical products, screen display areas, printed photos, and visible recapture clues based on recapture recognition and multimodal large model element localization. It is suitable for risk screening and manual review of store inspection photos across multiple categories.
|
|
585
583
|
*
|
|
586
584
|
* @remarks
|
|
587
585
|
* *Scenarios**
|
|
588
|
-
* 1. Inspection photo review: Screens
|
|
589
|
-
* 2. Screen or printed photo recapture verification:
|
|
590
|
-
* 3. Review clue display: Annotates products and visible clues on the original image to assist
|
|
586
|
+
* 1. Inspection photo review: Screens store-submitted photos for recapture risks.
|
|
587
|
+
* 2. Screen or printed photo recapture verification: Localizes visible screens, printed photos, and other media.
|
|
588
|
+
* 3. Review clue display: Annotates products and visible clues on the original image to assist in manual review.
|
|
591
589
|
* **Features**
|
|
592
|
-
* 1. General recapture detection:
|
|
593
|
-
* 2. Review element localization: Distinguishes physical products, screens, printed photos, and visible recapture clues. Products
|
|
594
|
-
* 3. Separate presentation of clues and conclusions: Localization text describes
|
|
595
|
-
* Supports a single HTTPS image
|
|
590
|
+
* 1. General recapture detection: Outputs a Boolean result for isFake.
|
|
591
|
+
* 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
|
+
* 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 a single HTTPS image input. The supplementary localization 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 localization is complete.
|
|
596
594
|
*
|
|
597
595
|
* @param request - GeneralRephotographyDetectionRequest
|
|
598
596
|
* @returns GeneralRephotographyDetectionResponse
|
|
599
597
|
*/
|
|
600
598
|
generalRephotographyDetection(request: $_model.GeneralRephotographyDetectionRequest): Promise<$_model.GeneralRephotographyDetectionResponse>;
|
|
601
599
|
/**
|
|
602
|
-
*
|
|
600
|
+
* Generates or rewrites e-commerce product copy, including titles, short highlights, search keywords, bullet points, and product descriptions, based on product information or existing copy. Adapts the content type and length to the requirements of the target platform. Supports Chinese and English input materials and optional multilingual translation, making it suitable for domestic product listing, cross-border product distribution, and product copy localization. Uses synchronous calls and processes one copy type for one product per request.
|
|
601
|
+
*
|
|
602
|
+
* @remarks
|
|
603
|
+
* # Product introduction
|
|
604
|
+
* Generates or rewrites e-commerce product copy, including titles, short highlights, search keywords, bullet points, and product descriptions, based on product information or existing copy. Adapts the content type and length to the requirements of the target platform.
|
|
605
|
+
* Supports Chinese and English input materials and optional multilingual translation, making it suitable for domestic product listing, cross-border product distribution, and product copy localization. Uses synchronous calls and processes one copy type for one product per request.
|
|
606
|
+
* # Scenarios
|
|
607
|
+
* | **Scenario** | **Description** |
|
|
608
|
+
* | --- | --- |
|
|
609
|
+
* | Same-platform localization | Select rewrite to translate as needed while retaining the original facts and structural type. |
|
|
610
|
+
* | 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 creation | Select generate to create the target content type based on product information. Categories and attributes can be used to supplement facts. |
|
|
612
|
+
* | Batch operation tool integration | The caller submits requests product by product. The workflow itself does not provide batch task or queuing APIs. |
|
|
613
|
+
* # Features
|
|
614
|
+
* ## Core capabilities
|
|
615
|
+
* This capability supports the creation of various copy content types for domestic and cross-border e-commerce scenarios. It can generate titles, detailed descriptions, keywords, highlights, and descriptions that comply with the content rules (such as length requirements and writing styles) of different platforms, and supports cross-language creation.
|
|
616
|
+
* | Content type | Platform | | | | | | Target language |
|
|
617
|
+
* | --- | --- | --- | --- | --- | --- | --- | --- |
|
|
618
|
+
* | | Amazon | Temu | TikTok | Shopify | Wildberries | Tmall |
|
|
619
|
+
* | **title** | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | Covers languages in popular regions:
|
|
620
|
+
* Chinese (zh), English (en), Russian (ru), German (de), French (fr), Korean (ko), Italian (it), Thai (th), Arabic (ar), Turkish (tr), Hebrew (he), Ukrainian (uk), Polish (pl), Japanese (ja), Dutch (nl), Portuguese (pt), Spanish (es), Malay (ms), Bulgarian (bg), Indonesian (id), and Vietnamese (vi). |
|
|
621
|
+
* | **highlight** | ✓ | | | | | ✓ |
|
|
622
|
+
* | **bulletPoint** | ✓ | | | ✓ | | |
|
|
623
|
+
* | **keywords** | ✓ | | | | | |
|
|
624
|
+
* | **description** | ✓ | ✓ | ✓ | ✓ | ✓ | |
|
|
625
|
+
* Based on the different content inputs provided by users, two production modes are supported:
|
|
626
|
+
* | **Mode** | **Description** | **Recommended scenario** |
|
|
627
|
+
* | --- | --- | --- |
|
|
628
|
+
* | Generate | Reorganizes and writes copy based on product information. | You have only product parameters, attributes, or selling points, or other types of product information, and need to create new titles, keywords, product descriptions, or other copy. |
|
|
629
|
+
* | Rewrite | Retains the original information and main structure while optimizing the expression. | You have existing product copy and want to adjust the wording, improve readability, or localize it with translation. |
|
|
630
|
+
* # Examples
|
|
631
|
+
* The following examples use the Amazon platform:
|
|
632
|
+
* | **Content type** | **Source language** | **Source content** | **Target language** | **Generated result** | **Capability advantage** |
|
|
633
|
+
* | --- | --- | --- | --- | --- | --- |
|
|
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 them in German bullet points for quick reading. |
|
|
635
|
+
* | 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 | Condenses lengthy materials to highlight core components and purposes, making it easy to grasp product features at a glance. |
|
|
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, reducing manual organization and translation efforts. |
|
|
638
|
+
* | 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. |
|
|
603
639
|
*
|
|
604
640
|
* @param request - GenerateProductContentRequest
|
|
605
641
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -607,28 +643,66 @@ export default class Client extends OpenApi {
|
|
|
607
643
|
*/
|
|
608
644
|
generateProductContentWithOptions(request: $_model.GenerateProductContentRequest, runtime: $dara.RuntimeOptions): Promise<$_model.GenerateProductContentResponse>;
|
|
609
645
|
/**
|
|
610
|
-
*
|
|
646
|
+
* Generates or rewrites e-commerce product copy, including titles, short highlights, search keywords, bullet points, and product descriptions, based on product information or existing copy. Adapts the content type and length to the requirements of the target platform. Supports Chinese and English input materials and optional multilingual translation, making it suitable for domestic product listing, cross-border product distribution, and product copy localization. Uses synchronous calls and processes one copy type for one product per request.
|
|
647
|
+
*
|
|
648
|
+
* @remarks
|
|
649
|
+
* # Product introduction
|
|
650
|
+
* Generates or rewrites e-commerce product copy, including titles, short highlights, search keywords, bullet points, and product descriptions, based on product information or existing copy. Adapts the content type and length to the requirements of the target platform.
|
|
651
|
+
* Supports Chinese and English input materials and optional multilingual translation, making it suitable for domestic product listing, cross-border product distribution, and product copy localization. Uses synchronous calls and processes one copy type for one product per request.
|
|
652
|
+
* # Scenarios
|
|
653
|
+
* | **Scenario** | **Description** |
|
|
654
|
+
* | --- | --- |
|
|
655
|
+
* | Same-platform localization | Select rewrite to translate as needed while retaining the original facts and structural type. |
|
|
656
|
+
* | 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 creation | Select generate to create the target content type based on product information. Categories and attributes can be used to supplement facts. |
|
|
658
|
+
* | Batch operation tool integration | The caller submits requests product by product. The workflow itself does not provide batch task or queuing APIs. |
|
|
659
|
+
* # Features
|
|
660
|
+
* ## Core capabilities
|
|
661
|
+
* This capability supports the creation of various copy content types for domestic and cross-border e-commerce scenarios. It can generate titles, detailed descriptions, keywords, highlights, and descriptions that comply with the content rules (such as length requirements and writing styles) of different platforms, and supports cross-language creation.
|
|
662
|
+
* | Content type | Platform | | | | | | Target language |
|
|
663
|
+
* | --- | --- | --- | --- | --- | --- | --- | --- |
|
|
664
|
+
* | | Amazon | Temu | TikTok | Shopify | Wildberries | Tmall |
|
|
665
|
+
* | **title** | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | Covers languages in popular regions:
|
|
666
|
+
* Chinese (zh), English (en), Russian (ru), German (de), French (fr), Korean (ko), Italian (it), Thai (th), Arabic (ar), Turkish (tr), Hebrew (he), Ukrainian (uk), Polish (pl), Japanese (ja), Dutch (nl), Portuguese (pt), Spanish (es), Malay (ms), Bulgarian (bg), Indonesian (id), and Vietnamese (vi). |
|
|
667
|
+
* | **highlight** | ✓ | | | | | ✓ |
|
|
668
|
+
* | **bulletPoint** | ✓ | | | ✓ | | |
|
|
669
|
+
* | **keywords** | ✓ | | | | | |
|
|
670
|
+
* | **description** | ✓ | ✓ | ✓ | ✓ | ✓ | |
|
|
671
|
+
* Based on the different content inputs provided by users, two production modes are supported:
|
|
672
|
+
* | **Mode** | **Description** | **Recommended scenario** |
|
|
673
|
+
* | --- | --- | --- |
|
|
674
|
+
* | Generate | Reorganizes and writes copy based on product information. | You have only product parameters, attributes, or selling points, or other types of product information, and need to create new titles, keywords, product descriptions, or other copy. |
|
|
675
|
+
* | Rewrite | Retains the original information and main structure while optimizing the expression. | You have existing product copy and want to adjust the wording, improve readability, or localize it with translation. |
|
|
676
|
+
* # Examples
|
|
677
|
+
* The following examples use the Amazon platform:
|
|
678
|
+
* | **Content type** | **Source language** | **Source content** | **Target language** | **Generated result** | **Capability advantage** |
|
|
679
|
+
* | --- | --- | --- | --- | --- | --- |
|
|
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 them in German bullet points for quick reading. |
|
|
681
|
+
* | 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 | Condenses lengthy materials to highlight core components and purposes, making it easy to grasp product features at a glance. |
|
|
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, reducing manual organization and translation efforts. |
|
|
684
|
+
* | 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. |
|
|
611
685
|
*
|
|
612
686
|
* @param request - GenerateProductContentRequest
|
|
613
687
|
* @returns GenerateProductContentResponse
|
|
614
688
|
*/
|
|
615
689
|
generateProductContent(request: $_model.GenerateProductContentRequest): Promise<$_model.GenerateProductContentResponse>;
|
|
616
690
|
/**
|
|
617
|
-
* Intelligently crops images to specified
|
|
691
|
+
* Intelligently crops images to specified sizes by automatically identifying the main subject area and precisely cropping them to various sizes to meet design requirements across different scenarios. (Synchronous)
|
|
618
692
|
*
|
|
619
693
|
* @remarks
|
|
620
|
-
* ## Product
|
|
621
|
-
* The image cropping service
|
|
622
|
-
* ##
|
|
623
|
-
* - **Multi-platform content distribution**: Automatically generates content in
|
|
694
|
+
* ## Product introduction
|
|
695
|
+
* The image cropping service can resize input images to specified dimensions. It supports automatic identification of the main subject area and precisely crops images to various sizes to meet design requirements across different scenarios. (Synchronous)
|
|
696
|
+
* ## Scenarios
|
|
697
|
+
* - **Multi-platform content distribution**: Automatically generates content styles in various sizes to adapt to the different image size requirements of different platforms and scenarios.
|
|
624
698
|
*
|
|
625
|
-
* - **Content
|
|
699
|
+
* - **Content delivery**: Automatically adjusts sizes for different ad slots on different platforms to highlight the main content, reduce blank space, and emphasize product features.
|
|
626
700
|
* ## Features
|
|
627
|
-
* *
|
|
701
|
+
* * Automatically identifies the main subject area of an image for precise cropping.
|
|
628
702
|
*
|
|
629
|
-
* *
|
|
630
|
-
* ##
|
|
631
|
-
* | **Original image** | **Cropped to 1000
|
|
703
|
+
* * Supports custom output sizes for cropping to adapt to different platforms and devices.
|
|
704
|
+
* ## Effect comparison
|
|
705
|
+
* | **Original image** | **Cropped to 1000\\*1000** | **Cropped to 3000\\*2000** |
|
|
632
706
|
* | --- | --- | --- |
|
|
633
707
|
* |  |  |  |
|
|
634
708
|
* |  |  |  |
|
|
@@ -640,21 +714,21 @@ export default class Client extends OpenApi {
|
|
|
640
714
|
*/
|
|
641
715
|
imageCroppingWithOptions(request: $_model.ImageCroppingRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageCroppingResponse>;
|
|
642
716
|
/**
|
|
643
|
-
* Intelligently crops images to specified
|
|
717
|
+
* Intelligently crops images to specified sizes by automatically identifying the main subject area and precisely cropping them to various sizes to meet design requirements across different scenarios. (Synchronous)
|
|
644
718
|
*
|
|
645
719
|
* @remarks
|
|
646
|
-
* ## Product
|
|
647
|
-
* The image cropping service
|
|
648
|
-
* ##
|
|
649
|
-
* - **Multi-platform content distribution**: Automatically generates content in
|
|
720
|
+
* ## Product introduction
|
|
721
|
+
* The image cropping service can resize input images to specified dimensions. It supports automatic identification of the main subject area and precisely crops images to various sizes to meet design requirements across different scenarios. (Synchronous)
|
|
722
|
+
* ## Scenarios
|
|
723
|
+
* - **Multi-platform content distribution**: Automatically generates content styles in various sizes to adapt to the different image size requirements of different platforms and scenarios.
|
|
650
724
|
*
|
|
651
|
-
* - **Content
|
|
725
|
+
* - **Content delivery**: Automatically adjusts sizes for different ad slots on different platforms to highlight the main content, reduce blank space, and emphasize product features.
|
|
652
726
|
* ## Features
|
|
653
|
-
* *
|
|
727
|
+
* * Automatically identifies the main subject area of an image for precise cropping.
|
|
654
728
|
*
|
|
655
|
-
* *
|
|
656
|
-
* ##
|
|
657
|
-
* | **Original image** | **Cropped to 1000
|
|
729
|
+
* * Supports custom output sizes for cropping to adapt to different platforms and devices.
|
|
730
|
+
* ## Effect comparison
|
|
731
|
+
* | **Original image** | **Cropped to 1000\\*1000** | **Cropped to 3000\\*2000** |
|
|
658
732
|
* | --- | --- | --- |
|
|
659
733
|
* |  |  |  |
|
|
660
734
|
* |  |  |  |
|
|
@@ -665,32 +739,32 @@ export default class Client extends OpenApi {
|
|
|
665
739
|
*/
|
|
666
740
|
imageCropping(request: $_model.ImageCroppingRequest): Promise<$_model.ImageCroppingResponse>;
|
|
667
741
|
/**
|
|
668
|
-
*
|
|
742
|
+
* Identifies the salient subject in an image, separates the subject from the background, and returns the subject image with the background removed. This feature also provides multiple background options and custom size options to optimize product display effects. (Synchronous)
|
|
669
743
|
*
|
|
670
744
|
* @remarks
|
|
671
|
-
* ## Product
|
|
672
|
-
* The intelligent image matting
|
|
745
|
+
* ## Product introduction
|
|
746
|
+
* The intelligent image matting feature automatically identifies the salient subject in an image, separates the subject from the background, and returns the subject image with the background removed. It also provides multiple background options and custom size options to optimize product display effects. (Synchronous)
|
|
673
747
|
* ## Scenarios
|
|
674
|
-
* * **
|
|
748
|
+
* * **Support secondary editing of materials**: After separating the image subject from the background, you can further edit the image.
|
|
675
749
|
*
|
|
676
|
-
* * **
|
|
750
|
+
* * **Improve material processing efficiency**: Quickly extract the subjects from various material images to facilitate background replacement, thereby improving the production efficiency of advertising images and marketing posters.
|
|
677
751
|
* ## Features.
|
|
678
|
-
* #### 1. One-click
|
|
679
|
-
* * **AI
|
|
752
|
+
* #### 1. One-click accurate subject identification
|
|
753
|
+
* * **Automatic AI identification**: Based on deep learning models, it intelligently distinguishes foreground subjects (such as portraits, products, and objects) from the background without manual outlining.
|
|
680
754
|
*
|
|
681
|
-
* * **Multi-scenario adaptation**: Supports
|
|
755
|
+
* * **Multi-scenario adaptation**: Supports accurate segmentation in complex scenarios (such as hair, transparent objects, and fur edges) with an accuracy rate of over 95%.
|
|
682
756
|
* #### 2. Intelligent edge optimization
|
|
683
|
-
* * **Detail-level processing**: Performs automatic optimization on edge
|
|
757
|
+
* * **Detail-level processing**: Performs automatic optimization on edge jaggies and semi-transparent areas (such as smoke and glass) to retain natural transition effects.
|
|
684
758
|
* #### 3. Multi-format output and background operations
|
|
685
|
-
* * **Transparent background export**: Directly generates PNG images with transparent backgrounds and white backgrounds,
|
|
759
|
+
* * **Transparent background export**: Directly generates PNG images with transparent backgrounds and white backgrounds, adapting to e-commerce and design scenarios.
|
|
686
760
|
*
|
|
687
|
-
* * **Custom background color support
|
|
761
|
+
* * **Custom background color support**: Supports custom background colors.
|
|
688
762
|
* ## Effect comparison
|
|
689
763
|
* | **Original image (input)** | **Result image (output)** |
|
|
690
764
|
* | --- | --- |
|
|
691
|
-
* |  |  |
|
|
766
|
+
* |  |  |
|
|
767
|
+
* |  |  |
|
|
694
768
|
*
|
|
695
769
|
* @param request - ImageMattingRequest
|
|
696
770
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -698,48 +772,48 @@ export default class Client extends OpenApi {
|
|
|
698
772
|
*/
|
|
699
773
|
imageMattingWithOptions(request: $_model.ImageMattingRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageMattingResponse>;
|
|
700
774
|
/**
|
|
701
|
-
*
|
|
775
|
+
* Identifies the salient subject in an image, separates the subject from the background, and returns the subject image with the background removed. This feature also provides multiple background options and custom size options to optimize product display effects. (Synchronous)
|
|
702
776
|
*
|
|
703
777
|
* @remarks
|
|
704
|
-
* ## Product
|
|
705
|
-
* The intelligent image matting
|
|
778
|
+
* ## Product introduction
|
|
779
|
+
* The intelligent image matting feature automatically identifies the salient subject in an image, separates the subject from the background, and returns the subject image with the background removed. It also provides multiple background options and custom size options to optimize product display effects. (Synchronous)
|
|
706
780
|
* ## Scenarios
|
|
707
|
-
* * **
|
|
781
|
+
* * **Support secondary editing of materials**: After separating the image subject from the background, you can further edit the image.
|
|
708
782
|
*
|
|
709
|
-
* * **
|
|
783
|
+
* * **Improve material processing efficiency**: Quickly extract the subjects from various material images to facilitate background replacement, thereby improving the production efficiency of advertising images and marketing posters.
|
|
710
784
|
* ## Features.
|
|
711
|
-
* #### 1. One-click
|
|
712
|
-
* * **AI
|
|
785
|
+
* #### 1. One-click accurate subject identification
|
|
786
|
+
* * **Automatic AI identification**: Based on deep learning models, it intelligently distinguishes foreground subjects (such as portraits, products, and objects) from the background without manual outlining.
|
|
713
787
|
*
|
|
714
|
-
* * **Multi-scenario adaptation**: Supports
|
|
788
|
+
* * **Multi-scenario adaptation**: Supports accurate segmentation in complex scenarios (such as hair, transparent objects, and fur edges) with an accuracy rate of over 95%.
|
|
715
789
|
* #### 2. Intelligent edge optimization
|
|
716
|
-
* * **Detail-level processing**: Performs automatic optimization on edge
|
|
790
|
+
* * **Detail-level processing**: Performs automatic optimization on edge jaggies and semi-transparent areas (such as smoke and glass) to retain natural transition effects.
|
|
717
791
|
* #### 3. Multi-format output and background operations
|
|
718
|
-
* * **Transparent background export**: Directly generates PNG images with transparent backgrounds and white backgrounds,
|
|
792
|
+
* * **Transparent background export**: Directly generates PNG images with transparent backgrounds and white backgrounds, adapting to e-commerce and design scenarios.
|
|
719
793
|
*
|
|
720
|
-
* * **Custom background color support
|
|
794
|
+
* * **Custom background color support**: Supports custom background colors.
|
|
721
795
|
* ## Effect comparison
|
|
722
796
|
* | **Original image (input)** | **Result image (output)** |
|
|
723
797
|
* | --- | --- |
|
|
724
|
-
* |  |  |
|
|
799
|
+
* |  |  |
|
|
800
|
+
* |  |  |
|
|
727
801
|
*
|
|
728
802
|
* @param request - ImageMattingRequest
|
|
729
803
|
* @returns ImageMattingResponse
|
|
730
804
|
*/
|
|
731
805
|
imageMatting(request: $_model.ImageMattingRequest): Promise<$_model.ImageMattingResponse>;
|
|
732
806
|
/**
|
|
733
|
-
* Extracts the salient subject from an image by separating it from the background and returns the subject image with the background removed.
|
|
807
|
+
* Extracts the salient subject from an image by automatically identifying and separating it from the background, and returns the subject image with the background removed. This operation also provides multiple background options and custom size selections to optimize product display.
|
|
734
808
|
*
|
|
735
809
|
* @remarks
|
|
736
810
|
* # Scenarios
|
|
737
811
|
* * Supports secondary editing of materials: After separating the image subject from the background, you can further edit the image.
|
|
738
812
|
*
|
|
739
|
-
* * Improves material processing efficiency: Quickly extracts the subjects
|
|
813
|
+
* * Improves material processing efficiency: Quickly extracts the subjects of various material images to facilitate background replacement, thereby improving the production efficiency of advertising images and marketing posters.
|
|
740
814
|
* # Features.
|
|
741
815
|
* #### 1. One-click precise subject recognition
|
|
742
|
-
* * **AI-based automatic recognition**: Based on deep learning models,
|
|
816
|
+
* * **AI-based automatic recognition**: Based on deep learning models, intelligently distinguishes foreground subjects (portraits, products, objects, etc.) from the background without manual outlining.
|
|
743
817
|
*
|
|
744
818
|
* * **Multi-scenario adaptation**: Supports precise segmentation in complex scenarios (such as hair, transparent objects, and fur edges) with an accuracy rate of over 95%.
|
|
745
819
|
* #### 2. Intelligent edge optimization
|
|
@@ -747,7 +821,7 @@ export default class Client extends OpenApi {
|
|
|
747
821
|
* #### 3. Multi-format output and background operations
|
|
748
822
|
* * **Transparent background export**: Directly generates PNG images with transparent backgrounds and white backgrounds, adapting to e-commerce and design scenarios.
|
|
749
823
|
*
|
|
750
|
-
* * **
|
|
824
|
+
* * **Supports custom background colors**
|
|
751
825
|
* # Effect comparison
|
|
752
826
|
* | **Original image (input)** | **Result image (output)** |
|
|
753
827
|
* | --- | --- |
|
|
@@ -761,16 +835,16 @@ export default class Client extends OpenApi {
|
|
|
761
835
|
*/
|
|
762
836
|
imageMattingAsyncWithOptions(request: $_model.ImageMattingAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageMattingAsyncResponse>;
|
|
763
837
|
/**
|
|
764
|
-
* Extracts the salient subject from an image by separating it from the background and returns the subject image with the background removed.
|
|
838
|
+
* Extracts the salient subject from an image by automatically identifying and separating it from the background, and returns the subject image with the background removed. This operation also provides multiple background options and custom size selections to optimize product display.
|
|
765
839
|
*
|
|
766
840
|
* @remarks
|
|
767
841
|
* # Scenarios
|
|
768
842
|
* * Supports secondary editing of materials: After separating the image subject from the background, you can further edit the image.
|
|
769
843
|
*
|
|
770
|
-
* * Improves material processing efficiency: Quickly extracts the subjects
|
|
844
|
+
* * Improves material processing efficiency: Quickly extracts the subjects of various material images to facilitate background replacement, thereby improving the production efficiency of advertising images and marketing posters.
|
|
771
845
|
* # Features.
|
|
772
846
|
* #### 1. One-click precise subject recognition
|
|
773
|
-
* * **AI-based automatic recognition**: Based on deep learning models,
|
|
847
|
+
* * **AI-based automatic recognition**: Based on deep learning models, intelligently distinguishes foreground subjects (portraits, products, objects, etc.) from the background without manual outlining.
|
|
774
848
|
*
|
|
775
849
|
* * **Multi-scenario adaptation**: Supports precise segmentation in complex scenarios (such as hair, transparent objects, and fur edges) with an accuracy rate of over 95%.
|
|
776
850
|
* #### 2. Intelligent edge optimization
|
|
@@ -778,7 +852,7 @@ export default class Client extends OpenApi {
|
|
|
778
852
|
* #### 3. Multi-format output and background operations
|
|
779
853
|
* * **Transparent background export**: Directly generates PNG images with transparent backgrounds and white backgrounds, adapting to e-commerce and design scenarios.
|
|
780
854
|
*
|
|
781
|
-
* * **
|
|
855
|
+
* * **Supports custom background colors**
|
|
782
856
|
* # Effect comparison
|
|
783
857
|
* | **Original image (input)** | **Result image (output)** |
|
|
784
858
|
* | --- | --- |
|
|
@@ -791,39 +865,39 @@ export default class Client extends OpenApi {
|
|
|
791
865
|
*/
|
|
792
866
|
imageMattingAsync(request: $_model.ImageMattingAsyncRequest): Promise<$_model.ImageMattingAsyncResponse>;
|
|
793
867
|
/**
|
|
794
|
-
*
|
|
868
|
+
* Identifies specific elements in e-commerce images.
|
|
795
869
|
*
|
|
796
870
|
* @remarks
|
|
797
871
|
* ## Product Introduction
|
|
798
|
-
* The
|
|
872
|
+
* The intelligent element recognition API is designed specifically for recognizing specific elements in e-commerce images. It deeply analyzes image details to help users quickly identify elements such as text, logos, watermarks, and text-containing color blocks in the main subject and background of an image, greatly improving the efficiency and accuracy of image filtering. (Synchronous)
|
|
799
873
|
* ## Scenarios
|
|
800
|
-
* **1. Intelligent image
|
|
801
|
-
* Merchants and platforms can use the
|
|
874
|
+
* **1. Intelligent image filtering and optimization:**
|
|
875
|
+
* 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, you can further call the intelligent elimination API to optimize these images, improve image quality, and shorten the product release cycle.
|
|
802
876
|
* **2. Automated image processing and efficiency improvement:**
|
|
803
|
-
*
|
|
877
|
+
* Through the intelligent element recognition API, merchants and platforms can automate the image processing workflow to automatically identify and mark image elements that need optimization. This workflow reduces manual intervention and improves image processing efficiency.
|
|
804
878
|
* ## Features
|
|
805
|
-
* **1. Definitions of image subject, image background, text, logo, watermark, and text-containing color block: For details, see the
|
|
879
|
+
* **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).**
|
|
806
880
|
* * Image subject: The core product area in the image.
|
|
807
881
|
*
|
|
808
|
-
* * Image background: The
|
|
882
|
+
* * Image background: The rest of the image other than the product subject.
|
|
809
883
|
*
|
|
810
|
-
* * Text: Horizontal, vertical, or
|
|
884
|
+
* * Text: Horizontal, vertical, or slanted English or Chinese text.
|
|
811
885
|
*
|
|
812
|
-
* * Logo:
|
|
886
|
+
* * Logo: Logos or trademarks.
|
|
813
887
|
*
|
|
814
|
-
* * Watermark: Monochrome transparent text,
|
|
888
|
+
* * Watermark: Monochrome transparent text, logos, images, URLs, store names, etc.
|
|
815
889
|
*
|
|
816
|
-
* * Text-containing color block:
|
|
890
|
+
* * Text-containing color block: Color blocks containing text outside the subject.
|
|
817
891
|
*
|
|
818
|
-
* **2. The
|
|
892
|
+
* **2. The features of the intelligent element recognition API mainly include:**
|
|
819
893
|
* * Element recognition: Identifies whether elements such as text, logos, watermarks, and text-containing color blocks exist in the image subject and background.
|
|
820
894
|
*
|
|
821
|
-
* * Workflow
|
|
895
|
+
* * Workflow collaboration: Used in combination with the intelligent elimination API. First, the intelligent element recognition API identifies the elements to be removed, and then the intelligent elimination API effectively removes them to ensure the accuracy and efficiency of image processing.
|
|
822
896
|
* ## Technical advantages
|
|
823
|
-
* * Synchronous batch processing: As a synchronous API, the
|
|
897
|
+
* * Synchronous batch processing: As a synchronous API, the intelligent element recognition API can process a large number of images while maintaining fast response, adapting to business needs of different scales.
|
|
824
898
|
*
|
|
825
|
-
* * Flexibility: Users can select the types of elements to
|
|
826
|
-
* ##
|
|
899
|
+
* * Flexibility: Users can select the types of elements to be recognized as needed, including elements in the subject and non-subject areas, such as watermarks, logos, and text, to meet personalized recognition needs.
|
|
900
|
+
* ## Result comparison
|
|
827
901
|
* | **Original image** | **Recognition result** |
|
|
828
902
|
* | --- | --- |
|
|
829
903
|
* |  | [Subject]
|
|
@@ -867,39 +941,39 @@ export default class Client extends OpenApi {
|
|
|
867
941
|
*/
|
|
868
942
|
imageRecognitionWithOptions(tmpReq: $_model.ImageRecognitionRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageRecognitionResponse>;
|
|
869
943
|
/**
|
|
870
|
-
*
|
|
944
|
+
* Identifies specific elements in e-commerce images.
|
|
871
945
|
*
|
|
872
946
|
* @remarks
|
|
873
947
|
* ## Product Introduction
|
|
874
|
-
* The
|
|
948
|
+
* The intelligent element recognition API is designed specifically for recognizing specific elements in e-commerce images. It deeply analyzes image details to help users quickly identify elements such as text, logos, watermarks, and text-containing color blocks in the main subject and background of an image, greatly improving the efficiency and accuracy of image filtering. (Synchronous)
|
|
875
949
|
* ## Scenarios
|
|
876
|
-
* **1. Intelligent image
|
|
877
|
-
* Merchants and platforms can use the
|
|
950
|
+
* **1. Intelligent image filtering and optimization:**
|
|
951
|
+
* 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, you can further call the intelligent elimination API to optimize these images, improve image quality, and shorten the product release cycle.
|
|
878
952
|
* **2. Automated image processing and efficiency improvement:**
|
|
879
|
-
*
|
|
953
|
+
* Through the intelligent element recognition API, merchants and platforms can automate the image processing workflow to automatically identify and mark image elements that need optimization. This workflow reduces manual intervention and improves image processing efficiency.
|
|
880
954
|
* ## Features
|
|
881
|
-
* **1. Definitions of image subject, image background, text, logo, watermark, and text-containing color block: For details, see the
|
|
955
|
+
* **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).**
|
|
882
956
|
* * Image subject: The core product area in the image.
|
|
883
957
|
*
|
|
884
|
-
* * Image background: The
|
|
958
|
+
* * Image background: The rest of the image other than the product subject.
|
|
885
959
|
*
|
|
886
|
-
* * Text: Horizontal, vertical, or
|
|
960
|
+
* * Text: Horizontal, vertical, or slanted English or Chinese text.
|
|
887
961
|
*
|
|
888
|
-
* * Logo:
|
|
962
|
+
* * Logo: Logos or trademarks.
|
|
889
963
|
*
|
|
890
|
-
* * Watermark: Monochrome transparent text,
|
|
964
|
+
* * Watermark: Monochrome transparent text, logos, images, URLs, store names, etc.
|
|
891
965
|
*
|
|
892
|
-
* * Text-containing color block:
|
|
966
|
+
* * Text-containing color block: Color blocks containing text outside the subject.
|
|
893
967
|
*
|
|
894
|
-
* **2. The
|
|
968
|
+
* **2. The features of the intelligent element recognition API mainly include:**
|
|
895
969
|
* * Element recognition: Identifies whether elements such as text, logos, watermarks, and text-containing color blocks exist in the image subject and background.
|
|
896
970
|
*
|
|
897
|
-
* * Workflow
|
|
971
|
+
* * Workflow collaboration: Used in combination with the intelligent elimination API. First, the intelligent element recognition API identifies the elements to be removed, and then the intelligent elimination API effectively removes them to ensure the accuracy and efficiency of image processing.
|
|
898
972
|
* ## Technical advantages
|
|
899
|
-
* * Synchronous batch processing: As a synchronous API, the
|
|
973
|
+
* * Synchronous batch processing: As a synchronous API, the intelligent element recognition API can process a large number of images while maintaining fast response, adapting to business needs of different scales.
|
|
900
974
|
*
|
|
901
|
-
* * Flexibility: Users can select the types of elements to
|
|
902
|
-
* ##
|
|
975
|
+
* * Flexibility: Users can select the types of elements to be recognized as needed, including elements in the subject and non-subject areas, such as watermarks, logos, and text, to meet personalized recognition needs.
|
|
976
|
+
* ## Result comparison
|
|
903
977
|
* | **Original image** | **Recognition result** |
|
|
904
978
|
* | --- | --- |
|
|
905
979
|
* |  | [Subject]
|
|
@@ -942,12 +1016,12 @@ export default class Client extends OpenApi {
|
|
|
942
1016
|
*/
|
|
943
1017
|
imageRecognition(request: $_model.ImageRecognitionRequest): Promise<$_model.ImageRecognitionResponse>;
|
|
944
1018
|
/**
|
|
945
|
-
* Identifies specific elements in e-commerce images. It
|
|
1019
|
+
* Identifies specific elements in e-commerce images. It deeply analyzes image details to help users quickly identify elements such as text, logos, watermarks, and text-containing color blocks in the main subject and background, significantly improving the efficiency and accuracy of image filtering.
|
|
946
1020
|
*
|
|
947
1021
|
* @remarks
|
|
948
1022
|
* # Scenarios
|
|
949
1023
|
* 1. Intelligent image filtering and optimization:
|
|
950
|
-
* 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.
|
|
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 further call the intelligent elimination API to optimize these images, improve image quality, and shorten the product release cycle.
|
|
951
1025
|
* 2. Automated image processing and efficiency improvement:
|
|
952
1026
|
* 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.
|
|
953
1027
|
* # Features
|
|
@@ -956,18 +1030,18 @@ export default class Client extends OpenApi {
|
|
|
956
1030
|
*
|
|
957
1031
|
* * Image background: The rest of the image other than the product subject.
|
|
958
1032
|
*
|
|
959
|
-
* * Text: Horizontal, vertical, or
|
|
1033
|
+
* * Text: Horizontal, vertical, or slanted English or Chinese text.
|
|
960
1034
|
*
|
|
961
1035
|
* * Logo: A logo or trademark.
|
|
962
1036
|
*
|
|
963
|
-
* * Watermark: Monochrome transparent text, logos, images, URLs, store names
|
|
1037
|
+
* * Watermark: Monochrome transparent text, logos, images, URLs, or store names.
|
|
964
1038
|
*
|
|
965
1039
|
* * Text-containing color block: A color block containing text outside the subject.
|
|
966
1040
|
*
|
|
967
|
-
* **2. The intelligent element recognition API
|
|
1041
|
+
* **2. The features of the intelligent element recognition API include:**
|
|
968
1042
|
* * Element recognition: Identifies whether elements such as text, logos, watermarks, and text-containing color blocks exist in the image subject and background.
|
|
969
1043
|
*
|
|
970
|
-
* * Workflow collaboration: Used in combination with the intelligent elimination API.
|
|
1044
|
+
* * 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.
|
|
971
1045
|
*
|
|
972
1046
|
* **3. Technical advantages:**
|
|
973
1047
|
* * Synchronous batch processing: As a synchronous API, the intelligent element recognition API can process a large number of images while maintaining fast response, adapting to business needs of different scales.
|
|
@@ -1017,12 +1091,12 @@ export default class Client extends OpenApi {
|
|
|
1017
1091
|
*/
|
|
1018
1092
|
imageRecognitionAsyncWithOptions(tmpReq: $_model.ImageRecognitionAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageRecognitionAsyncResponse>;
|
|
1019
1093
|
/**
|
|
1020
|
-
* Identifies specific elements in e-commerce images. It
|
|
1094
|
+
* Identifies specific elements in e-commerce images. It deeply analyzes image details to help users quickly identify elements such as text, logos, watermarks, and text-containing color blocks in the main subject and background, significantly improving the efficiency and accuracy of image filtering.
|
|
1021
1095
|
*
|
|
1022
1096
|
* @remarks
|
|
1023
1097
|
* # Scenarios
|
|
1024
1098
|
* 1. Intelligent image filtering and optimization:
|
|
1025
|
-
* 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.
|
|
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 further call the intelligent elimination API to optimize these images, improve image quality, and shorten the product release cycle.
|
|
1026
1100
|
* 2. Automated image processing and efficiency improvement:
|
|
1027
1101
|
* 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.
|
|
1028
1102
|
* # Features
|
|
@@ -1031,18 +1105,18 @@ export default class Client extends OpenApi {
|
|
|
1031
1105
|
*
|
|
1032
1106
|
* * Image background: The rest of the image other than the product subject.
|
|
1033
1107
|
*
|
|
1034
|
-
* * Text: Horizontal, vertical, or
|
|
1108
|
+
* * Text: Horizontal, vertical, or slanted English or Chinese text.
|
|
1035
1109
|
*
|
|
1036
1110
|
* * Logo: A logo or trademark.
|
|
1037
1111
|
*
|
|
1038
|
-
* * Watermark: Monochrome transparent text, logos, images, URLs, store names
|
|
1112
|
+
* * Watermark: Monochrome transparent text, logos, images, URLs, or store names.
|
|
1039
1113
|
*
|
|
1040
1114
|
* * Text-containing color block: A color block containing text outside the subject.
|
|
1041
1115
|
*
|
|
1042
|
-
* **2. The intelligent element recognition API
|
|
1116
|
+
* **2. The features of the intelligent element recognition API include:**
|
|
1043
1117
|
* * Element recognition: Identifies whether elements such as text, logos, watermarks, and text-containing color blocks exist in the image subject and background.
|
|
1044
1118
|
*
|
|
1045
|
-
* * Workflow collaboration: Used in combination with the intelligent elimination API.
|
|
1119
|
+
* * 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.
|
|
1046
1120
|
*
|
|
1047
1121
|
* **3. Technical advantages:**
|
|
1048
1122
|
* * Synchronous batch processing: As a synchronous API, the intelligent element recognition API can process a large number of images while maintaining fast response, adapting to business needs of different scales.
|
|
@@ -1091,31 +1165,31 @@ export default class Client extends OpenApi {
|
|
|
1091
1165
|
*/
|
|
1092
1166
|
imageRecognitionAsync(request: $_model.ImageRecognitionAsyncRequest): Promise<$_model.ImageRecognitionAsyncResponse>;
|
|
1093
1167
|
/**
|
|
1094
|
-
* Intelligently
|
|
1168
|
+
* Intelligently removes unwanted elements from e-commerce images. Tailored for e-commerce scenarios, it automatically identifies and removes text, specific names, transparent text blocks, and watermarks. You can specify objects to remove on demand to efficiently and accurately process large image batches and simplify image editing in synchronous or asynchronous mode.
|
|
1095
1169
|
*
|
|
1096
1170
|
* @remarks
|
|
1097
1171
|
* ## Product Introduction
|
|
1098
|
-
* The
|
|
1099
|
-
* ##
|
|
1100
|
-
* * **Efficient e-commerce
|
|
1172
|
+
* The intelligent image object removal product is customized for e-commerce images. It automatically identifies and removes text, specific names, transparent text blocks, and intrusive text overlays from e-commerce images. You can specify objects to be removed as needed to efficiently and accurately process large batches of images and simplify image editing. Supports synchronous and asynchronous modes.
|
|
1173
|
+
* ## Scenarios
|
|
1174
|
+
* * **Efficient processing of e-commerce images:**
|
|
1101
1175
|
*
|
|
1102
|
-
*
|
|
1103
|
-
* * **
|
|
1176
|
+
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
1177
|
+
* * **Product information synchronization across multiple platforms:**
|
|
1104
1178
|
*
|
|
1105
|
-
* When
|
|
1106
|
-
* ##
|
|
1107
|
-
* 1. First,
|
|
1179
|
+
* When merchants list products on different e-commerce platforms, they can quickly remove specific text and intrusive text overlays to comply with the image specifications of different platforms.
|
|
1180
|
+
* ## Features
|
|
1181
|
+
* 1. First, clarify the definitions of the image subject and the image background. In actual use, when specifying the objects to be removed, you can choose the removal scope to be the image subject or the image background area. Both API and editor integration methods are supported to meet different types of requirements.
|
|
1108
1182
|
*
|
|
1109
1183
|
* 1. Image subject: the core product area in the image.
|
|
1110
1184
|
*
|
|
1111
|
-
* 2. Image background: the
|
|
1185
|
+
* 2. Image background: the rest of the image other than the product subject.
|
|
1112
1186
|
*
|
|
1113
|
-
* 2.
|
|
1114
|
-
* ##
|
|
1115
|
-
* | **Original image** | **Image after
|
|
1187
|
+
* 2. Second, the objects to be removed support the following four types: text, specific names, transparent text blocks, and intrusive text overlays. You can refer to the following examples to clarify your usage requirements and perform targeted operations:
|
|
1188
|
+
* ## Result comparison
|
|
1189
|
+
* | **Original image** | **Image after removal** |
|
|
1116
1190
|
* | --- | --- |
|
|
1117
|
-
* |  |  |
|
|
1192
|
+
* |  |  |
|
|
1119
1193
|
*
|
|
1120
1194
|
* @param request - ImageRemovalProRequest
|
|
1121
1195
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -1123,58 +1197,58 @@ export default class Client extends OpenApi {
|
|
|
1123
1197
|
*/
|
|
1124
1198
|
imageRemovalProWithOptions(request: $_model.ImageRemovalProRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageRemovalProResponse>;
|
|
1125
1199
|
/**
|
|
1126
|
-
* Intelligently
|
|
1200
|
+
* Intelligently removes unwanted elements from e-commerce images. Tailored for e-commerce scenarios, it automatically identifies and removes text, specific names, transparent text blocks, and watermarks. You can specify objects to remove on demand to efficiently and accurately process large image batches and simplify image editing in synchronous or asynchronous mode.
|
|
1127
1201
|
*
|
|
1128
1202
|
* @remarks
|
|
1129
1203
|
* ## Product Introduction
|
|
1130
|
-
* The
|
|
1131
|
-
* ##
|
|
1132
|
-
* * **Efficient e-commerce
|
|
1204
|
+
* The intelligent image object removal product is customized for e-commerce images. It automatically identifies and removes text, specific names, transparent text blocks, and intrusive text overlays from e-commerce images. You can specify objects to be removed as needed to efficiently and accurately process large batches of images and simplify image editing. Supports synchronous and asynchronous modes.
|
|
1205
|
+
* ## Scenarios
|
|
1206
|
+
* * **Efficient processing of e-commerce images:**
|
|
1133
1207
|
*
|
|
1134
|
-
*
|
|
1135
|
-
* * **
|
|
1208
|
+
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
1209
|
+
* * **Product information synchronization across multiple platforms:**
|
|
1136
1210
|
*
|
|
1137
|
-
* When
|
|
1138
|
-
* ##
|
|
1139
|
-
* 1. First,
|
|
1211
|
+
* When merchants list products on different e-commerce platforms, they can quickly remove specific text and intrusive text overlays to comply with the image specifications of different platforms.
|
|
1212
|
+
* ## Features
|
|
1213
|
+
* 1. First, clarify the definitions of the image subject and the image background. In actual use, when specifying the objects to be removed, you can choose the removal scope to be the image subject or the image background area. Both API and editor integration methods are supported to meet different types of requirements.
|
|
1140
1214
|
*
|
|
1141
1215
|
* 1. Image subject: the core product area in the image.
|
|
1142
1216
|
*
|
|
1143
|
-
* 2. Image background: the
|
|
1217
|
+
* 2. Image background: the rest of the image other than the product subject.
|
|
1144
1218
|
*
|
|
1145
|
-
* 2.
|
|
1146
|
-
* ##
|
|
1147
|
-
* | **Original image** | **Image after
|
|
1219
|
+
* 2. Second, the objects to be removed support the following four types: text, specific names, transparent text blocks, and intrusive text overlays. You can refer to the following examples to clarify your usage requirements and perform targeted operations:
|
|
1220
|
+
* ## Result comparison
|
|
1221
|
+
* | **Original image** | **Image after removal** |
|
|
1148
1222
|
* | --- | --- |
|
|
1149
|
-
* |  |  |
|
|
1224
|
+
* |  |  |
|
|
1151
1225
|
*
|
|
1152
1226
|
* @param request - ImageRemovalProRequest
|
|
1153
1227
|
* @returns ImageRemovalProResponse
|
|
1154
1228
|
*/
|
|
1155
1229
|
imageRemovalPro(request: $_model.ImageRemovalProRequest): Promise<$_model.ImageRemovalProResponse>;
|
|
1156
1230
|
/**
|
|
1157
|
-
* Removes
|
|
1231
|
+
* Removes text, specific names, transparent text blocks, and promotional watermarks from e-commerce images. This operation automatically identifies and removes these elements or allows you to specify the objects to be removed, enabling efficient and accurate processing of large batches of images and simplifying image editing.
|
|
1158
1232
|
*
|
|
1159
1233
|
* @remarks
|
|
1160
1234
|
* ## Scenarios
|
|
1161
|
-
* * **Efficient
|
|
1235
|
+
* * **Efficient e-commerce image processing:**
|
|
1162
1236
|
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
1163
|
-
* * **
|
|
1164
|
-
* Quickly removes specific text and watermarks when merchants list products on different e-commerce platforms
|
|
1237
|
+
* * **Multi-platform product information synchronization:**
|
|
1238
|
+
* Quickly removes specific text and promotional watermarks when merchants list products on different e-commerce platforms, ensuring compliance with the image specifications of different platforms.
|
|
1165
1239
|
* ## Features
|
|
1166
|
-
* 1. First, understand the definitions of the image subject and the image background. In actual use, when specifying the objects to
|
|
1240
|
+
* 1. First, understand the definitions of the image subject and the image background. In actual use, when specifying the objects to be removed, you can choose to remove objects from the image subject or the image background. Both API and editor integration methods are supported to meet different needs.
|
|
1167
1241
|
*
|
|
1168
1242
|
* 1. Image subject: the core product area in the image.
|
|
1169
1243
|
*
|
|
1170
|
-
* 2. Image background: the rest of the image
|
|
1244
|
+
* 2. Image background: the rest of the image excluding the product subject.
|
|
1171
1245
|
*
|
|
1172
|
-
* 2. Second, the
|
|
1246
|
+
* 2. Second, the objects to be removed can be text, specific names, transparent text blocks, or promotional watermarks. You can refer to the following examples to clarify your requirements and perform targeted operations:
|
|
1173
1247
|
* ## Effect comparison
|
|
1174
1248
|
* | **Original image** | **Processed image** |
|
|
1175
1249
|
* | --- | --- |
|
|
1176
1250
|
* |  |  |
|
|
1177
|
-
* |  |  |
|
|
1178
1252
|
*
|
|
1179
1253
|
* @param request - ImageRemovalProAsyncRequest
|
|
1180
1254
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -1182,27 +1256,27 @@ export default class Client extends OpenApi {
|
|
|
1182
1256
|
*/
|
|
1183
1257
|
imageRemovalProAsyncWithOptions(request: $_model.ImageRemovalProAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageRemovalProAsyncResponse>;
|
|
1184
1258
|
/**
|
|
1185
|
-
* Removes
|
|
1259
|
+
* Removes text, specific names, transparent text blocks, and promotional watermarks from e-commerce images. This operation automatically identifies and removes these elements or allows you to specify the objects to be removed, enabling efficient and accurate processing of large batches of images and simplifying image editing.
|
|
1186
1260
|
*
|
|
1187
1261
|
* @remarks
|
|
1188
1262
|
* ## Scenarios
|
|
1189
|
-
* * **Efficient
|
|
1263
|
+
* * **Efficient e-commerce image processing:**
|
|
1190
1264
|
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
1191
|
-
* * **
|
|
1192
|
-
* Quickly removes specific text and watermarks when merchants list products on different e-commerce platforms
|
|
1265
|
+
* * **Multi-platform product information synchronization:**
|
|
1266
|
+
* Quickly removes specific text and promotional watermarks when merchants list products on different e-commerce platforms, ensuring compliance with the image specifications of different platforms.
|
|
1193
1267
|
* ## Features
|
|
1194
|
-
* 1. First, understand the definitions of the image subject and the image background. In actual use, when specifying the objects to
|
|
1268
|
+
* 1. First, understand the definitions of the image subject and the image background. In actual use, when specifying the objects to be removed, you can choose to remove objects from the image subject or the image background. Both API and editor integration methods are supported to meet different needs.
|
|
1195
1269
|
*
|
|
1196
1270
|
* 1. Image subject: the core product area in the image.
|
|
1197
1271
|
*
|
|
1198
|
-
* 2. Image background: the rest of the image
|
|
1272
|
+
* 2. Image background: the rest of the image excluding the product subject.
|
|
1199
1273
|
*
|
|
1200
|
-
* 2. Second, the
|
|
1274
|
+
* 2. Second, the objects to be removed can be text, specific names, transparent text blocks, or promotional watermarks. You can refer to the following examples to clarify your requirements and perform targeted operations:
|
|
1201
1275
|
* ## Effect comparison
|
|
1202
1276
|
* | **Original image** | **Processed image** |
|
|
1203
1277
|
* | --- | --- |
|
|
1204
1278
|
* |  |  |
|
|
1205
|
-
* |  |  |
|
|
1206
1280
|
*
|
|
1207
1281
|
* @param request - ImageRemovalProAsyncRequest
|
|
1208
1282
|
* @returns ImageRemovalProAsyncResponse
|
|
@@ -1392,33 +1466,33 @@ export default class Client extends OpenApi {
|
|
|
1392
1466
|
*/
|
|
1393
1467
|
imageRemove(request: $_model.ImageRemoveRequest): Promise<$_model.ImageRemoveResponse>;
|
|
1394
1468
|
/**
|
|
1395
|
-
* Intelligently removes unwanted elements from e-commerce images by automatically identifying and erasing text, specific names, transparent text blocks, and
|
|
1469
|
+
* Intelligently removes unwanted elements from e-commerce images by automatically identifying and erasing text, specific names, transparent text blocks, and intrusive watermarks. It also allows you to specify objects for removal as needed, enabling efficient and accurate processing of large image batches and simplifying image editing workflows.
|
|
1396
1470
|
*
|
|
1397
1471
|
* @remarks
|
|
1398
1472
|
* ## Scenarios
|
|
1399
|
-
* * **Efficient e-commerce
|
|
1473
|
+
* * **Efficient processing of e-commerce images:**
|
|
1400
1474
|
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
1401
1475
|
* * **Multi-platform product information synchronization:**
|
|
1402
|
-
* When merchants
|
|
1476
|
+
* When merchants synchronize product listings across different e-commerce platforms, they can quickly remove specific text and watermarks to comply with the image specifications of different platforms.
|
|
1403
1477
|
* * **Marketing material preparation:**
|
|
1404
1478
|
* Merchants can easily remove original promotional information and quickly update it with the latest campaign information.
|
|
1405
|
-
* > Note: Merchants or platforms can batch remove impurities in images to optimize image quality.
|
|
1479
|
+
* > Note: Merchants or platforms can batch remove impurities in images to optimize image quality. Use this feature in combination with the Intelligent Recognition API (coming soon) to first filter out 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. By calling them in sequence, you can maximize the erasure effect and reduce false removals and false recognitions.
|
|
1406
1480
|
* ## Features
|
|
1407
|
-
* 1. First, clarify the definitions of the image subject and the image background. In actual use, when specifying the objects to
|
|
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 area. Both API and editor integration methods are supported to meet different types of requirements.
|
|
1408
1482
|
*
|
|
1409
1483
|
* 1. Image subject: the core product area in the image.
|
|
1410
1484
|
*
|
|
1411
1485
|
* 2. Image background: the rest of the image other than the product subject.
|
|
1412
1486
|
*
|
|
1413
|
-
* 2. Second, the objects to
|
|
1487
|
+
* 2. Second, the objects to remove support the following three scenarios:
|
|
1414
1488
|
*
|
|
1415
|
-
* 1. The user only
|
|
1489
|
+
* 1. The user selects only the type. You can select text, specific names, transparent text blocks, and watermarks. You can clarify your usage requirements through the following examples for targeted operations.
|
|
1416
1490
|
*
|
|
1417
|
-
* 2. (Upgraded) Provides specified image erasure.
|
|
1491
|
+
* 2. (Upgraded) Provides specified image erasure. You can specify multiple images at a time.
|
|
1418
1492
|
*
|
|
1419
|
-
* 3. (Upgraded) Provides specified text erasure.
|
|
1493
|
+
* 3. (Upgraded) Provides specified text erasure. You can specify multiple text strings at a time.
|
|
1420
1494
|
*
|
|
1421
|
-
* Processing flow: The user passes
|
|
1495
|
+
* Processing flow: The user passes the original image URL → The OCR and VLM models detect the text or image position → Determine the coordinates of the area to be inpainted → AI inpainting generates a clean image → Return the result image URL.
|
|
1422
1496
|
* ## Effect comparison
|
|
1423
1497
|
* | **Objects that can be removed from the image** | **Original image** | **Image after erasure** |
|
|
1424
1498
|
* | --- | --- | --- |
|
|
@@ -1458,7 +1532,7 @@ export default class Client extends OpenApi {
|
|
|
1458
1532
|
* * Does not involve the image subject area
|
|
1459
1533
|
*
|
|
1460
1534
|
*  |
|
|
1461
|
-
* |
|
|
1535
|
+
* | Watermarks | * Involves the image subject area
|
|
1462
1536
|
*
|
|
1463
1537
|
* 
|
|
1464
1538
|
*
|
|
@@ -1479,33 +1553,33 @@ export default class Client extends OpenApi {
|
|
|
1479
1553
|
*/
|
|
1480
1554
|
imageRemoveAsyncWithOptions(tmpReq: $_model.ImageRemoveAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageRemoveAsyncResponse>;
|
|
1481
1555
|
/**
|
|
1482
|
-
* Intelligently removes unwanted elements from e-commerce images by automatically identifying and erasing text, specific names, transparent text blocks, and
|
|
1556
|
+
* Intelligently removes unwanted elements from e-commerce images by automatically identifying and erasing text, specific names, transparent text blocks, and intrusive watermarks. It also allows you to specify objects for removal as needed, enabling efficient and accurate processing of large image batches and simplifying image editing workflows.
|
|
1483
1557
|
*
|
|
1484
1558
|
* @remarks
|
|
1485
1559
|
* ## Scenarios
|
|
1486
|
-
* * **Efficient e-commerce
|
|
1560
|
+
* * **Efficient processing of e-commerce images:**
|
|
1487
1561
|
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
1488
1562
|
* * **Multi-platform product information synchronization:**
|
|
1489
|
-
* When merchants
|
|
1563
|
+
* When merchants synchronize product listings across different e-commerce platforms, they can quickly remove specific text and watermarks to comply with the image specifications of different platforms.
|
|
1490
1564
|
* * **Marketing material preparation:**
|
|
1491
1565
|
* Merchants can easily remove original promotional information and quickly update it with the latest campaign information.
|
|
1492
|
-
* > Note: Merchants or platforms can batch remove impurities in images to optimize image quality.
|
|
1566
|
+
* > Note: Merchants or platforms can batch remove impurities in images to optimize image quality. Use this feature in combination with the Intelligent Recognition API (coming soon) to first filter out 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. By calling them in sequence, you can maximize the erasure effect and reduce false removals and false recognitions.
|
|
1493
1567
|
* ## Features
|
|
1494
|
-
* 1. First, clarify the definitions of the image subject and the image background. In actual use, when specifying the objects to
|
|
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 area. Both API and editor integration methods are supported to meet different types of requirements.
|
|
1495
1569
|
*
|
|
1496
1570
|
* 1. Image subject: the core product area in the image.
|
|
1497
1571
|
*
|
|
1498
1572
|
* 2. Image background: the rest of the image other than the product subject.
|
|
1499
1573
|
*
|
|
1500
|
-
* 2. Second, the objects to
|
|
1574
|
+
* 2. Second, the objects to remove support the following three scenarios:
|
|
1501
1575
|
*
|
|
1502
|
-
* 1. The user only
|
|
1576
|
+
* 1. The user selects only the type. You can select text, specific names, transparent text blocks, and watermarks. You can clarify your usage requirements through the following examples for targeted operations.
|
|
1503
1577
|
*
|
|
1504
|
-
* 2. (Upgraded) Provides specified image erasure.
|
|
1578
|
+
* 2. (Upgraded) Provides specified image erasure. You can specify multiple images at a time.
|
|
1505
1579
|
*
|
|
1506
|
-
* 3. (Upgraded) Provides specified text erasure.
|
|
1580
|
+
* 3. (Upgraded) Provides specified text erasure. You can specify multiple text strings at a time.
|
|
1507
1581
|
*
|
|
1508
|
-
* Processing flow: The user passes
|
|
1582
|
+
* Processing flow: The user passes the original image URL → The OCR and VLM models detect the text or image position → Determine the coordinates of the area to be inpainted → AI inpainting generates a clean image → Return the result image URL.
|
|
1509
1583
|
* ## Effect comparison
|
|
1510
1584
|
* | **Objects that can be removed from the image** | **Original image** | **Image after erasure** |
|
|
1511
1585
|
* | --- | --- | --- |
|
|
@@ -1545,7 +1619,7 @@ export default class Client extends OpenApi {
|
|
|
1545
1619
|
* * Does not involve the image subject area
|
|
1546
1620
|
*
|
|
1547
1621
|
*  |
|
|
1548
|
-
* |
|
|
1622
|
+
* | Watermarks | * Involves the image subject area
|
|
1549
1623
|
*
|
|
1550
1624
|
* 
|
|
1551
1625
|
*
|
|
@@ -1565,11 +1639,11 @@ export default class Client extends OpenApi {
|
|
|
1565
1639
|
*/
|
|
1566
1640
|
imageRemoveAsync(request: $_model.ImageRemoveAsyncRequest): Promise<$_model.ImageRemoveAsyncResponse>;
|
|
1567
1641
|
/**
|
|
1568
|
-
*
|
|
1642
|
+
* Translates e-commerce images by using the PLUS edition of the image translation service. Built on the Mixture of Experts (MOE) architecture, this edition delivers higher translation accuracy for multiple minor languages than the Lite and Pro editions. It is recommended for the following 12 language pairs, with more to be added in the future.
|
|
1569
1643
|
*
|
|
1570
1644
|
* @remarks
|
|
1571
|
-
* ## Product
|
|
1572
|
-
*
|
|
1645
|
+
* ## Product introduction
|
|
1646
|
+
* The PLUS edition of the image translation service is designed specifically for e-commerce images. Built on the Mixture of Experts (MOE) architecture, it delivers higher translation accuracy for multiple minor languages than the Lite and Pro editions. We recommend that you use this edition for the following 12 language pairs. More language pairs will be supported in the future.
|
|
1573
1647
|
* Supported language pairs:
|
|
1574
1648
|
* | **No.** | **Source language** | | **Target language** | |
|
|
1575
1649
|
* | --- | --- | --- | --- | --- |
|
|
@@ -1587,13 +1661,13 @@ export default class Client extends OpenApi {
|
|
|
1587
1661
|
* | 11 | en | English | de | German |
|
|
1588
1662
|
* | 12 | en | English | pl | Polish |
|
|
1589
1663
|
* ## Scenarios
|
|
1590
|
-
* Main
|
|
1664
|
+
* Main images and detail images for cross-border e-commerce.
|
|
1591
1665
|
* ## Features
|
|
1592
|
-
* * **Product
|
|
1666
|
+
* * **Product subject information protection**: Allows you to specify whether to translate the text on the product subject. This helps protect the subject information, such as the embedded product name, from being translated.
|
|
1593
1667
|
*
|
|
1594
|
-
* * **Brand name protection**: Allows you to
|
|
1668
|
+
* * **Brand name protection**: Allows you to specify whether to translate the brand name in the image. This helps protect the brand name from being translated.
|
|
1595
1669
|
*
|
|
1596
|
-
* * **Translation intervention**: Allows you to customize translation results, including keeping text
|
|
1670
|
+
* * **Translation intervention**: Allows you to customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), or leaving it untranslated (ABC-null). This is commonly used for 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.
|
|
1597
1671
|
*
|
|
1598
1672
|
* @param request - ImageTranslationPlusRequest
|
|
1599
1673
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -1601,11 +1675,11 @@ export default class Client extends OpenApi {
|
|
|
1601
1675
|
*/
|
|
1602
1676
|
imageTranslationPlusWithOptions(request: $_model.ImageTranslationPlusRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageTranslationPlusResponse>;
|
|
1603
1677
|
/**
|
|
1604
|
-
*
|
|
1678
|
+
* Translates e-commerce images by using the PLUS edition of the image translation service. Built on the Mixture of Experts (MOE) architecture, this edition delivers higher translation accuracy for multiple minor languages than the Lite and Pro editions. It is recommended for the following 12 language pairs, with more to be added in the future.
|
|
1605
1679
|
*
|
|
1606
1680
|
* @remarks
|
|
1607
|
-
* ## Product
|
|
1608
|
-
*
|
|
1681
|
+
* ## Product introduction
|
|
1682
|
+
* The PLUS edition of the image translation service is designed specifically for e-commerce images. Built on the Mixture of Experts (MOE) architecture, it delivers higher translation accuracy for multiple minor languages than the Lite and Pro editions. We recommend that you use this edition for the following 12 language pairs. More language pairs will be supported in the future.
|
|
1609
1683
|
* Supported language pairs:
|
|
1610
1684
|
* | **No.** | **Source language** | | **Target language** | |
|
|
1611
1685
|
* | --- | --- | --- | --- | --- |
|
|
@@ -1623,30 +1697,30 @@ export default class Client extends OpenApi {
|
|
|
1623
1697
|
* | 11 | en | English | de | German |
|
|
1624
1698
|
* | 12 | en | English | pl | Polish |
|
|
1625
1699
|
* ## Scenarios
|
|
1626
|
-
* Main
|
|
1700
|
+
* Main images and detail images for cross-border e-commerce.
|
|
1627
1701
|
* ## Features
|
|
1628
|
-
* * **Product
|
|
1702
|
+
* * **Product subject information protection**: Allows you to specify whether to translate the text on the product subject. This helps protect the subject information, such as the embedded product name, from being translated.
|
|
1629
1703
|
*
|
|
1630
|
-
* * **Brand name protection**: Allows you to
|
|
1704
|
+
* * **Brand name protection**: Allows you to specify whether to translate the brand name in the image. This helps protect the brand name from being translated.
|
|
1631
1705
|
*
|
|
1632
|
-
* * **Translation intervention**: Allows you to customize translation results, including keeping text
|
|
1706
|
+
* * **Translation intervention**: Allows you to customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), or leaving it untranslated (ABC-null). This is commonly used for 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.
|
|
1633
1707
|
*
|
|
1634
1708
|
* @param request - ImageTranslationPlusRequest
|
|
1635
1709
|
* @returns ImageTranslationPlusResponse
|
|
1636
1710
|
*/
|
|
1637
1711
|
imageTranslationPlus(request: $_model.ImageTranslationPlusRequest): Promise<$_model.ImageTranslationPlusResponse>;
|
|
1638
1712
|
/**
|
|
1639
|
-
*
|
|
1713
|
+
* Image Translation Plus is designed specifically for e-commerce images. It adopts the Mixture of Experts (MoE) architecture and outperforms Image Translation Lite and Pro in translation accuracy for multiple minor languages.
|
|
1640
1714
|
*
|
|
1641
1715
|
* @remarks
|
|
1642
1716
|
* ## Scenarios
|
|
1643
1717
|
* Main images and detail images for cross-border e-commerce.
|
|
1644
1718
|
* ## Features
|
|
1645
|
-
* * **Product subject information protection**:
|
|
1719
|
+
* * **Product subject information protection**: You can choose whether to translate the text on the product subject. This helps you protect the subject information from being translated, such as embedded information like product names.
|
|
1646
1720
|
*
|
|
1647
|
-
* * **Brand name protection**:
|
|
1721
|
+
* * **Brand name protection**: You can choose whether to translate the brand names in the image. This helps you protect brand name information from being translated.
|
|
1648
1722
|
*
|
|
1649
|
-
* * **Translation intervention**:
|
|
1723
|
+
* * **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 achieve 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.
|
|
1650
1724
|
* ## Supported language pairs
|
|
1651
1725
|
* | **No.** | **Source language** | | **Target language** | |
|
|
1652
1726
|
* | --- | --- | --- | --- | --- |
|
|
@@ -1664,8 +1738,8 @@ export default class Client extends OpenApi {
|
|
|
1664
1738
|
* | 11 | en | English | de | German |
|
|
1665
1739
|
* | 12 | en | English | pl | Polish |
|
|
1666
1740
|
* ## Preparations and call process
|
|
1667
|
-
*
|
|
1668
|
-
* For the integration process
|
|
1741
|
+
* Image Translation Plus and other asynchronous APIs share the same result retrieval process, RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
1742
|
+
* 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).
|
|
1669
1743
|
*
|
|
1670
1744
|
* @param request - ImageTranslationPlusAsyncRequest
|
|
1671
1745
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -1673,17 +1747,17 @@ export default class Client extends OpenApi {
|
|
|
1673
1747
|
*/
|
|
1674
1748
|
imageTranslationPlusAsyncWithOptions(request: $_model.ImageTranslationPlusAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageTranslationPlusAsyncResponse>;
|
|
1675
1749
|
/**
|
|
1676
|
-
*
|
|
1750
|
+
* Image Translation Plus is designed specifically for e-commerce images. It adopts the Mixture of Experts (MoE) architecture and outperforms Image Translation Lite and Pro in translation accuracy for multiple minor languages.
|
|
1677
1751
|
*
|
|
1678
1752
|
* @remarks
|
|
1679
1753
|
* ## Scenarios
|
|
1680
1754
|
* Main images and detail images for cross-border e-commerce.
|
|
1681
1755
|
* ## Features
|
|
1682
|
-
* * **Product subject information protection**:
|
|
1756
|
+
* * **Product subject information protection**: You can choose whether to translate the text on the product subject. This helps you protect the subject information from being translated, such as embedded information like product names.
|
|
1683
1757
|
*
|
|
1684
|
-
* * **Brand name protection**:
|
|
1758
|
+
* * **Brand name protection**: You can choose whether to translate the brand names in the image. This helps you protect brand name information from being translated.
|
|
1685
1759
|
*
|
|
1686
|
-
* * **Translation intervention**:
|
|
1760
|
+
* * **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 achieve 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.
|
|
1687
1761
|
* ## Supported language pairs
|
|
1688
1762
|
* | **No.** | **Source language** | | **Target language** | |
|
|
1689
1763
|
* | --- | --- | --- | --- | --- |
|
|
@@ -1701,27 +1775,27 @@ export default class Client extends OpenApi {
|
|
|
1701
1775
|
* | 11 | en | English | de | German |
|
|
1702
1776
|
* | 12 | en | English | pl | Polish |
|
|
1703
1777
|
* ## Preparations and call process
|
|
1704
|
-
*
|
|
1705
|
-
* For the integration process
|
|
1778
|
+
* Image Translation Plus and other asynchronous APIs share the same result retrieval process, RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
1779
|
+
* 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).
|
|
1706
1780
|
*
|
|
1707
1781
|
* @param request - ImageTranslationPlusAsyncRequest
|
|
1708
1782
|
* @returns ImageTranslationPlusAsyncResponse
|
|
1709
1783
|
*/
|
|
1710
1784
|
imageTranslationPlusAsync(request: $_model.ImageTranslationPlusAsyncRequest): Promise<$_model.ImageTranslationPlusAsyncResponse>;
|
|
1711
1785
|
/**
|
|
1712
|
-
* Translates images using the Pro edition
|
|
1786
|
+
* Translates e-commerce images by using the Pro edition of the image translation service. Integrates multimodal large models to achieve more accurate image understanding, significantly improves translation quality, and continuously expands and optimizes multilingual translation capabilities. Supports over 400 language pairs, including bridged languages.
|
|
1713
1787
|
*
|
|
1714
1788
|
* @remarks
|
|
1715
|
-
* ## Product
|
|
1716
|
-
* The
|
|
1789
|
+
* ## Product introduction
|
|
1790
|
+
* The Pro edition of the image translation service is designed specifically for e-commerce images. It integrates multimodal large models to achieve more accurate image understanding, significantly improves translation quality, and continuously expands and optimizes multilingual translation capabilities. It supports over 400 language pairs, including bridged languages.
|
|
1717
1791
|
* ## Scenarios
|
|
1718
|
-
* E-commerce product images, marketing images, and images
|
|
1719
|
-
* ##
|
|
1720
|
-
* - **Product subject information protection**:
|
|
1721
|
-
* - **
|
|
1722
|
-
* - **Brand name protection**:
|
|
1723
|
-
* - **Translation intervention**:
|
|
1724
|
-
* - <props="china"> **Image editor integration**: For
|
|
1792
|
+
* E-commerce product images, marketing images, and images in various other scenarios.
|
|
1793
|
+
* ## Features
|
|
1794
|
+
* - **Product subject information protection**: Allows you to specify whether to translate text on the product subject. This helps you protect subject information and prevents embedded information such as product names from being translated.
|
|
1795
|
+
* - **Secondary editing after translation**: Allows you to specify whether to return layout information such as text position, font, and color. 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.
|
|
1796
|
+
* - **Brand name protection**: Allows you to specify whether to translate brand names in images. This helps you protect brand name information from being translated.
|
|
1797
|
+
* - **Translation intervention**: Allows you to customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), and omitting the translation (ABC-null). This is commonly used for scenarios such as brand word protection. You only need to pass the corresponding intervention glossary ID when calling the API to meet your translation needs in different scenarios. You can upload up to 100,000 intervention words. If you need a higher quota, contact the platform.
|
|
1798
|
+
* - <props="china"> **Image editor integration**: For details, see [Image translation editor protocol](https://www.alibabacloud.com/help/en/document_detail/3042647.html).
|
|
1725
1799
|
*
|
|
1726
1800
|
* @param request - ImageTranslationProRequest
|
|
1727
1801
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -1729,42 +1803,42 @@ export default class Client extends OpenApi {
|
|
|
1729
1803
|
*/
|
|
1730
1804
|
imageTranslationProWithOptions(request: $_model.ImageTranslationProRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageTranslationProResponse>;
|
|
1731
1805
|
/**
|
|
1732
|
-
* Translates images using the Pro edition
|
|
1806
|
+
* Translates e-commerce images by using the Pro edition of the image translation service. Integrates multimodal large models to achieve more accurate image understanding, significantly improves translation quality, and continuously expands and optimizes multilingual translation capabilities. Supports over 400 language pairs, including bridged languages.
|
|
1733
1807
|
*
|
|
1734
1808
|
* @remarks
|
|
1735
|
-
* ## Product
|
|
1736
|
-
* The
|
|
1809
|
+
* ## Product introduction
|
|
1810
|
+
* The Pro edition of the image translation service is designed specifically for e-commerce images. It integrates multimodal large models to achieve more accurate image understanding, significantly improves translation quality, and continuously expands and optimizes multilingual translation capabilities. It supports over 400 language pairs, including bridged languages.
|
|
1737
1811
|
* ## Scenarios
|
|
1738
|
-
* E-commerce product images, marketing images, and images
|
|
1739
|
-
* ##
|
|
1740
|
-
* - **Product subject information protection**:
|
|
1741
|
-
* - **
|
|
1742
|
-
* - **Brand name protection**:
|
|
1743
|
-
* - **Translation intervention**:
|
|
1744
|
-
* - <props="china"> **Image editor integration**: For
|
|
1812
|
+
* E-commerce product images, marketing images, and images in various other scenarios.
|
|
1813
|
+
* ## Features
|
|
1814
|
+
* - **Product subject information protection**: Allows you to specify whether to translate text on the product subject. This helps you protect subject information and prevents embedded information such as product names from being translated.
|
|
1815
|
+
* - **Secondary editing after translation**: Allows you to specify whether to return layout information such as text position, font, and color. 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.
|
|
1816
|
+
* - **Brand name protection**: Allows you to specify whether to translate brand names in images. This helps you protect brand name information from being translated.
|
|
1817
|
+
* - **Translation intervention**: Allows you to customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), and omitting the translation (ABC-null). This is commonly used for scenarios such as brand word protection. You only need to pass the corresponding intervention glossary ID when calling the API to meet your translation needs in different scenarios. You can upload up to 100,000 intervention words. If you need a higher quota, contact the platform.
|
|
1818
|
+
* - <props="china"> **Image editor integration**: For details, see [Image translation editor protocol](https://www.alibabacloud.com/help/en/document_detail/3042647.html).
|
|
1745
1819
|
*
|
|
1746
1820
|
* @param request - ImageTranslationProRequest
|
|
1747
1821
|
* @returns ImageTranslationProResponse
|
|
1748
1822
|
*/
|
|
1749
1823
|
imageTranslationPro(request: $_model.ImageTranslationProRequest): Promise<$_model.ImageTranslationProResponse>;
|
|
1750
1824
|
/**
|
|
1751
|
-
* Translates images
|
|
1825
|
+
* Translates images by using Image Translation Pro, which is designed specifically 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. It supports more than 400 language pairs, including bridged languages.
|
|
1752
1826
|
*
|
|
1753
1827
|
* @remarks
|
|
1754
1828
|
* ## Scenarios
|
|
1755
|
-
* E-commerce product images, marketing images, and images
|
|
1829
|
+
* E-commerce product images, marketing images, and images for various other scenarios.
|
|
1756
1830
|
* ## Features
|
|
1757
|
-
* * 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
|
|
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.
|
|
1758
1832
|
*
|
|
1759
1833
|
* * 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.
|
|
1760
1834
|
*
|
|
1761
1835
|
* * Brand name protection: You can specify whether to translate brand names in the image. This helps you protect brand name information from being translated.
|
|
1762
1836
|
*
|
|
1763
|
-
* * 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
|
|
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 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, which meets 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.
|
|
1764
1838
|
* ## Preparations and call process
|
|
1765
|
-
* Image Translation Pro supports both synchronous and asynchronous
|
|
1766
|
-
* The 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.
|
|
1767
|
-
* For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls,
|
|
1839
|
+
* 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
|
+
* The asynchronous APIs for text translation and other capabilities share the same result retrieval process, ApsaraMQ for RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
1841
|
+
* 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).
|
|
1768
1842
|
*
|
|
1769
1843
|
* @param request - ImageTranslationProAsyncRequest
|
|
1770
1844
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -1772,45 +1846,45 @@ export default class Client extends OpenApi {
|
|
|
1772
1846
|
*/
|
|
1773
1847
|
imageTranslationProAsyncWithOptions(request: $_model.ImageTranslationProAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageTranslationProAsyncResponse>;
|
|
1774
1848
|
/**
|
|
1775
|
-
* Translates images
|
|
1849
|
+
* Translates images by using Image Translation Pro, which is designed specifically 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. It supports more than 400 language pairs, including bridged languages.
|
|
1776
1850
|
*
|
|
1777
1851
|
* @remarks
|
|
1778
1852
|
* ## Scenarios
|
|
1779
|
-
* E-commerce product images, marketing images, and images
|
|
1853
|
+
* E-commerce product images, marketing images, and images for various other scenarios.
|
|
1780
1854
|
* ## Features
|
|
1781
|
-
* * 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
|
|
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.
|
|
1782
1856
|
*
|
|
1783
1857
|
* * 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.
|
|
1784
1858
|
*
|
|
1785
1859
|
* * Brand name protection: You can specify whether to translate brand names in the image. This helps you protect brand name information from being translated.
|
|
1786
1860
|
*
|
|
1787
|
-
* * 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
|
|
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 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, which meets 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.
|
|
1788
1862
|
* ## Preparations and call process
|
|
1789
|
-
* Image Translation Pro supports both synchronous and asynchronous
|
|
1790
|
-
* The 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.
|
|
1791
|
-
* For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls,
|
|
1863
|
+
* 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
|
+
* The asynchronous APIs for text translation and other capabilities share the same result retrieval process, ApsaraMQ for RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
1865
|
+
* 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).
|
|
1792
1866
|
*
|
|
1793
1867
|
* @param request - ImageTranslationProAsyncRequest
|
|
1794
1868
|
* @returns ImageTranslationProAsyncResponse
|
|
1795
1869
|
*/
|
|
1796
1870
|
imageTranslationProAsync(request: $_model.ImageTranslationProAsyncRequest): Promise<$_model.ImageTranslationProAsyncResponse>;
|
|
1797
1871
|
/**
|
|
1798
|
-
* Translates
|
|
1872
|
+
* Translates e-commerce images and supports over 400 language pairs, including bridged languages. Accurately processes complex text layouts within images and ensures that the translated content matches the image context, helping e-commerce platforms and developers easily achieve multilingual conversion and presentation of image content. Additionally, returns layer information such as the position, font, and color of text in the image to facilitate secondary editing of translation results in image editors.
|
|
1799
1873
|
*
|
|
1800
1874
|
* @remarks
|
|
1801
1875
|
* # 1. Product Introduction
|
|
1802
|
-
* The image translation product is
|
|
1803
|
-
* # 2.
|
|
1876
|
+
* 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 matches the image context, helping e-commerce platforms and developers easily achieve multilingual conversion and presentation. Additionally, the product returns layer information such as text position, font, and color, facilitating integration with image editors for secondary editing.
|
|
1877
|
+
* # 2. Scenarios
|
|
1804
1878
|
* E-commerce product images, marketing images, and images for various other scenarios.
|
|
1805
1879
|
* # 3. Features
|
|
1806
|
-
* * **Product subject information protection**: Allows you to
|
|
1880
|
+
* * **Product subject information protection**: Allows you to specify whether to translate text on the product subject, protecting subject information such as embedded product names from being translated.
|
|
1807
1881
|
*
|
|
1808
|
-
* * **Brand name protection**: Allows you to
|
|
1882
|
+
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image, protecting brand name information from being translated.
|
|
1809
1883
|
*
|
|
1810
|
-
* * **Secondary editing after translation (layer information)**: Allows you to
|
|
1884
|
+
* * **Secondary editing after translation (layer information)**: Allows you to specify 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 availability of the editor SDK, refer to platform notifications.
|
|
1811
1885
|
*
|
|
1812
|
-
* * **Translation intervention
|
|
1813
|
-
* <props="china">* **Image editor integration
|
|
1886
|
+
* * **Translation intervention**: Allows you to customize translation results, including no translation (ABC-ABC), specified translation (ABC-DEF), and skipping translation (ABC-null value). This is commonly used for scenarios such as brand word protection. You can implement 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 words. If you need more, contact the platform for assistance.
|
|
1887
|
+
* <props="china">* **Image editor integration**: For more information, see [Image Translation Editor Protocol](https://www.alibabacloud.com/help/en/document_detail/3042647.html).
|
|
1814
1888
|
*
|
|
1815
1889
|
* @param request - ImageTranslationStandardRequest
|
|
1816
1890
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -1818,45 +1892,45 @@ export default class Client extends OpenApi {
|
|
|
1818
1892
|
*/
|
|
1819
1893
|
imageTranslationStandardWithOptions(request: $_model.ImageTranslationStandardRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageTranslationStandardResponse>;
|
|
1820
1894
|
/**
|
|
1821
|
-
* Translates
|
|
1895
|
+
* Translates e-commerce images and supports over 400 language pairs, including bridged languages. Accurately processes complex text layouts within images and ensures that the translated content matches the image context, helping e-commerce platforms and developers easily achieve multilingual conversion and presentation of image content. Additionally, returns layer information such as the position, font, and color of text in the image to facilitate secondary editing of translation results in image editors.
|
|
1822
1896
|
*
|
|
1823
1897
|
* @remarks
|
|
1824
1898
|
* # 1. Product Introduction
|
|
1825
|
-
* The image translation product is
|
|
1826
|
-
* # 2.
|
|
1899
|
+
* 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 matches the image context, helping e-commerce platforms and developers easily achieve multilingual conversion and presentation. Additionally, the product returns layer information such as text position, font, and color, facilitating integration with image editors for secondary editing.
|
|
1900
|
+
* # 2. Scenarios
|
|
1827
1901
|
* E-commerce product images, marketing images, and images for various other scenarios.
|
|
1828
1902
|
* # 3. Features
|
|
1829
|
-
* * **Product subject information protection**: Allows you to
|
|
1903
|
+
* * **Product subject information protection**: Allows you to specify whether to translate text on the product subject, protecting subject information such as embedded product names from being translated.
|
|
1830
1904
|
*
|
|
1831
|
-
* * **Brand name protection**: Allows you to
|
|
1905
|
+
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image, protecting brand name information from being translated.
|
|
1832
1906
|
*
|
|
1833
|
-
* * **Secondary editing after translation (layer information)**: Allows you to
|
|
1907
|
+
* * **Secondary editing after translation (layer information)**: Allows you to specify 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 availability of the editor SDK, refer to platform notifications.
|
|
1834
1908
|
*
|
|
1835
|
-
* * **Translation intervention
|
|
1836
|
-
* <props="china">* **Image editor integration
|
|
1909
|
+
* * **Translation intervention**: Allows you to customize translation results, including no translation (ABC-ABC), specified translation (ABC-DEF), and skipping translation (ABC-null value). This is commonly used for scenarios such as brand word protection. You can implement 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 words. If you need more, contact the platform for assistance.
|
|
1910
|
+
* <props="china">* **Image editor integration**: For more information, see [Image Translation Editor Protocol](https://www.alibabacloud.com/help/en/document_detail/3042647.html).
|
|
1837
1911
|
*
|
|
1838
1912
|
* @param request - ImageTranslationStandardRequest
|
|
1839
1913
|
* @returns ImageTranslationStandardResponse
|
|
1840
1914
|
*/
|
|
1841
1915
|
imageTranslationStandard(request: $_model.ImageTranslationStandardRequest): Promise<$_model.ImageTranslationStandardResponse>;
|
|
1842
1916
|
/**
|
|
1843
|
-
* Translates images
|
|
1917
|
+
* Translates images tailored for e-commerce scenarios, supporting over 400 language directions (including bridged languages), accurately processing complex text layouts within images, and ensuring translated content matches the image context to help e-commerce platforms and developers easily achieve multilingual conversion and presentation of image content. It also returns layer information such as text position, font, and color to facilitate secondary editing of translation results in image editors.
|
|
1844
1918
|
*
|
|
1845
1919
|
* @remarks
|
|
1846
1920
|
* ## Scenarios
|
|
1847
1921
|
* E-commerce product images, marketing images, and images for various other scenarios.
|
|
1848
1922
|
* ## Features
|
|
1849
|
-
* * **Product subject information protection**: Allows you to specify whether to translate
|
|
1923
|
+
* * **Product subject information protection**: Allows you to specify whether to translate text on the product subject. This protects the subject information from being translated and prevents embedded information such as product names from being translated.
|
|
1850
1924
|
*
|
|
1851
|
-
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image. This
|
|
1925
|
+
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image. This protects brand name information from being translated.
|
|
1852
1926
|
*
|
|
1853
|
-
* * **Secondary editing after translation (layer information)**: Allows you to specify whether to return layer information such as
|
|
1927
|
+
* * **Secondary editing after translation (layer information)**: Allows you to specify 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 translation results. For updates on the availability of the editor SDK, refer to platform notifications.
|
|
1854
1928
|
*
|
|
1855
|
-
* * **Translation intervention**: Allows you to customize translation results, including keeping
|
|
1929
|
+
* * **Translation intervention**: Allows you to customize translation results, including keeping text untranslated (ABC-ABC), specifying translations (ABC-DEF), and omitting translations (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, which meets 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.
|
|
1856
1930
|
* ## Preparations and call process
|
|
1857
|
-
* *
|
|
1858
|
-
* * The asynchronous
|
|
1859
|
-
* * For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls, refer to [Asynchronous API
|
|
1931
|
+
* * Image Translation Standard Edition supports both synchronous and asynchronous calls. This topic describes the asynchronous call API. For synchronous calls, refer to [Image Translation Standard Edition](https://www.alibabacloud.com/help/en/aidge/image-translation).
|
|
1932
|
+
* * The asynchronous APIs for Image Translation Standard Edition and other features share the result retrieval process, ApsaraMQ for RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
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).
|
|
1860
1934
|
*
|
|
1861
1935
|
* @param request - ImageTranslationStandardAsyncRequest
|
|
1862
1936
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -1864,28 +1938,83 @@ export default class Client extends OpenApi {
|
|
|
1864
1938
|
*/
|
|
1865
1939
|
imageTranslationStandardAsyncWithOptions(request: $_model.ImageTranslationStandardAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageTranslationStandardAsyncResponse>;
|
|
1866
1940
|
/**
|
|
1867
|
-
* Translates images
|
|
1941
|
+
* Translates images tailored for e-commerce scenarios, supporting over 400 language directions (including bridged languages), accurately processing complex text layouts within images, and ensuring translated content matches the image context to help e-commerce platforms and developers easily achieve multilingual conversion and presentation of image content. It also returns layer information such as text position, font, and color to facilitate secondary editing of translation results in image editors.
|
|
1868
1942
|
*
|
|
1869
1943
|
* @remarks
|
|
1870
1944
|
* ## Scenarios
|
|
1871
1945
|
* E-commerce product images, marketing images, and images for various other scenarios.
|
|
1872
1946
|
* ## Features
|
|
1873
|
-
* * **Product subject information protection**: Allows you to specify whether to translate
|
|
1947
|
+
* * **Product subject information protection**: Allows you to specify whether to translate text on the product subject. This protects the subject information from being translated and prevents embedded information such as product names from being translated.
|
|
1874
1948
|
*
|
|
1875
|
-
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image. This
|
|
1949
|
+
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image. This protects brand name information from being translated.
|
|
1876
1950
|
*
|
|
1877
|
-
* * **Secondary editing after translation (layer information)**: Allows you to specify whether to return layer information such as
|
|
1951
|
+
* * **Secondary editing after translation (layer information)**: Allows you to specify 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 translation results. For updates on the availability of the editor SDK, refer to platform notifications.
|
|
1878
1952
|
*
|
|
1879
|
-
* * **Translation intervention**: Allows you to customize translation results, including keeping
|
|
1953
|
+
* * **Translation intervention**: Allows you to customize translation results, including keeping text untranslated (ABC-ABC), specifying translations (ABC-DEF), and omitting translations (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, which meets 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.
|
|
1880
1954
|
* ## Preparations and call process
|
|
1881
|
-
* *
|
|
1882
|
-
* * The asynchronous
|
|
1883
|
-
* * For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls, refer to [Asynchronous API
|
|
1955
|
+
* * Image Translation Standard Edition supports both synchronous and asynchronous calls. This topic describes the asynchronous call API. For synchronous calls, refer to [Image Translation Standard Edition](https://www.alibabacloud.com/help/en/aidge/image-translation).
|
|
1956
|
+
* * The asynchronous APIs for Image Translation Standard Edition and other features share the result retrieval process, ApsaraMQ for RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
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).
|
|
1884
1958
|
*
|
|
1885
1959
|
* @param request - ImageTranslationStandardAsyncRequest
|
|
1886
1960
|
* @returns ImageTranslationStandardAsyncResponse
|
|
1887
1961
|
*/
|
|
1888
1962
|
imageTranslationStandardAsync(request: $_model.ImageTranslationStandardAsyncRequest): Promise<$_model.ImageTranslationStandardAsyncResponse>;
|
|
1963
|
+
/**
|
|
1964
|
+
* Synchronously upscales e-commerce images to intelligently enhance resolution and details by improving textures and optimizing image quality. Supports high-definition outputs such as 2K and 4K to meet the requirements for main product images, detail images, and marketing materials, enabling efficient processing of large image batches to improve overall product image quality.
|
|
1965
|
+
*
|
|
1966
|
+
* @remarks
|
|
1967
|
+
* # Product introduction
|
|
1968
|
+
* The high-definition upscaling product is tailored for e-commerce images. It intelligently enhances image resolution and details, improves textures and image quality during upscaling, and supports high-definition outputs such as 2K and 4K. It meets the high-definition 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)
|
|
1969
|
+
* # 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 and improve product display quality.
|
|
1971
|
+
*
|
|
1972
|
+
* * Multi-platform product material adaptation: Upscales existing product images in high definition to meet the image display requirements of different e-commerce platforms and adapt to multi-platform and multi-scenario material usage needs.
|
|
1973
|
+
*
|
|
1974
|
+
* * Batch optimization of existing images: Enhances existing low-resolution product images in high definition to reduce reshooting and production costs and improve the reuse efficiency of image materials.
|
|
1975
|
+
* # Features
|
|
1976
|
+
* 1. Intelligent high-definition upscaling: Uses AI-based image enhancement technology to improve the resolution and optimize the details of input images, enhancing image clarity and texture representation.
|
|
1977
|
+
*
|
|
1978
|
+
* 2. Multiple upscaling factors: Supports 2x and 4x upscaling factors. You can flexibly select the factor based on image quality and business requirements.
|
|
1979
|
+
*
|
|
1980
|
+
* 3. Synchronous API calls: Supports synchronous submission of images and retrieval of processing results through API calls, facilitating integration into e-commerce image processing workflows.
|
|
1981
|
+
* # Effect comparison
|
|
1982
|
+
* | **Original image** | **Upscaled image** |
|
|
1983
|
+
* | --- | --- |
|
|
1984
|
+
* |  |  |
|
|
1985
|
+
*
|
|
1986
|
+
* @param request - ImageUpscaleRequest
|
|
1987
|
+
* @param runtime - runtime options for this request RuntimeOptions
|
|
1988
|
+
* @returns ImageUpscaleResponse
|
|
1989
|
+
*/
|
|
1990
|
+
imageUpscaleWithOptions(request: $_model.ImageUpscaleRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageUpscaleResponse>;
|
|
1991
|
+
/**
|
|
1992
|
+
* Synchronously upscales e-commerce images to intelligently enhance resolution and details by improving textures and optimizing image quality. Supports high-definition outputs such as 2K and 4K to meet the requirements for main product images, detail images, and marketing materials, enabling efficient processing of large image batches to improve overall product image quality.
|
|
1993
|
+
*
|
|
1994
|
+
* @remarks
|
|
1995
|
+
* # Product introduction
|
|
1996
|
+
* The high-definition upscaling product is tailored for e-commerce images. It intelligently enhances image resolution and details, improves textures and image quality during upscaling, and supports high-definition outputs such as 2K and 4K. It meets the high-definition 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)
|
|
1997
|
+
* # Scenarios
|
|
1998
|
+
* * 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 and improve product display quality.
|
|
1999
|
+
*
|
|
2000
|
+
* * Multi-platform product material adaptation: Upscales existing product images in high definition to meet the image display requirements of different e-commerce platforms and adapt to multi-platform and multi-scenario material usage needs.
|
|
2001
|
+
*
|
|
2002
|
+
* * Batch optimization of existing images: Enhances existing low-resolution product images in high definition to reduce reshooting and production costs and improve the reuse efficiency of image materials.
|
|
2003
|
+
* # Features
|
|
2004
|
+
* 1. Intelligent high-definition upscaling: Uses AI-based image enhancement technology to improve the resolution and optimize the details of input images, enhancing image clarity and texture representation.
|
|
2005
|
+
*
|
|
2006
|
+
* 2. Multiple upscaling factors: Supports 2x and 4x upscaling factors. You can flexibly select the factor based on image quality and business requirements.
|
|
2007
|
+
*
|
|
2008
|
+
* 3. Synchronous API calls: Supports synchronous submission of images and retrieval of processing results through API calls, facilitating integration into e-commerce image processing workflows.
|
|
2009
|
+
* # Effect comparison
|
|
2010
|
+
* | **Original image** | **Upscaled image** |
|
|
2011
|
+
* | --- | --- |
|
|
2012
|
+
* |  |  |
|
|
2013
|
+
*
|
|
2014
|
+
* @param request - ImageUpscaleRequest
|
|
2015
|
+
* @returns ImageUpscaleResponse
|
|
2016
|
+
*/
|
|
2017
|
+
imageUpscale(request: $_model.ImageUpscaleRequest): Promise<$_model.ImageUpscaleResponse>;
|
|
1889
2018
|
/**
|
|
1890
2019
|
* Supports automatic language identification for 31 languages in query scenarios and 35 languages in general scenarios. Applicable to short text such as search terms, titles, and conversations.
|
|
1891
2020
|
*
|
|
@@ -2417,7 +2546,7 @@ export default class Client extends OpenApi {
|
|
|
2417
2546
|
*/
|
|
2418
2547
|
queryAsyncTaskResult(request: $_model.QueryAsyncTaskResultRequest): Promise<$_model.QueryAsyncTaskResultResponse>;
|
|
2419
2548
|
/**
|
|
2420
|
-
*
|
|
2549
|
+
* Queries the display knowledge base content by using a paged query with paging (synchronization).
|
|
2421
2550
|
*
|
|
2422
2551
|
* @param tmpReq - QueryDisplayKnowledgeRequest
|
|
2423
2552
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -2425,7 +2554,7 @@ export default class Client extends OpenApi {
|
|
|
2425
2554
|
*/
|
|
2426
2555
|
queryDisplayKnowledgeWithOptions(tmpReq: $_model.QueryDisplayKnowledgeRequest, runtime: $dara.RuntimeOptions): Promise<$_model.QueryDisplayKnowledgeResponse>;
|
|
2427
2556
|
/**
|
|
2428
|
-
*
|
|
2557
|
+
* Queries the display knowledge base content by using a paged query with paging (synchronization).
|
|
2429
2558
|
*
|
|
2430
2559
|
* @param request - QueryDisplayKnowledgeRequest
|
|
2431
2560
|
* @returns QueryDisplayKnowledgeResponse
|
|
@@ -2730,105 +2859,105 @@ export default class Client extends OpenApi {
|
|
|
2730
2859
|
*/
|
|
2731
2860
|
sizeChartExtract(request: $_model.SizeChartExtractRequest): Promise<$_model.SizeChartExtractResponse>;
|
|
2732
2861
|
/**
|
|
2733
|
-
* Extracts structured information such as size charts and
|
|
2862
|
+
* Extracts structured information such as size charts and item weight and dimensions from images by using a multimodal large model. (Asynchronous)
|
|
2734
2863
|
*
|
|
2735
2864
|
* @remarks
|
|
2736
2865
|
* ## Scenarios
|
|
2737
|
-
* Size charts:
|
|
2738
|
-
*
|
|
2739
|
-
* ##
|
|
2740
|
-
* The size chart extraction service is based on multimodal large
|
|
2741
|
-
* Core capabilities: You
|
|
2866
|
+
* Size charts: Extracts size charts of apparel categories into text.
|
|
2867
|
+
* Item weight and dimensions: Extracts item weight and dimension information from images.
|
|
2868
|
+
* ## Features
|
|
2869
|
+
* The size chart extraction service is based on a multimodal large model. It automatically recognizes size charts or item weight and dimension information in images and converts the information into structured text. You provide an image URL, and the system processes the request as an asynchronous task and returns the extracted structured data. You can use the ColumnNameList parameter to specify the column names to be recognized, such as Size, Bust, and Length, for precise and targeted extraction. You can also use the LanguageModel parameter to control the output language. 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 item weight and dimension information.
|
|
2870
|
+
* Core capabilities: You input an image URL and optional column name configurations, and the system outputs the structured data of the size chart or item weight and dimensions in the image. The API operation uses an 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 a large number of calls.
|
|
2742
2871
|
* ## Comparison
|
|
2743
2872
|
* | Input image | Output result |
|
|
2744
2873
|
* | --- | --- |
|
|
2745
2874
|
* |  | {
|
|
2746
2875
|
* "SizeChart": [
|
|
2747
2876
|
* {
|
|
2748
|
-
* "
|
|
2877
|
+
* "尺码": {
|
|
2749
2878
|
* "value": "S"
|
|
2750
2879
|
* },
|
|
2751
|
-
* "
|
|
2880
|
+
* "腰围": {
|
|
2752
2881
|
* "unit": "CM",
|
|
2753
2882
|
* "value": 58
|
|
2754
2883
|
* },
|
|
2755
|
-
* "
|
|
2884
|
+
* "裙长": {
|
|
2756
2885
|
* "unit": "CM",
|
|
2757
2886
|
* "value": 81
|
|
2758
2887
|
* },
|
|
2759
|
-
* "
|
|
2888
|
+
* "体重建议": {
|
|
2760
2889
|
* "unit": "kg",
|
|
2761
2890
|
* "lower_value": 40,
|
|
2762
2891
|
* "upper_value": 47.5
|
|
2763
2892
|
* }
|
|
2764
2893
|
* },
|
|
2765
2894
|
* {
|
|
2766
|
-
* "
|
|
2895
|
+
* "尺码": {
|
|
2767
2896
|
* "value": "M"
|
|
2768
2897
|
* },
|
|
2769
|
-
* "
|
|
2898
|
+
* "腰围": {
|
|
2770
2899
|
* "unit": "CM",
|
|
2771
2900
|
* "value": 59
|
|
2772
2901
|
* },
|
|
2773
|
-
* "
|
|
2902
|
+
* "裙长": {
|
|
2774
2903
|
* "unit": "CM",
|
|
2775
2904
|
* "value": 82
|
|
2776
2905
|
* },
|
|
2777
|
-
* "
|
|
2906
|
+
* "体重建议": {
|
|
2778
2907
|
* "unit": "kg",
|
|
2779
2908
|
* "lower_value": 45,
|
|
2780
2909
|
* "upper_value": 52.5
|
|
2781
2910
|
* }
|
|
2782
2911
|
* },
|
|
2783
2912
|
* {
|
|
2784
|
-
* "
|
|
2913
|
+
* "尺码": {
|
|
2785
2914
|
* "value": "L"
|
|
2786
2915
|
* },
|
|
2787
|
-
* "
|
|
2916
|
+
* "腰围": {
|
|
2788
2917
|
* "unit": "CM",
|
|
2789
2918
|
* "value": 60
|
|
2790
2919
|
* },
|
|
2791
|
-
* "
|
|
2920
|
+
* "裙长": {
|
|
2792
2921
|
* "unit": "CM",
|
|
2793
2922
|
* "value": 83
|
|
2794
2923
|
* },
|
|
2795
|
-
* "
|
|
2924
|
+
* "体重建议": {
|
|
2796
2925
|
* "unit": "kg",
|
|
2797
2926
|
* "lower_value": 50,
|
|
2798
2927
|
* "upper_value": 57.5
|
|
2799
2928
|
* }
|
|
2800
2929
|
* },
|
|
2801
2930
|
* {
|
|
2802
|
-
* "
|
|
2931
|
+
* "尺码": {
|
|
2803
2932
|
* "value": "XL"
|
|
2804
2933
|
* },
|
|
2805
|
-
* "
|
|
2934
|
+
* "腰围": {
|
|
2806
2935
|
* "unit": "CM",
|
|
2807
2936
|
* "value": 61
|
|
2808
2937
|
* },
|
|
2809
|
-
* "
|
|
2938
|
+
* "裙长": {
|
|
2810
2939
|
* "unit": "CM",
|
|
2811
2940
|
* "value": 84
|
|
2812
2941
|
* },
|
|
2813
|
-
* "
|
|
2942
|
+
* "体重建议": {
|
|
2814
2943
|
* "unit": "kg",
|
|
2815
2944
|
* "lower_value": 55,
|
|
2816
2945
|
* "upper_value": 62.5
|
|
2817
2946
|
* }
|
|
2818
2947
|
* },
|
|
2819
2948
|
* {
|
|
2820
|
-
* "
|
|
2949
|
+
* "尺码": {
|
|
2821
2950
|
* "value": "2XL"
|
|
2822
2951
|
* },
|
|
2823
|
-
* "
|
|
2952
|
+
* "腰围": {
|
|
2824
2953
|
* "unit": "CM",
|
|
2825
2954
|
* "value": 62
|
|
2826
2955
|
* },
|
|
2827
|
-
* "
|
|
2956
|
+
* "裙长": {
|
|
2828
2957
|
* "unit": "CM",
|
|
2829
2958
|
* "value": 85
|
|
2830
2959
|
* },
|
|
2831
|
-
* "
|
|
2960
|
+
* "体重建议": {
|
|
2832
2961
|
* "unit": "kg",
|
|
2833
2962
|
* "lower_value": 60,
|
|
2834
2963
|
* "upper_value": 67.5
|
|
@@ -2844,7 +2973,7 @@ export default class Client extends OpenApi {
|
|
|
2844
2973
|
* "IntersectionAttributes": [
|
|
2845
2974
|
* "Size",
|
|
2846
2975
|
* "Skirt length",
|
|
2847
|
-
* "Waist (
|
|
2976
|
+
* "Waist (stretch)",
|
|
2848
2977
|
* "Weight recommendation"
|
|
2849
2978
|
* \\]
|
|
2850
2979
|
* } |
|
|
@@ -2855,105 +2984,105 @@ export default class Client extends OpenApi {
|
|
|
2855
2984
|
*/
|
|
2856
2985
|
sizeChartExtractAsyncWithOptions(tmpReq: $_model.SizeChartExtractAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.SizeChartExtractAsyncResponse>;
|
|
2857
2986
|
/**
|
|
2858
|
-
* Extracts structured information such as size charts and
|
|
2987
|
+
* Extracts structured information such as size charts and item weight and dimensions from images by using a multimodal large model. (Asynchronous)
|
|
2859
2988
|
*
|
|
2860
2989
|
* @remarks
|
|
2861
2990
|
* ## Scenarios
|
|
2862
|
-
* Size charts:
|
|
2863
|
-
*
|
|
2864
|
-
* ##
|
|
2865
|
-
* The size chart extraction service is based on multimodal large
|
|
2866
|
-
* Core capabilities: You
|
|
2991
|
+
* Size charts: Extracts size charts of apparel categories into text.
|
|
2992
|
+
* Item weight and dimensions: Extracts item weight and dimension information from images.
|
|
2993
|
+
* ## Features
|
|
2994
|
+
* The size chart extraction service is based on a multimodal large model. It automatically recognizes size charts or item weight and dimension information in images and converts the information into structured text. You provide an image URL, and the system processes the request as an asynchronous task and returns the extracted structured data. You can use the ColumnNameList parameter to specify the column names to be recognized, such as Size, Bust, and Length, for precise and targeted extraction. You can also use the LanguageModel parameter to control the output language. 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 item weight and dimension information.
|
|
2995
|
+
* Core capabilities: You input an image URL and optional column name configurations, and the system outputs the structured data of the size chart or item weight and dimensions in the image. The API operation uses an 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 a large number of calls.
|
|
2867
2996
|
* ## Comparison
|
|
2868
2997
|
* | Input image | Output result |
|
|
2869
2998
|
* | --- | --- |
|
|
2870
2999
|
* |  | {
|
|
2871
3000
|
* "SizeChart": [
|
|
2872
3001
|
* {
|
|
2873
|
-
* "
|
|
3002
|
+
* "尺码": {
|
|
2874
3003
|
* "value": "S"
|
|
2875
3004
|
* },
|
|
2876
|
-
* "
|
|
3005
|
+
* "腰围": {
|
|
2877
3006
|
* "unit": "CM",
|
|
2878
3007
|
* "value": 58
|
|
2879
3008
|
* },
|
|
2880
|
-
* "
|
|
3009
|
+
* "裙长": {
|
|
2881
3010
|
* "unit": "CM",
|
|
2882
3011
|
* "value": 81
|
|
2883
3012
|
* },
|
|
2884
|
-
* "
|
|
3013
|
+
* "体重建议": {
|
|
2885
3014
|
* "unit": "kg",
|
|
2886
3015
|
* "lower_value": 40,
|
|
2887
3016
|
* "upper_value": 47.5
|
|
2888
3017
|
* }
|
|
2889
3018
|
* },
|
|
2890
3019
|
* {
|
|
2891
|
-
* "
|
|
3020
|
+
* "尺码": {
|
|
2892
3021
|
* "value": "M"
|
|
2893
3022
|
* },
|
|
2894
|
-
* "
|
|
3023
|
+
* "腰围": {
|
|
2895
3024
|
* "unit": "CM",
|
|
2896
3025
|
* "value": 59
|
|
2897
3026
|
* },
|
|
2898
|
-
* "
|
|
3027
|
+
* "裙长": {
|
|
2899
3028
|
* "unit": "CM",
|
|
2900
3029
|
* "value": 82
|
|
2901
3030
|
* },
|
|
2902
|
-
* "
|
|
3031
|
+
* "体重建议": {
|
|
2903
3032
|
* "unit": "kg",
|
|
2904
3033
|
* "lower_value": 45,
|
|
2905
3034
|
* "upper_value": 52.5
|
|
2906
3035
|
* }
|
|
2907
3036
|
* },
|
|
2908
3037
|
* {
|
|
2909
|
-
* "
|
|
3038
|
+
* "尺码": {
|
|
2910
3039
|
* "value": "L"
|
|
2911
3040
|
* },
|
|
2912
|
-
* "
|
|
3041
|
+
* "腰围": {
|
|
2913
3042
|
* "unit": "CM",
|
|
2914
3043
|
* "value": 60
|
|
2915
3044
|
* },
|
|
2916
|
-
* "
|
|
3045
|
+
* "裙长": {
|
|
2917
3046
|
* "unit": "CM",
|
|
2918
3047
|
* "value": 83
|
|
2919
3048
|
* },
|
|
2920
|
-
* "
|
|
3049
|
+
* "体重建议": {
|
|
2921
3050
|
* "unit": "kg",
|
|
2922
3051
|
* "lower_value": 50,
|
|
2923
3052
|
* "upper_value": 57.5
|
|
2924
3053
|
* }
|
|
2925
3054
|
* },
|
|
2926
3055
|
* {
|
|
2927
|
-
* "
|
|
3056
|
+
* "尺码": {
|
|
2928
3057
|
* "value": "XL"
|
|
2929
3058
|
* },
|
|
2930
|
-
* "
|
|
3059
|
+
* "腰围": {
|
|
2931
3060
|
* "unit": "CM",
|
|
2932
3061
|
* "value": 61
|
|
2933
3062
|
* },
|
|
2934
|
-
* "
|
|
3063
|
+
* "裙长": {
|
|
2935
3064
|
* "unit": "CM",
|
|
2936
3065
|
* "value": 84
|
|
2937
3066
|
* },
|
|
2938
|
-
* "
|
|
3067
|
+
* "体重建议": {
|
|
2939
3068
|
* "unit": "kg",
|
|
2940
3069
|
* "lower_value": 55,
|
|
2941
3070
|
* "upper_value": 62.5
|
|
2942
3071
|
* }
|
|
2943
3072
|
* },
|
|
2944
3073
|
* {
|
|
2945
|
-
* "
|
|
3074
|
+
* "尺码": {
|
|
2946
3075
|
* "value": "2XL"
|
|
2947
3076
|
* },
|
|
2948
|
-
* "
|
|
3077
|
+
* "腰围": {
|
|
2949
3078
|
* "unit": "CM",
|
|
2950
3079
|
* "value": 62
|
|
2951
3080
|
* },
|
|
2952
|
-
* "
|
|
3081
|
+
* "裙长": {
|
|
2953
3082
|
* "unit": "CM",
|
|
2954
3083
|
* "value": 85
|
|
2955
3084
|
* },
|
|
2956
|
-
* "
|
|
3085
|
+
* "体重建议": {
|
|
2957
3086
|
* "unit": "kg",
|
|
2958
3087
|
* "lower_value": 60,
|
|
2959
3088
|
* "upper_value": 67.5
|
|
@@ -2969,7 +3098,7 @@ export default class Client extends OpenApi {
|
|
|
2969
3098
|
* "IntersectionAttributes": [
|
|
2970
3099
|
* "Size",
|
|
2971
3100
|
* "Skirt length",
|
|
2972
|
-
* "Waist (
|
|
3101
|
+
* "Waist (stretch)",
|
|
2973
3102
|
* "Weight recommendation"
|
|
2974
3103
|
* \\]
|
|
2975
3104
|
* } |
|
|
@@ -3155,7 +3284,7 @@ export default class Client extends OpenApi {
|
|
|
3155
3284
|
*/
|
|
3156
3285
|
textTranslate(request: $_model.TextTranslateRequest): Promise<$_model.TextTranslateResponse>;
|
|
3157
3286
|
/**
|
|
3158
|
-
* Translates text by using the Maas MT
|
|
3287
|
+
* Translates text by using the Maas MT e-commerce translation model, which is trained on over 1 billion high-quality bilingual sentence pairs and optimized for e-commerce terms such as brands, models, materials, and attributes. It supports 156 languages, over 400 language pairs, and automatic source language detection.
|
|
3159
3288
|
*
|
|
3160
3289
|
* @remarks
|
|
3161
3290
|
* ## Scenarios
|
|
@@ -3165,26 +3294,26 @@ export default class Client extends OpenApi {
|
|
|
3165
3294
|
*
|
|
3166
3295
|
* * Product attributes: Product attribute terms are short and contain e-commerce-specific words such as models and parameters.
|
|
3167
3296
|
*
|
|
3168
|
-
* * Customer service conversations: In customer service scenarios, the model optimizes issues such as missing context and typos, and supports polite expressions in
|
|
3297
|
+
* * Customer service conversations: In customer service scenarios, the model optimizes issues such as missing context and typos, and supports polite expressions in some language pairs.
|
|
3169
3298
|
*
|
|
3170
|
-
*
|
|
3299
|
+
* The Maas MT large language model can also be used for translation in general scenarios, such as office work, meetings, and daily conversations.
|
|
3171
3300
|
* ## Features
|
|
3172
|
-
* * **Ultra-low hallucination rate and high-speed inference
|
|
3301
|
+
* * **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 provides faster translation inference and an extremely low hallucination rate, making it especially suitable for large-scale invocation scenarios.
|
|
3173
3302
|
*
|
|
3174
|
-
* * **Supported text formats
|
|
3303
|
+
* * **Supported text formats**: The model supports text and HTML formats.
|
|
3175
3304
|
*
|
|
3176
|
-
* * **Translation intervention
|
|
3305
|
+
* * **Translation intervention**: You can customize translation results, including keeping words untranslated (ABC-ABC), specifying translations (ABC-DEF), and omitting translations (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 words. If you need more, contact the platform.
|
|
3177
3306
|
*
|
|
3178
|
-
* * **Translation
|
|
3307
|
+
* * **Translation effect comparison**
|
|
3179
3308
|
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation advantages** |
|
|
3180
3309
|
* | --- | --- | --- | --- | --- |
|
|
3181
3310
|
* | 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 |
|
|
3182
3311
|
* | 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 |
|
|
3183
|
-
* | 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
|
|
3184
|
-
* ## Preparations and
|
|
3185
|
-
* Text translation supports both
|
|
3186
|
-
* The asynchronous APIs for text translation and other
|
|
3187
|
-
* For the asynchronous
|
|
3312
|
+
* | 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. It is translated as a "key bag" rather than a "keychain". Other translations may cause ambiguity about the product subject. |
|
|
3313
|
+
* ## Preparations and call flow
|
|
3314
|
+
* Text translation supports both synchronization and asynchronous call methods. This topic describes the asynchronous call API. For synchronization calls, see [Text Translation - Synchronization API](https://api.aliyun.com/document/Aidge/2026-04-28/TextTranslate).
|
|
3315
|
+
* 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.
|
|
3316
|
+
* For the asynchronous call flow, subscribe rules, message formats and encryption protocols, and detailed integration solutions, see [Asynchronous API call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
3188
3317
|
*
|
|
3189
3318
|
* @param tmpReq - TextTranslateAsyncRequest
|
|
3190
3319
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3192,7 +3321,7 @@ export default class Client extends OpenApi {
|
|
|
3192
3321
|
*/
|
|
3193
3322
|
textTranslateAsyncWithOptions(tmpReq: $_model.TextTranslateAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.TextTranslateAsyncResponse>;
|
|
3194
3323
|
/**
|
|
3195
|
-
* Translates text by using the Maas MT
|
|
3324
|
+
* Translates text by using the Maas MT e-commerce translation model, which is trained on over 1 billion high-quality bilingual sentence pairs and optimized for e-commerce terms such as brands, models, materials, and attributes. It supports 156 languages, over 400 language pairs, and automatic source language detection.
|
|
3196
3325
|
*
|
|
3197
3326
|
* @remarks
|
|
3198
3327
|
* ## Scenarios
|
|
@@ -3202,33 +3331,33 @@ export default class Client extends OpenApi {
|
|
|
3202
3331
|
*
|
|
3203
3332
|
* * Product attributes: Product attribute terms are short and contain e-commerce-specific words such as models and parameters.
|
|
3204
3333
|
*
|
|
3205
|
-
* * Customer service conversations: In customer service scenarios, the model optimizes issues such as missing context and typos, and supports polite expressions in
|
|
3334
|
+
* * Customer service conversations: In customer service scenarios, the model optimizes issues such as missing context and typos, and supports polite expressions in some language pairs.
|
|
3206
3335
|
*
|
|
3207
|
-
*
|
|
3336
|
+
* The Maas MT large language model can also be used for translation in general scenarios, such as office work, meetings, and daily conversations.
|
|
3208
3337
|
* ## Features
|
|
3209
|
-
* * **Ultra-low hallucination rate and high-speed inference
|
|
3338
|
+
* * **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 provides faster translation inference and an extremely low hallucination rate, making it especially suitable for large-scale invocation scenarios.
|
|
3210
3339
|
*
|
|
3211
|
-
* * **Supported text formats
|
|
3340
|
+
* * **Supported text formats**: The model supports text and HTML formats.
|
|
3212
3341
|
*
|
|
3213
|
-
* * **Translation intervention
|
|
3342
|
+
* * **Translation intervention**: You can customize translation results, including keeping words untranslated (ABC-ABC), specifying translations (ABC-DEF), and omitting translations (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 words. If you need more, contact the platform.
|
|
3214
3343
|
*
|
|
3215
|
-
* * **Translation
|
|
3344
|
+
* * **Translation effect comparison**
|
|
3216
3345
|
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation advantages** |
|
|
3217
3346
|
* | --- | --- | --- | --- | --- |
|
|
3218
3347
|
* | 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 |
|
|
3219
3348
|
* | 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 |
|
|
3220
|
-
* | 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
|
|
3221
|
-
* ## Preparations and
|
|
3222
|
-
* Text translation supports both
|
|
3223
|
-
* The asynchronous APIs for text translation and other
|
|
3224
|
-
* For the asynchronous
|
|
3349
|
+
* | 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. It is translated as a "key bag" rather than a "keychain". Other translations may cause ambiguity about the product subject. |
|
|
3350
|
+
* ## Preparations and call flow
|
|
3351
|
+
* Text translation supports both synchronization and asynchronous call methods. This topic describes the asynchronous call API. For synchronization calls, see [Text Translation - Synchronization API](https://api.aliyun.com/document/Aidge/2026-04-28/TextTranslate).
|
|
3352
|
+
* 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.
|
|
3353
|
+
* For the asynchronous call flow, subscribe rules, message formats and encryption protocols, and detailed integration solutions, see [Asynchronous API call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
3225
3354
|
*
|
|
3226
3355
|
* @param request - TextTranslateAsyncRequest
|
|
3227
3356
|
* @returns TextTranslateAsyncResponse
|
|
3228
3357
|
*/
|
|
3229
3358
|
textTranslateAsync(request: $_model.TextTranslateAsyncRequest): Promise<$_model.TextTranslateAsyncResponse>;
|
|
3230
3359
|
/**
|
|
3231
|
-
* Synchronously
|
|
3360
|
+
* Synchronously modifies the content of a display knowledge base in batches.
|
|
3232
3361
|
*
|
|
3233
3362
|
* @param tmpReq - UpdateDisplayKnowledgeRequest
|
|
3234
3363
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3236,7 +3365,7 @@ export default class Client extends OpenApi {
|
|
|
3236
3365
|
*/
|
|
3237
3366
|
updateDisplayKnowledgeWithOptions(tmpReq: $_model.UpdateDisplayKnowledgeRequest, runtime: $dara.RuntimeOptions): Promise<$_model.UpdateDisplayKnowledgeResponse>;
|
|
3238
3367
|
/**
|
|
3239
|
-
* Synchronously
|
|
3368
|
+
* Synchronously modifies the content of a display knowledge base in batches.
|
|
3240
3369
|
*
|
|
3241
3370
|
* @param request - UpdateDisplayKnowledgeRequest
|
|
3242
3371
|
* @returns UpdateDisplayKnowledgeResponse
|
|
@@ -3294,28 +3423,28 @@ export default class Client extends OpenApi {
|
|
|
3294
3423
|
*/
|
|
3295
3424
|
videoGeneration(request: $_model.VideoGenerationRequest): Promise<$_model.VideoGenerationResponse>;
|
|
3296
3425
|
/**
|
|
3297
|
-
* 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. The API uses an asynchronous invocation mode. After you submit a translation task, you can obtain the
|
|
3426
|
+
* 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. The API uses an asynchronous invocation mode. After you submit a translation task, you can obtain the task ID and poll the task status by calling the query API until the task is completed and the result is returned.
|
|
3298
3427
|
*
|
|
3299
3428
|
* @remarks
|
|
3300
3429
|
* ## Product introduction
|
|
3301
3430
|
* 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.
|
|
3302
3431
|
* 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.
|
|
3303
3432
|
* ## Scenarios
|
|
3304
|
-
* * **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
|
|
3433
|
+
* * **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 facilitate promotion on overseas platforms.
|
|
3305
3434
|
*
|
|
3306
3435
|
* * **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.
|
|
3307
3436
|
*
|
|
3308
|
-
* * **Global brand advertising**: Automatically generates video versions in the
|
|
3437
|
+
* * **Global brand advertising**: Automatically generates video versions in the languages of the target regions to reduce manual production costs.
|
|
3309
3438
|
*
|
|
3310
3439
|
* * **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.
|
|
3311
3440
|
* ## Features
|
|
3312
3441
|
* | Feature | Identifier | Description |
|
|
3313
3442
|
* | --- | --- | --- |
|
|
3314
|
-
* | Speech subtitle translation | speech | Translates the video speech into target language dubbing. You can choose to erase the original subtitles
|
|
3315
|
-
* | On-screen text translation | visual | Translates the source language text in the video frames, or erases the on-screen text without translation. You can choose to erase brand logos. |
|
|
3316
|
-
* Speech subtitle translation (speech) generates target language dubbing based on the spoken content in the video, processes the subtitles
|
|
3443
|
+
* | Speech subtitle translation | speech | Translates the video speech into target language dubbing. You can choose to only erase the original subtitles or replace them with translated subtitles. By default, the original subtitles are not processed and no new subtitles are added. |
|
|
3444
|
+
* | 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. |
|
|
3445
|
+
* Speech subtitle translation (speech) generates target language dubbing based on the spoken content in the video, processes the subtitles according to 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 first erases the original subtitles and then adds subtitles synchronized with the translated speech.
|
|
3317
3446
|
* 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.
|
|
3318
|
-
* When both speech and visual are selected, the speech subtitle translation is completed and the video is synthesized first,
|
|
3447
|
+
* When both speech and visual are selected, the speech subtitle translation is completed and the video is synthesized first. Then, on-screen text processing is performed on this video, retaining the translated dubbing, and a final video is output. The order of features 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 ones will be retained during subsequent on-screen text processing.
|
|
3319
3448
|
*
|
|
3320
3449
|
* @param tmpReq - VideoTranslationRequest
|
|
3321
3450
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3323,66 +3452,66 @@ export default class Client extends OpenApi {
|
|
|
3323
3452
|
*/
|
|
3324
3453
|
videoTranslationWithOptions(tmpReq: $_model.VideoTranslationRequest, runtime: $dara.RuntimeOptions): Promise<$_model.VideoTranslationResponse>;
|
|
3325
3454
|
/**
|
|
3326
|
-
* 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. The API uses an asynchronous invocation mode. After you submit a translation task, you can obtain the
|
|
3455
|
+
* 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. The API uses an asynchronous invocation mode. After you submit a translation task, you can obtain the task ID and poll the task status by calling the query API until the task is completed and the result is returned.
|
|
3327
3456
|
*
|
|
3328
3457
|
* @remarks
|
|
3329
3458
|
* ## Product introduction
|
|
3330
3459
|
* 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.
|
|
3331
3460
|
* 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.
|
|
3332
3461
|
* ## Scenarios
|
|
3333
|
-
* * **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
|
|
3462
|
+
* * **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 facilitate promotion on overseas platforms.
|
|
3334
3463
|
*
|
|
3335
3464
|
* * **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.
|
|
3336
3465
|
*
|
|
3337
|
-
* * **Global brand advertising**: Automatically generates video versions in the
|
|
3466
|
+
* * **Global brand advertising**: Automatically generates video versions in the languages of the target regions to reduce manual production costs.
|
|
3338
3467
|
*
|
|
3339
3468
|
* * **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.
|
|
3340
3469
|
* ## Features
|
|
3341
3470
|
* | Feature | Identifier | Description |
|
|
3342
3471
|
* | --- | --- | --- |
|
|
3343
|
-
* | Speech subtitle translation | speech | Translates the video speech into target language dubbing. You can choose to erase the original subtitles
|
|
3344
|
-
* | On-screen text translation | visual | Translates the source language text in the video frames, or erases the on-screen text without translation. You can choose to erase brand logos. |
|
|
3345
|
-
* Speech subtitle translation (speech) generates target language dubbing based on the spoken content in the video, processes the subtitles
|
|
3472
|
+
* | Speech subtitle translation | speech | Translates the video speech into target language dubbing. You can choose to only erase the original subtitles or replace them with translated subtitles. By default, the original subtitles are not processed and no new subtitles are added. |
|
|
3473
|
+
* | 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. |
|
|
3474
|
+
* Speech subtitle translation (speech) generates target language dubbing based on the spoken content in the video, processes the subtitles according to 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 first erases the original subtitles and then adds subtitles synchronized with the translated speech.
|
|
3346
3475
|
* 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.
|
|
3347
|
-
* When both speech and visual are selected, the speech subtitle translation is completed and the video is synthesized first,
|
|
3476
|
+
* When both speech and visual are selected, the speech subtitle translation is completed and the video is synthesized first. Then, on-screen text processing is performed on this video, retaining the translated dubbing, and a final video is output. The order of features 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 ones will be retained during subsequent on-screen text processing.
|
|
3348
3477
|
*
|
|
3349
3478
|
* @param request - VideoTranslationRequest
|
|
3350
3479
|
* @returns VideoTranslationResponse
|
|
3351
3480
|
*/
|
|
3352
3481
|
videoTranslation(request: $_model.VideoTranslationRequest): Promise<$_model.VideoTranslationResponse>;
|
|
3353
3482
|
/**
|
|
3354
|
-
* Generates virtual try-on images
|
|
3483
|
+
* Generates virtual try-on images by using AI algorithms. This API service replaces the clothing on a model image with a specified garment image while preserving the model\\"s pose, facial features, and other details, ensuring a realistic and well-fitted result. You only need to provide the URLs of the original images to obtain the processed image.
|
|
3355
3484
|
*
|
|
3356
3485
|
* @remarks
|
|
3357
3486
|
* ## Scenarios
|
|
3358
|
-
* - **Virtual try-on for clothing
|
|
3359
|
-
* Supports
|
|
3487
|
+
* - **Virtual try-on for clothing:**
|
|
3488
|
+
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After you upload a model image and a garment image, the system generates natural and realistic try-on effects to visually demonstrate how the clothing looks on the model.
|
|
3360
3489
|
* - **Virtual try-on for shoes and hats:**
|
|
3361
|
-
* Supports virtual try-on for shoes
|
|
3490
|
+
* Supports virtual try-on for accessories such as shoes and hats. The system intelligently matches the position and proportion of the items based on the model\\"s pose and body parts to present a coordinated and realistic wearing effect.
|
|
3362
3491
|
* - **E-commerce product display and marketing:**
|
|
3363
|
-
*
|
|
3492
|
+
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional photography, outfit changes, and post-production, and improving the production efficiency of product images.
|
|
3364
3493
|
* - **Online shopping experience optimization:**
|
|
3365
|
-
*
|
|
3494
|
+
* Allows consumers to preview the wearing effect of products through virtual try-on, providing a more intuitive understanding of the style, matching, and overall effect of the products, which assists in purchase decisions and enhances the shopping experience.
|
|
3366
3495
|
* ## Features
|
|
3367
|
-
* - **First,
|
|
3368
|
-
* - a. Model image: the image of the person
|
|
3369
|
-
* - b. Product image: the image of the clothing, shoes, or hat to be
|
|
3370
|
-
* - **Second, select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
3371
|
-
* - a. Specify product type: directly
|
|
3372
|
-
* - b. Automatic type recognition: if
|
|
3373
|
-
* - **Finally, the system combines the model image, product image, and product type to generate a virtual try-on image
|
|
3374
|
-
* - a. Preserve model details: the generation process does not
|
|
3375
|
-
* - b. Maintain
|
|
3376
|
-
* - c. Generate try-on effect: the product is naturally applied
|
|
3377
|
-
* ##
|
|
3496
|
+
* - **First, you 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:**
|
|
3497
|
+
* - a. Model image: the image of the person who will wear the clothing in the virtual try-on.
|
|
3498
|
+
* - b. Product image: the image of the clothing, shoes, or hat to be worn by the model.
|
|
3499
|
+
* - **Second, you can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
3500
|
+
* - a. Specify product type: you can directly input the type of the current product, and the system will process it according to the specified type.
|
|
3501
|
+
* - b. Automatic type recognition: if you 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.
|
|
3502
|
+
* - **Finally, the system combines the model image, product image, and product type to generate a virtual try-on image, showing the wearing effect of the product on the model:**
|
|
3503
|
+
* - a. Preserve model details: the generation process does not adjust the appearance, hairstyle, pose, body shape, or other details of the person in the original model image.
|
|
3504
|
+
* - 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.
|
|
3505
|
+
* - c. Generate try-on effect: the product is naturally applied to the model, fitting the person\\"s pose and body structure to generate a coordinated and realistic virtual try-on image.
|
|
3506
|
+
* ## Examples
|
|
3378
3507
|
* | **Type** | **Model image** | **Garment image** | **Try-on result** |
|
|
3379
3508
|
* | --- | --- | --- | --- |
|
|
3380
|
-
* | Tops |  |  |  |  |  |  |
|
|
3510
|
+
* | Bottoms |  |  |  |
|
|
3511
|
+
* | Shoes |  |  |  |
|
|
3383
3512
|
* | Jumpsuits |  |  |  |
|
|
3384
3513
|
* | Dresses |  |  |  |
|
|
3385
|
-
* | Hats |  |  |  |  |
|
|
3386
3515
|
*
|
|
3387
3516
|
* @param request - VirtualTryOnRequest
|
|
3388
3517
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3390,38 +3519,38 @@ export default class Client extends OpenApi {
|
|
|
3390
3519
|
*/
|
|
3391
3520
|
virtualTryOnWithOptions(request: $_model.VirtualTryOnRequest, runtime: $dara.RuntimeOptions): Promise<$_model.VirtualTryOnResponse>;
|
|
3392
3521
|
/**
|
|
3393
|
-
* Generates virtual try-on images
|
|
3522
|
+
* Generates virtual try-on images by using AI algorithms. This API service replaces the clothing on a model image with a specified garment image while preserving the model\\"s pose, facial features, and other details, ensuring a realistic and well-fitted result. You only need to provide the URLs of the original images to obtain the processed image.
|
|
3394
3523
|
*
|
|
3395
3524
|
* @remarks
|
|
3396
3525
|
* ## Scenarios
|
|
3397
|
-
* - **Virtual try-on for clothing
|
|
3398
|
-
* Supports
|
|
3526
|
+
* - **Virtual try-on for clothing:**
|
|
3527
|
+
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After you upload a model image and a garment image, the system generates natural and realistic try-on effects to visually demonstrate how the clothing looks on the model.
|
|
3399
3528
|
* - **Virtual try-on for shoes and hats:**
|
|
3400
|
-
* Supports virtual try-on for shoes
|
|
3529
|
+
* Supports virtual try-on for accessories such as shoes and hats. The system intelligently matches the position and proportion of the items based on the model\\"s pose and body parts to present a coordinated and realistic wearing effect.
|
|
3401
3530
|
* - **E-commerce product display and marketing:**
|
|
3402
|
-
*
|
|
3531
|
+
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional photography, outfit changes, and post-production, and improving the production efficiency of product images.
|
|
3403
3532
|
* - **Online shopping experience optimization:**
|
|
3404
|
-
*
|
|
3533
|
+
* Allows consumers to preview the wearing effect of products through virtual try-on, providing a more intuitive understanding of the style, matching, and overall effect of the products, which assists in purchase decisions and enhances the shopping experience.
|
|
3405
3534
|
* ## Features
|
|
3406
|
-
* - **First,
|
|
3407
|
-
* - a. Model image: the image of the person
|
|
3408
|
-
* - b. Product image: the image of the clothing, shoes, or hat to be
|
|
3409
|
-
* - **Second, select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
3410
|
-
* - a. Specify product type: directly
|
|
3411
|
-
* - b. Automatic type recognition: if
|
|
3412
|
-
* - **Finally, the system combines the model image, product image, and product type to generate a virtual try-on image
|
|
3413
|
-
* - a. Preserve model details: the generation process does not
|
|
3414
|
-
* - b. Maintain
|
|
3415
|
-
* - c. Generate try-on effect: the product is naturally applied
|
|
3416
|
-
* ##
|
|
3535
|
+
* - **First, you 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:**
|
|
3536
|
+
* - a. Model image: the image of the person who will wear the clothing in the virtual try-on.
|
|
3537
|
+
* - b. Product image: the image of the clothing, shoes, or hat to be worn by the model.
|
|
3538
|
+
* - **Second, you can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
3539
|
+
* - a. Specify product type: you can directly input the type of the current product, and the system will process it according to the specified type.
|
|
3540
|
+
* - b. Automatic type recognition: if you 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.
|
|
3541
|
+
* - **Finally, the system combines the model image, product image, and product type to generate a virtual try-on image, showing the wearing effect of the product on the model:**
|
|
3542
|
+
* - a. Preserve model details: the generation process does not adjust the appearance, hairstyle, pose, body shape, or other details of the person in the original model image.
|
|
3543
|
+
* - 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.
|
|
3544
|
+
* - c. Generate try-on effect: the product is naturally applied to the model, fitting the person\\"s pose and body structure to generate a coordinated and realistic virtual try-on image.
|
|
3545
|
+
* ## Examples
|
|
3417
3546
|
* | **Type** | **Model image** | **Garment image** | **Try-on result** |
|
|
3418
3547
|
* | --- | --- | --- | --- |
|
|
3419
|
-
* | Tops |  |  |  |  |  |  |
|
|
3549
|
+
* | Bottoms |  |  |  |
|
|
3550
|
+
* | Shoes |  |  |  |
|
|
3422
3551
|
* | Jumpsuits |  |  |  |
|
|
3423
3552
|
* | Dresses |  |  |  |
|
|
3424
|
-
* | Hats |  |  |  |  |
|
|
3425
3554
|
*
|
|
3426
3555
|
* @param request - VirtualTryOnRequest
|
|
3427
3556
|
* @returns VirtualTryOnResponse
|