@alicloud/aidge20260428 5.12.2 → 5.14.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/client.d.ts +774 -630
- package/dist/client.js +863 -630
- package/dist/client.js.map +1 -1
- package/dist/models/AddDisplayKnowledgeResponseBody.d.ts +3 -0
- package/dist/models/AddDisplayKnowledgeResponseBody.js.map +1 -1
- package/dist/models/AiTryOnRequest.d.ts +65 -8
- package/dist/models/AiTryOnRequest.js +10 -0
- package/dist/models/AiTryOnRequest.js.map +1 -1
- package/dist/models/AiTryOnResponseBody.d.ts +8 -8
- package/dist/models/CategoryAttributeMatchResponseBody.d.ts +3 -0
- package/dist/models/CategoryAttributeMatchResponseBody.js.map +1 -1
- package/dist/models/DeleteDisplayKnowledgeResponseBody.d.ts +3 -0
- package/dist/models/DeleteDisplayKnowledgeResponseBody.js.map +1 -1
- package/dist/models/DocumentTranslateRequest.d.ts +10 -7
- package/dist/models/DocumentTranslateRequest.js.map +1 -1
- package/dist/models/DocumentTranslateResponseBody.d.ts +3 -3
- package/dist/models/EcomVideoRecreationRequest.d.ts +11 -17
- package/dist/models/EcomVideoRecreationRequest.js.map +1 -1
- package/dist/models/EcomVideoRecreationResponseBody.d.ts +3 -3
- package/dist/models/EcomVideoRecreationShrinkRequest.d.ts +2 -2
- package/dist/models/GeneralRephotographyDetectionResponseBody.d.ts +4 -4
- package/dist/models/GenerateProductContentRequest.d.ts +11 -13
- package/dist/models/GenerateProductContentRequest.js.map +1 -1
- package/dist/models/GenerateProductContentResponseBody.d.ts +9 -7
- package/dist/models/GenerateProductContentResponseBody.js.map +1 -1
- package/dist/models/ImageMattingAsyncRequest.d.ts +1 -1
- package/dist/models/ImageMattingAsyncResponseBody.d.ts +2 -2
- package/dist/models/ImageRecognitionAsyncRequest.d.ts +14 -11
- package/dist/models/ImageRecognitionAsyncRequest.js.map +1 -1
- package/dist/models/ImageRecognitionAsyncResponseBody.d.ts +5 -5
- package/dist/models/ImageRecognitionAsyncShrinkRequest.d.ts +14 -11
- package/dist/models/ImageRecognitionAsyncShrinkRequest.js.map +1 -1
- package/dist/models/ImageRemovalProAsyncRequest.d.ts +1 -1
- package/dist/models/ImageRemovalProAsyncResponseBody.d.ts +5 -7
- package/dist/models/ImageRemovalProAsyncResponseBody.js.map +1 -1
- package/dist/models/ImageRemovalProResponseBody.d.ts +3 -0
- package/dist/models/ImageRemovalProResponseBody.js.map +1 -1
- package/dist/models/ImageRemoveAsyncRequest.d.ts +19 -8
- package/dist/models/ImageRemoveAsyncRequest.js.map +1 -1
- package/dist/models/ImageRemoveAsyncResponseBody.d.ts +8 -6
- package/dist/models/ImageRemoveAsyncResponseBody.js.map +1 -1
- package/dist/models/ImageRemoveAsyncShrinkRequest.d.ts +19 -8
- package/dist/models/ImageRemoveAsyncShrinkRequest.js.map +1 -1
- package/dist/models/ImageTranslationPlusAsyncRequest.d.ts +11 -11
- package/dist/models/ImageTranslationPlusAsyncResponseBody.d.ts +4 -4
- package/dist/models/ImageTranslationProAsyncRequest.d.ts +5 -5
- package/dist/models/ImageTranslationProAsyncResponseBody.d.ts +1 -1
- package/dist/models/ImageTranslationStandardAsyncRequest.d.ts +1 -1
- package/dist/models/ImageTranslationStandardAsyncResponseBody.d.ts +3 -3
- package/dist/models/ImageTranslationStandardRequest.d.ts +4 -4
- package/dist/models/ImageTranslationStandardResponseBody.d.ts +10 -10
- package/dist/models/ImageUpscaleRequest.d.ts +1 -1
- package/dist/models/ImageUpscaleResponseBody.d.ts +7 -7
- package/dist/models/MaterialInspectionRequest.d.ts +4 -4
- package/dist/models/MaterialInspectionResponseBody.d.ts +9 -9
- package/dist/models/MerchandisePlacementDetectionLiteResponseBody.d.ts +15 -12
- package/dist/models/MerchandisePlacementDetectionLiteResponseBody.js.map +1 -1
- package/dist/models/MerchandisePlacementDetectionProRequest.d.ts +5 -5
- package/dist/models/MerchandisePlacementDetectionProResponseBody.d.ts +6 -6
- package/dist/models/MerchandisePlacementDetectionRequest.d.ts +7 -7
- package/dist/models/MerchandisePlacementDetectionResponseBody.d.ts +19 -19
- package/dist/models/MerchandisePriceTagDetectionRequest.d.ts +1 -1
- package/dist/models/MerchandisePriceTagDetectionResponseBody.d.ts +11 -11
- package/dist/models/MerchandiseSceneDetectionRequest.d.ts +1 -1
- package/dist/models/MerchandiseSceneDetectionResponseBody.d.ts +16 -10
- package/dist/models/MerchandiseSceneDetectionResponseBody.js.map +1 -1
- package/dist/models/MilkPowderCanBottomCodeRephotographyDetectionResponseBody.d.ts +7 -7
- package/dist/models/MilkPowderCartonCodeRephotographyDetectionResponseBody.d.ts +12 -9
- package/dist/models/MilkPowderCartonCodeRephotographyDetectionResponseBody.js.map +1 -1
- package/dist/models/PrepaidTextTranslateRequest.d.ts +8 -8
- package/dist/models/PrepaidTextTranslateResponseBody.d.ts +11 -8
- package/dist/models/PrepaidTextTranslateResponseBody.js.map +1 -1
- package/dist/models/PrepaidTextTranslateShrinkRequest.d.ts +8 -8
- package/dist/models/ProductVideoGenerationRequest.d.ts +62 -0
- package/dist/models/ProductVideoGenerationRequest.js +71 -0
- package/dist/models/ProductVideoGenerationRequest.js.map +1 -0
- package/dist/models/ProductVideoGenerationResponse.d.ts +19 -0
- package/dist/models/ProductVideoGenerationResponse.js +69 -0
- package/dist/models/ProductVideoGenerationResponse.js.map +1 -0
- package/dist/models/ProductVideoGenerationResponseBody.d.ts +86 -0
- package/dist/models/ProductVideoGenerationResponseBody.js +92 -0
- package/dist/models/ProductVideoGenerationResponseBody.js.map +1 -0
- package/dist/models/ProductVideoGenerationShrinkRequest.d.ts +62 -0
- package/dist/models/ProductVideoGenerationShrinkRequest.js +68 -0
- package/dist/models/ProductVideoGenerationShrinkRequest.js.map +1 -0
- package/dist/models/QueryDisplayKnowledgeResponseBody.d.ts +3 -0
- package/dist/models/QueryDisplayKnowledgeResponseBody.js.map +1 -1
- package/dist/models/SizeChartExtractAsyncRequest.d.ts +3 -3
- package/dist/models/SizeChartExtractAsyncResponseBody.d.ts +7 -5
- package/dist/models/SizeChartExtractAsyncResponseBody.js.map +1 -1
- package/dist/models/SizeChartExtractAsyncShrinkRequest.d.ts +3 -3
- package/dist/models/StorefrontSceneRecognitionRequest.d.ts +1 -1
- package/dist/models/StorefrontSceneRecognitionResponseBody.d.ts +9 -6
- package/dist/models/StorefrontSceneRecognitionResponseBody.js.map +1 -1
- package/dist/models/SubmitProductMatchRequest.d.ts +8 -8
- package/dist/models/SubmitProductMatchResponseBody.d.ts +7 -7
- package/dist/models/TextTranslateAsyncRequest.d.ts +9 -9
- package/dist/models/TextTranslateAsyncResponseBody.d.ts +6 -6
- package/dist/models/TextTranslateAsyncShrinkRequest.d.ts +9 -9
- package/dist/models/UpdateDisplayKnowledgeResponseBody.d.ts +3 -0
- package/dist/models/UpdateDisplayKnowledgeResponseBody.js.map +1 -1
- package/dist/models/VacancyDetectionRequest.d.ts +39 -0
- package/dist/models/VacancyDetectionRequest.js +62 -0
- package/dist/models/VacancyDetectionRequest.js.map +1 -0
- package/dist/models/VacancyDetectionResponse.d.ts +19 -0
- package/dist/models/VacancyDetectionResponse.js +69 -0
- package/dist/models/VacancyDetectionResponse.js.map +1 -0
- package/dist/models/VacancyDetectionResponseBody.d.ts +83 -0
- package/dist/models/VacancyDetectionResponseBody.js +93 -0
- package/dist/models/VacancyDetectionResponseBody.js.map +1 -0
- package/dist/models/VideoGenerationRequest.d.ts +18 -17
- package/dist/models/VideoGenerationRequest.js.map +1 -1
- package/dist/models/VideoGenerationResponseBody.d.ts +2 -2
- package/dist/models/VideoTranslationRequest.d.ts +8 -17
- package/dist/models/VideoTranslationRequest.js.map +1 -1
- package/dist/models/VideoTranslationResponseBody.d.ts +4 -6
- package/dist/models/VideoTranslationResponseBody.js.map +1 -1
- package/dist/models/VideoTranslationShrinkRequest.d.ts +8 -17
- package/dist/models/VideoTranslationShrinkRequest.js.map +1 -1
- package/dist/models/VirtualTryOnResponseBody.d.ts +7 -6
- package/dist/models/VirtualTryOnResponseBody.js.map +1 -1
- package/dist/models/model.d.ts +9 -0
- package/dist/models/model.js +23 -5
- package/dist/models/model.js.map +1 -1
- package/package.json +1 -1
- package/src/client.ts +882 -630
- package/src/models/AddDisplayKnowledgeResponseBody.ts +3 -0
- package/src/models/AiTryOnRequest.ts +75 -8
- package/src/models/AiTryOnResponseBody.ts +8 -8
- package/src/models/CategoryAttributeMatchResponseBody.ts +3 -0
- package/src/models/DeleteDisplayKnowledgeResponseBody.ts +3 -0
- package/src/models/DocumentTranslateRequest.ts +10 -7
- package/src/models/DocumentTranslateResponseBody.ts +3 -3
- package/src/models/EcomVideoRecreationRequest.ts +11 -17
- package/src/models/EcomVideoRecreationResponseBody.ts +3 -3
- package/src/models/EcomVideoRecreationShrinkRequest.ts +2 -2
- package/src/models/GeneralRephotographyDetectionResponseBody.ts +4 -4
- package/src/models/GenerateProductContentRequest.ts +11 -13
- package/src/models/GenerateProductContentResponseBody.ts +9 -7
- package/src/models/ImageMattingAsyncRequest.ts +1 -1
- package/src/models/ImageMattingAsyncResponseBody.ts +2 -2
- package/src/models/ImageRecognitionAsyncRequest.ts +14 -11
- package/src/models/ImageRecognitionAsyncResponseBody.ts +5 -5
- package/src/models/ImageRecognitionAsyncShrinkRequest.ts +14 -11
- package/src/models/ImageRemovalProAsyncRequest.ts +1 -1
- package/src/models/ImageRemovalProAsyncResponseBody.ts +5 -7
- package/src/models/ImageRemovalProResponseBody.ts +3 -0
- package/src/models/ImageRemoveAsyncRequest.ts +19 -8
- package/src/models/ImageRemoveAsyncResponseBody.ts +8 -6
- package/src/models/ImageRemoveAsyncShrinkRequest.ts +19 -8
- package/src/models/ImageTranslationPlusAsyncRequest.ts +11 -11
- package/src/models/ImageTranslationPlusAsyncResponseBody.ts +4 -4
- package/src/models/ImageTranslationProAsyncRequest.ts +5 -5
- package/src/models/ImageTranslationProAsyncResponseBody.ts +1 -1
- package/src/models/ImageTranslationStandardAsyncRequest.ts +1 -1
- package/src/models/ImageTranslationStandardAsyncResponseBody.ts +3 -3
- package/src/models/ImageTranslationStandardRequest.ts +4 -4
- package/src/models/ImageTranslationStandardResponseBody.ts +10 -10
- package/src/models/ImageUpscaleRequest.ts +1 -1
- package/src/models/ImageUpscaleResponseBody.ts +7 -7
- package/src/models/MaterialInspectionRequest.ts +4 -4
- package/src/models/MaterialInspectionResponseBody.ts +9 -9
- package/src/models/MerchandisePlacementDetectionLiteResponseBody.ts +15 -12
- package/src/models/MerchandisePlacementDetectionProRequest.ts +5 -5
- package/src/models/MerchandisePlacementDetectionProResponseBody.ts +6 -6
- package/src/models/MerchandisePlacementDetectionRequest.ts +7 -7
- package/src/models/MerchandisePlacementDetectionResponseBody.ts +19 -19
- package/src/models/MerchandisePriceTagDetectionRequest.ts +1 -1
- package/src/models/MerchandisePriceTagDetectionResponseBody.ts +11 -11
- package/src/models/MerchandiseSceneDetectionRequest.ts +1 -1
- package/src/models/MerchandiseSceneDetectionResponseBody.ts +16 -10
- package/src/models/MilkPowderCanBottomCodeRephotographyDetectionResponseBody.ts +7 -7
- package/src/models/MilkPowderCartonCodeRephotographyDetectionResponseBody.ts +12 -9
- package/src/models/PrepaidTextTranslateRequest.ts +8 -8
- package/src/models/PrepaidTextTranslateResponseBody.ts +11 -8
- package/src/models/PrepaidTextTranslateShrinkRequest.ts +8 -8
- package/src/models/ProductVideoGenerationRequest.ts +88 -0
- package/src/models/ProductVideoGenerationResponse.ts +40 -0
- package/src/models/ProductVideoGenerationResponseBody.ts +124 -0
- package/src/models/ProductVideoGenerationShrinkRequest.ts +85 -0
- package/src/models/QueryDisplayKnowledgeResponseBody.ts +3 -0
- package/src/models/SizeChartExtractAsyncRequest.ts +3 -3
- package/src/models/SizeChartExtractAsyncResponseBody.ts +7 -5
- package/src/models/SizeChartExtractAsyncShrinkRequest.ts +3 -3
- package/src/models/StorefrontSceneRecognitionRequest.ts +1 -1
- package/src/models/StorefrontSceneRecognitionResponseBody.ts +9 -6
- package/src/models/SubmitProductMatchRequest.ts +8 -8
- package/src/models/SubmitProductMatchResponseBody.ts +7 -7
- package/src/models/TextTranslateAsyncRequest.ts +9 -9
- package/src/models/TextTranslateAsyncResponseBody.ts +6 -6
- package/src/models/TextTranslateAsyncShrinkRequest.ts +9 -9
- package/src/models/UpdateDisplayKnowledgeResponseBody.ts +3 -0
- package/src/models/VacancyDetectionRequest.ts +56 -0
- package/src/models/VacancyDetectionResponse.ts +40 -0
- package/src/models/VacancyDetectionResponseBody.ts +120 -0
- package/src/models/VideoGenerationRequest.ts +18 -17
- package/src/models/VideoGenerationResponseBody.ts +2 -2
- package/src/models/VideoTranslationRequest.ts +8 -17
- package/src/models/VideoTranslationResponseBody.ts +4 -6
- package/src/models/VideoTranslationShrinkRequest.ts +8 -17
- package/src/models/VirtualTryOnResponseBody.ts +7 -6
- package/src/models/model.ts +9 -0
package/src/client.ts
CHANGED
|
@@ -86,38 +86,68 @@ export default class Client extends OpenApi {
|
|
|
86
86
|
}
|
|
87
87
|
|
|
88
88
|
/**
|
|
89
|
-
* Generates
|
|
89
|
+
* Generates virtual try-on images by using AI algorithms to replace a model\\"s clothing with a specified garment based on the input garment and model images. The operation preserves the model\\"s posture, facial features, and other visual details while ensuring a realistic and well-fitted appearance of the garment. It returns a processed image based on the provided URL of the original product image.
|
|
90
90
|
*
|
|
91
91
|
* @remarks
|
|
92
|
-
*
|
|
93
|
-
*
|
|
94
|
-
*
|
|
95
|
-
*
|
|
96
|
-
*
|
|
97
|
-
*
|
|
98
|
-
*
|
|
99
|
-
*
|
|
100
|
-
*
|
|
101
|
-
*
|
|
102
|
-
*
|
|
103
|
-
*
|
|
104
|
-
*
|
|
105
|
-
* -
|
|
106
|
-
*
|
|
107
|
-
*
|
|
108
|
-
*
|
|
109
|
-
*
|
|
110
|
-
*
|
|
111
|
-
*
|
|
112
|
-
*
|
|
113
|
-
* | **Type** | **Model image** | **Clothing image** | **Try-on result image** |
|
|
92
|
+
* # Product overview
|
|
93
|
+
* Virtual try-on is an AI-based image generation API service that replaces the clothing on a model with specified garments based on user-provided clothing and model images. It preserves the model\\"s other details and scene details without changing the model\\"s pose or facial features, ensuring a realistic and well-fitted appearance of the garments. You only need to provide the URLs of the original product images to obtain the processed images.
|
|
94
|
+
* # Scenarios
|
|
95
|
+
* * **Virtual try-on for clothing, shoes, and hats:**
|
|
96
|
+
*
|
|
97
|
+
* Supports virtual try-on for 14 categories of clothing, shoes, hats, and accessories, including tops, coats, bottoms, dresses, jumpsuits, socks, shoes, hats, earrings, necklaces, bracelets, scarves, bags, and glasses. After you upload a person image and product images, the system intelligently matches the position and proportion of the products based on the person\\"s pose and body parts to generate natural and realistic try-on effects. This intuitively displays the on-body performance of the clothing and presents a coordinated and realistic wearing effect.
|
|
98
|
+
* * **Model replacement (model skin/face replacement)**
|
|
99
|
+
*
|
|
100
|
+
* You provide the original model scene image and the face or reference image of the target model to apply the target person\\"s face to the model in the original image. This is applicable to customer-specified models, unified brand images, and character image adaptation for different markets. It also reduces the duplication of using the same model image as other merchants.
|
|
101
|
+
*
|
|
102
|
+
* * **Pose replacement (pose fission)**
|
|
103
|
+
*
|
|
104
|
+
* You provide the original model scene image and a pose reference image with a specified pose to generate the effect of the original person and outfit in the new pose. This displays the fit, silhouette, and on-body performance of the products in different poses such as standing, raising hands, and turning around.
|
|
105
|
+
* * **E-commerce product display and marketing:**
|
|
106
|
+
*
|
|
107
|
+
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional shooting, outfit changes, and post-production, and improving the production efficiency of product images.
|
|
108
|
+
* * **Online shopping experience optimization:**
|
|
109
|
+
*
|
|
110
|
+
* Consumers can preview the wearing effect of products through virtual try-on to more intuitively understand the style, matching, and overall effect of the products, assisting in purchase decisions and enhancing the shopping experience.
|
|
111
|
+
* # Features
|
|
112
|
+
* | Feature | Supported scope | User input and specification method | Scenario value |
|
|
114
113
|
* | --- | --- | --- | --- |
|
|
115
|
-
* |
|
|
116
|
-
*
|
|
117
|
-
*
|
|
118
|
-
*
|
|
119
|
-
*
|
|
120
|
-
*
|
|
114
|
+
* | **Clothing replacement/product wearing** | * Clothing: tops, bottoms (pants, skirts), coats, dresses, jumpsuits/rompers.
|
|
115
|
+
*
|
|
116
|
+
* * Shoes and hats: shoes, socks, hats.
|
|
117
|
+
*
|
|
118
|
+
* * Accessories: earrings, necklaces, bracelets, scarves, bags, glasses. | Upload a model image and product images, and the products will naturally fit the model. The system automatically matches the wearing position based on the clothing category, ensuring that the pose, proportion, and wearing layers are consistent with real human effects, while maintaining the person\\"s scene and pose in the original image.
|
|
119
|
+
* Try-on modes:
|
|
120
|
+
* * Supports single-item try-on.
|
|
121
|
+
*
|
|
122
|
+
* * Supports multi-item outfit matching (multiple items in one image or multiple items across multiple images).
|
|
123
|
+
*
|
|
124
|
+
* Note: The multi-item outfit matching capability was newly launched in November. | Uniformly generates the wearing effects of clothing, shoes, hats, and accessories, reducing item-by-item outfit changes and real-life shooting. |
|
|
125
|
+
* | **Model replacement/model skin replacement (face replacement)** | Supports user-specified target models.
|
|
126
|
+
* The original image can be a single-item try-on image or a multi-item outfit image. | Upload the original model scene image and provide one face photo or clear model reference image of the target person to replace the face and identity features of the model in the scene with those of the target person.
|
|
127
|
+
* The original outfit, pose, and scene are all preserved, and the generated result uses the person\\"s pose and background from the scene image. | Uses customer-specified or authorized model images to reduce duplication with existing model images and unify brand visuals. |
|
|
128
|
+
* | **Pose replacement/pose fission** | Generates images based on the user-specified pose.
|
|
129
|
+
* The original image can be a single-item try-on image or a multi-item outfit image. | Upload the original model scene image and one pose reference image to change the model\\"s pose to the action in the reference image. The person and outfit remain unchanged, and the wrinkles, drape, and layers of the clothing naturally adjust to the new pose. | Displays the fit, silhouette, and on-body style of the products in different poses, expanding the detail pages and marketing materials. |
|
|
130
|
+
* # 4. Effect examples
|
|
131
|
+
* | Scenario | Type/outfit description | Original model scene image | Product image/reference image | Effect image |
|
|
132
|
+
* | --- | --- | --- | --- | --- |
|
|
133
|
+
* | Single-item try-on | **Vest**
|
|
134
|
+
* Black buttoned sleeveless vest |  |  |  |
|
|
135
|
+
* | Single-item try-on | Top |  |  |  |
|
|
136
|
+
* | Single-item try-on | Bottom |  |  |  |
|
|
137
|
+
* | Single-item try-on | Shoes |  |  |  |
|
|
138
|
+
* | Single-item try-on | Jumpsuit |  |  |  |
|
|
139
|
+
* | Single-item try-on | Skirt |  |  |  |
|
|
140
|
+
* | Single-item try-on | Hat |  |  |  |
|
|
141
|
+
* | Multi-item try-on | **Two-item outfit**
|
|
142
|
+
* Dress + high heels |  |  |  |
|
|
143
|
+
* | Multi-item try-on | **Three-item outfit**
|
|
144
|
+
* Striped polo shirt + denim shorts + work boots |  |  |  |
|
|
145
|
+
* | Multi-item try-on | **Four-item outfit**
|
|
146
|
+
* Printed T-shirt + pants + hat + bag |  |  |  |
|
|
147
|
+
* | Model replacement | **Model skin/face replacement**
|
|
148
|
+
* Preserves the original top, pants, and scene |  |  |  |
|
|
149
|
+
* | Pose replacement | **Specified pose**
|
|
150
|
+
* Preserves the original outfit and adjusts to the hand-raising pose in the reference image |  |  |  |
|
|
121
151
|
*
|
|
122
152
|
* @param request - AiTryOnRequest
|
|
123
153
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -134,14 +164,34 @@ export default class Client extends OpenApi {
|
|
|
134
164
|
query["ClothType"] = request.clothType;
|
|
135
165
|
}
|
|
136
166
|
|
|
167
|
+
if (!$dara.isNull(request.mode)) {
|
|
168
|
+
query["Mode"] = request.mode;
|
|
169
|
+
}
|
|
170
|
+
|
|
137
171
|
if (!$dara.isNull(request.modelImageUrl)) {
|
|
138
172
|
query["ModelImageUrl"] = request.modelImageUrl;
|
|
139
173
|
}
|
|
140
174
|
|
|
175
|
+
if (!$dara.isNull(request.modelTemplateUrl)) {
|
|
176
|
+
query["ModelTemplateUrl"] = request.modelTemplateUrl;
|
|
177
|
+
}
|
|
178
|
+
|
|
179
|
+
if (!$dara.isNull(request.poseTemplateUrl)) {
|
|
180
|
+
query["PoseTemplateUrl"] = request.poseTemplateUrl;
|
|
181
|
+
}
|
|
182
|
+
|
|
183
|
+
if (!$dara.isNull(request.ratio)) {
|
|
184
|
+
query["Ratio"] = request.ratio;
|
|
185
|
+
}
|
|
186
|
+
|
|
141
187
|
if (!$dara.isNull(request.resolution)) {
|
|
142
188
|
query["Resolution"] = request.resolution;
|
|
143
189
|
}
|
|
144
190
|
|
|
191
|
+
if (!$dara.isNull(request.tryonType)) {
|
|
192
|
+
query["TryonType"] = request.tryonType;
|
|
193
|
+
}
|
|
194
|
+
|
|
145
195
|
let req = new $OpenApiUtil.OpenApiRequest({
|
|
146
196
|
query: OpenApiUtil.query(query),
|
|
147
197
|
});
|
|
@@ -160,38 +210,68 @@ export default class Client extends OpenApi {
|
|
|
160
210
|
}
|
|
161
211
|
|
|
162
212
|
/**
|
|
163
|
-
* Generates
|
|
213
|
+
* Generates virtual try-on images by using AI algorithms to replace a model\\"s clothing with a specified garment based on the input garment and model images. The operation preserves the model\\"s posture, facial features, and other visual details while ensuring a realistic and well-fitted appearance of the garment. It returns a processed image based on the provided URL of the original product image.
|
|
164
214
|
*
|
|
165
215
|
* @remarks
|
|
166
|
-
*
|
|
167
|
-
*
|
|
168
|
-
*
|
|
169
|
-
*
|
|
170
|
-
*
|
|
171
|
-
*
|
|
172
|
-
*
|
|
173
|
-
*
|
|
174
|
-
*
|
|
175
|
-
*
|
|
176
|
-
*
|
|
177
|
-
*
|
|
178
|
-
*
|
|
179
|
-
* -
|
|
180
|
-
*
|
|
181
|
-
*
|
|
182
|
-
*
|
|
183
|
-
*
|
|
184
|
-
*
|
|
185
|
-
*
|
|
186
|
-
*
|
|
187
|
-
* | **Type** | **Model image** | **Clothing image** | **Try-on result image** |
|
|
216
|
+
* # Product overview
|
|
217
|
+
* Virtual try-on is an AI-based image generation API service that replaces the clothing on a model with specified garments based on user-provided clothing and model images. It preserves the model\\"s other details and scene details without changing the model\\"s pose or facial features, ensuring a realistic and well-fitted appearance of the garments. You only need to provide the URLs of the original product images to obtain the processed images.
|
|
218
|
+
* # Scenarios
|
|
219
|
+
* * **Virtual try-on for clothing, shoes, and hats:**
|
|
220
|
+
*
|
|
221
|
+
* Supports virtual try-on for 14 categories of clothing, shoes, hats, and accessories, including tops, coats, bottoms, dresses, jumpsuits, socks, shoes, hats, earrings, necklaces, bracelets, scarves, bags, and glasses. After you upload a person image and product images, the system intelligently matches the position and proportion of the products based on the person\\"s pose and body parts to generate natural and realistic try-on effects. This intuitively displays the on-body performance of the clothing and presents a coordinated and realistic wearing effect.
|
|
222
|
+
* * **Model replacement (model skin/face replacement)**
|
|
223
|
+
*
|
|
224
|
+
* You provide the original model scene image and the face or reference image of the target model to apply the target person\\"s face to the model in the original image. This is applicable to customer-specified models, unified brand images, and character image adaptation for different markets. It also reduces the duplication of using the same model image as other merchants.
|
|
225
|
+
*
|
|
226
|
+
* * **Pose replacement (pose fission)**
|
|
227
|
+
*
|
|
228
|
+
* You provide the original model scene image and a pose reference image with a specified pose to generate the effect of the original person and outfit in the new pose. This displays the fit, silhouette, and on-body performance of the products in different poses such as standing, raising hands, and turning around.
|
|
229
|
+
* * **E-commerce product display and marketing:**
|
|
230
|
+
*
|
|
231
|
+
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional shooting, outfit changes, and post-production, and improving the production efficiency of product images.
|
|
232
|
+
* * **Online shopping experience optimization:**
|
|
233
|
+
*
|
|
234
|
+
* Consumers can preview the wearing effect of products through virtual try-on to more intuitively understand the style, matching, and overall effect of the products, assisting in purchase decisions and enhancing the shopping experience.
|
|
235
|
+
* # Features
|
|
236
|
+
* | Feature | Supported scope | User input and specification method | Scenario value |
|
|
188
237
|
* | --- | --- | --- | --- |
|
|
189
|
-
* |
|
|
190
|
-
*
|
|
191
|
-
*
|
|
192
|
-
*
|
|
193
|
-
*
|
|
194
|
-
*
|
|
238
|
+
* | **Clothing replacement/product wearing** | * Clothing: tops, bottoms (pants, skirts), coats, dresses, jumpsuits/rompers.
|
|
239
|
+
*
|
|
240
|
+
* * Shoes and hats: shoes, socks, hats.
|
|
241
|
+
*
|
|
242
|
+
* * Accessories: earrings, necklaces, bracelets, scarves, bags, glasses. | Upload a model image and product images, and the products will naturally fit the model. The system automatically matches the wearing position based on the clothing category, ensuring that the pose, proportion, and wearing layers are consistent with real human effects, while maintaining the person\\"s scene and pose in the original image.
|
|
243
|
+
* Try-on modes:
|
|
244
|
+
* * Supports single-item try-on.
|
|
245
|
+
*
|
|
246
|
+
* * Supports multi-item outfit matching (multiple items in one image or multiple items across multiple images).
|
|
247
|
+
*
|
|
248
|
+
* Note: The multi-item outfit matching capability was newly launched in November. | Uniformly generates the wearing effects of clothing, shoes, hats, and accessories, reducing item-by-item outfit changes and real-life shooting. |
|
|
249
|
+
* | **Model replacement/model skin replacement (face replacement)** | Supports user-specified target models.
|
|
250
|
+
* The original image can be a single-item try-on image or a multi-item outfit image. | Upload the original model scene image and provide one face photo or clear model reference image of the target person to replace the face and identity features of the model in the scene with those of the target person.
|
|
251
|
+
* The original outfit, pose, and scene are all preserved, and the generated result uses the person\\"s pose and background from the scene image. | Uses customer-specified or authorized model images to reduce duplication with existing model images and unify brand visuals. |
|
|
252
|
+
* | **Pose replacement/pose fission** | Generates images based on the user-specified pose.
|
|
253
|
+
* The original image can be a single-item try-on image or a multi-item outfit image. | Upload the original model scene image and one pose reference image to change the model\\"s pose to the action in the reference image. The person and outfit remain unchanged, and the wrinkles, drape, and layers of the clothing naturally adjust to the new pose. | Displays the fit, silhouette, and on-body style of the products in different poses, expanding the detail pages and marketing materials. |
|
|
254
|
+
* # 4. Effect examples
|
|
255
|
+
* | Scenario | Type/outfit description | Original model scene image | Product image/reference image | Effect image |
|
|
256
|
+
* | --- | --- | --- | --- | --- |
|
|
257
|
+
* | Single-item try-on | **Vest**
|
|
258
|
+
* Black buttoned sleeveless vest |  |  |  |
|
|
259
|
+
* | Single-item try-on | Top |  |  |  |
|
|
260
|
+
* | Single-item try-on | Bottom |  |  |  |
|
|
261
|
+
* | Single-item try-on | Shoes |  |  |  |
|
|
262
|
+
* | Single-item try-on | Jumpsuit |  |  |  |
|
|
263
|
+
* | Single-item try-on | Skirt |  |  |  |
|
|
264
|
+
* | Single-item try-on | Hat |  |  |  |
|
|
265
|
+
* | Multi-item try-on | **Two-item outfit**
|
|
266
|
+
* Dress + high heels |  |  |  |
|
|
267
|
+
* | Multi-item try-on | **Three-item outfit**
|
|
268
|
+
* Striped polo shirt + denim shorts + work boots |  |  |  |
|
|
269
|
+
* | Multi-item try-on | **Four-item outfit**
|
|
270
|
+
* Printed T-shirt + pants + hat + bag |  |  |  |
|
|
271
|
+
* | Model replacement | **Model skin/face replacement**
|
|
272
|
+
* Preserves the original top, pants, and scene |  |  |  |
|
|
273
|
+
* | Pose replacement | **Specified pose**
|
|
274
|
+
* Preserves the original outfit and adjusts to the hand-raising pose in the reference image |  |  |  |
|
|
195
275
|
*
|
|
196
276
|
* @param request - AiTryOnRequest
|
|
197
277
|
* @returns AiTryOnResponse
|
|
@@ -818,18 +898,18 @@ export default class Client extends OpenApi {
|
|
|
818
898
|
}
|
|
819
899
|
|
|
820
900
|
/**
|
|
821
|
-
* 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
|
|
901
|
+
* Analyzes the area of floor displays based on product recognition, SKU asset knowledge bases, and dedicated area reasoning model building. The product first locates products in floor displays, reads the actual length, width, height, and reference images of the corresponding SKUs, and infers the two side lengths and area of the bounding rectangle of the floor display area. This feature is suitable for evaluating the scale of floor displays in stores and conducting inspection reviews.
|
|
822
902
|
*
|
|
823
903
|
* @remarks
|
|
824
904
|
* *Scenarios**
|
|
825
905
|
* - 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.
|
|
826
|
-
* - Multi-SKU mixed layout analysis: Uses the dimensions of different products to infer
|
|
827
|
-
* - Area result review: Verifies the results
|
|
906
|
+
* - Multi-SKU mixed layout analysis: Uses the dimensions of different products to infer side lengths.
|
|
907
|
+
* - Area result review: Verifies the results based on the original image, product assets, and the returned two side lengths and area.
|
|
828
908
|
* **Features**
|
|
829
909
|
* - 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.
|
|
830
910
|
* - Phased area inference: Sequentially forms decision edges, SKU projections, dimension accumulation, and the final area.
|
|
831
|
-
* - Unified units: SKU asset dimensions are stored in centimeters. The
|
|
832
|
-
* - Completeness and
|
|
911
|
+
* - Unified units: SKU asset dimensions are stored in centimeters. The result side lengths are output in meters and the area is output in square meters.
|
|
912
|
+
* - Completeness and value verification: Returns a failure if assets are missing, no valid bounding boxes are found, or the area does not match the product of the side lengths.
|
|
833
913
|
*
|
|
834
914
|
* @param request - DiduiAreaDeductionProRequest
|
|
835
915
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -864,18 +944,18 @@ export default class Client extends OpenApi {
|
|
|
864
944
|
}
|
|
865
945
|
|
|
866
946
|
/**
|
|
867
|
-
* 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
|
|
947
|
+
* Analyzes the area of floor displays based on product recognition, SKU asset knowledge bases, and dedicated area reasoning model building. The product first locates products in floor displays, reads the actual length, width, height, and reference images of the corresponding SKUs, and infers the two side lengths and area of the bounding rectangle of the floor display area. This feature is suitable for evaluating the scale of floor displays in stores and conducting inspection reviews.
|
|
868
948
|
*
|
|
869
949
|
* @remarks
|
|
870
950
|
* *Scenarios**
|
|
871
951
|
* - 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.
|
|
872
|
-
* - Multi-SKU mixed layout analysis: Uses the dimensions of different products to infer
|
|
873
|
-
* - Area result review: Verifies the results
|
|
952
|
+
* - Multi-SKU mixed layout analysis: Uses the dimensions of different products to infer side lengths.
|
|
953
|
+
* - Area result review: Verifies the results based on the original image, product assets, and the returned two side lengths and area.
|
|
874
954
|
* **Features**
|
|
875
955
|
* - 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.
|
|
876
956
|
* - Phased area inference: Sequentially forms decision edges, SKU projections, dimension accumulation, and the final area.
|
|
877
|
-
* - Unified units: SKU asset dimensions are stored in centimeters. The
|
|
878
|
-
* - Completeness and
|
|
957
|
+
* - Unified units: SKU asset dimensions are stored in centimeters. The result side lengths are output in meters and the area is output in square meters.
|
|
958
|
+
* - Completeness and value verification: Returns a failure if assets are missing, no valid bounding boxes are found, or the area does not match the product of the side lengths.
|
|
879
959
|
*
|
|
880
960
|
* @param request - DiduiAreaDeductionProRequest
|
|
881
961
|
* @returns DiduiAreaDeductionProResponse
|
|
@@ -886,22 +966,29 @@ export default class Client extends OpenApi {
|
|
|
886
966
|
}
|
|
887
967
|
|
|
888
968
|
/**
|
|
889
|
-
* Translates documents
|
|
969
|
+
* Translates documents with a solution designed specifically for document translation. It supports over 150 languages and provides pivot translation capabilities with thousands of pivot combinations. It handles multi-scenario, multi-page, and highly complex document translation, but does not currently support scanned documents. It excels in the following aspects:
|
|
970
|
+
* - Content accuracy: translation accuracy, and accuracy of parameters and units.
|
|
971
|
+
* - Structural integrity: overall layout continuity, and restoration of page margins and layouts.
|
|
890
972
|
*
|
|
891
973
|
* @remarks
|
|
892
|
-
*
|
|
893
|
-
* Designed specifically for document translation, this
|
|
974
|
+
* # Product introduction
|
|
975
|
+
* Designed specifically for document translation, this service supports more than 150 languages and provides bridging translation capabilities with thousands of language combinations. It handles multi-scenario, multi-page, and highly complex document translations, but does not currently support scanned documents.
|
|
894
976
|
* It excels in the following aspects:
|
|
895
|
-
*
|
|
896
|
-
*
|
|
897
|
-
*
|
|
898
|
-
*
|
|
899
|
-
*
|
|
900
|
-
*
|
|
901
|
-
*
|
|
902
|
-
*
|
|
903
|
-
*
|
|
904
|
-
*
|
|
977
|
+
* * Content accuracy: translation accuracy, and accuracy of parameters and units.
|
|
978
|
+
*
|
|
979
|
+
* * Structural integrity: overall layout continuity, and restoration of page margins and layouts.
|
|
980
|
+
* # Scenarios
|
|
981
|
+
* Cross-border e-commerce product manuals, contracts, agreements, business proposals, qualification documents, teaching materials, courseware, and various other scenarios.
|
|
982
|
+
* # Features
|
|
983
|
+
* * Supports PDF, Word, and Excel formats. Supports source documents that contain multiple languages. For the detailed language list, see Section 4.4.
|
|
984
|
+
*
|
|
985
|
+
* * Supports the translation of text within images in documents, as well as complex translation scenarios involving other charts and special symbols.
|
|
986
|
+
*
|
|
987
|
+
* * Supports highly accurate layout restoration after translation.
|
|
988
|
+
*
|
|
989
|
+
* * Supports the translation of a single PDF or Word document with up to **800 pages**.
|
|
990
|
+
*
|
|
991
|
+
* * Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and translation omission (ABC-null value). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API to meet your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance. For detailed instructions on translation intervention, see [Full-modal translation - Translation intervention instruction manual](https://www.alibabacloud.com/help/en/aidge/full-modal-translation-translation-intervention-instruction-manual)
|
|
905
992
|
*
|
|
906
993
|
* @param request - DocumentTranslateRequest
|
|
907
994
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -944,22 +1031,29 @@ export default class Client extends OpenApi {
|
|
|
944
1031
|
}
|
|
945
1032
|
|
|
946
1033
|
/**
|
|
947
|
-
* Translates documents
|
|
1034
|
+
* Translates documents with a solution designed specifically for document translation. It supports over 150 languages and provides pivot translation capabilities with thousands of pivot combinations. It handles multi-scenario, multi-page, and highly complex document translation, but does not currently support scanned documents. It excels in the following aspects:
|
|
1035
|
+
* - Content accuracy: translation accuracy, and accuracy of parameters and units.
|
|
1036
|
+
* - Structural integrity: overall layout continuity, and restoration of page margins and layouts.
|
|
948
1037
|
*
|
|
949
1038
|
* @remarks
|
|
950
|
-
*
|
|
951
|
-
* Designed specifically for document translation, this
|
|
1039
|
+
* # Product introduction
|
|
1040
|
+
* Designed specifically for document translation, this service supports more than 150 languages and provides bridging translation capabilities with thousands of language combinations. It handles multi-scenario, multi-page, and highly complex document translations, but does not currently support scanned documents.
|
|
952
1041
|
* It excels in the following aspects:
|
|
953
|
-
*
|
|
954
|
-
*
|
|
955
|
-
*
|
|
956
|
-
*
|
|
957
|
-
*
|
|
958
|
-
*
|
|
959
|
-
*
|
|
960
|
-
*
|
|
961
|
-
*
|
|
962
|
-
*
|
|
1042
|
+
* * Content accuracy: translation accuracy, and accuracy of parameters and units.
|
|
1043
|
+
*
|
|
1044
|
+
* * Structural integrity: overall layout continuity, and restoration of page margins and layouts.
|
|
1045
|
+
* # Scenarios
|
|
1046
|
+
* Cross-border e-commerce product manuals, contracts, agreements, business proposals, qualification documents, teaching materials, courseware, and various other scenarios.
|
|
1047
|
+
* # Features
|
|
1048
|
+
* * Supports PDF, Word, and Excel formats. Supports source documents that contain multiple languages. For the detailed language list, see Section 4.4.
|
|
1049
|
+
*
|
|
1050
|
+
* * Supports the translation of text within images in documents, as well as complex translation scenarios involving other charts and special symbols.
|
|
1051
|
+
*
|
|
1052
|
+
* * Supports highly accurate layout restoration after translation.
|
|
1053
|
+
*
|
|
1054
|
+
* * Supports the translation of a single PDF or Word document with up to **800 pages**.
|
|
1055
|
+
*
|
|
1056
|
+
* * Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and translation omission (ABC-null value). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API to meet your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance. For detailed instructions on translation intervention, see [Full-modal translation - Translation intervention instruction manual](https://www.alibabacloud.com/help/en/aidge/full-modal-translation-translation-intervention-instruction-manual)
|
|
963
1057
|
*
|
|
964
1058
|
* @param request - DocumentTranslateRequest
|
|
965
1059
|
* @returns DocumentTranslateResponse
|
|
@@ -970,45 +1064,45 @@ export default class Client extends OpenApi {
|
|
|
970
1064
|
}
|
|
971
1065
|
|
|
972
1066
|
/**
|
|
973
|
-
*
|
|
1067
|
+
* Provides an AI video service for e-commerce content production, covering video understanding, element replacement, quality verification, and result delivery. The service focuses on product and person consistency, detail restoration, conversion expression, and scaled production. It supports targeted replacement of products or persons based on viral video templates, quickly generating multiple versions of content while preserving original actions, camera rhythms, and marketing structures to reduce shooting, editing, and adaptation costs.
|
|
974
1068
|
*
|
|
975
1069
|
* @remarks
|
|
976
1070
|
* ## **Product introduction**
|
|
977
|
-
* E-commerce video
|
|
1071
|
+
* E-commerce video variation is an AI video service for product content production, covering video understanding, element replacement, quality verification, and result delivery. The service focuses on product and person consistency, detail restoration, conversion expression, and scaled production. It supports targeted replacement of products or persons based on viral video templates, quickly generating multiple versions of content while preserving original actions, camera rhythms, and marketing structures to reduce shooting, editing, and adaptation costs.
|
|
978
1072
|
* ## **Scenarios**
|
|
979
|
-
* - **Video material
|
|
980
|
-
* - **
|
|
981
|
-
* - **Product explanation and selling point expression:** Suitable for products such as apparel, beauty and personal care, food and
|
|
982
|
-
* - **Multi-selling point and multi-version testing:**
|
|
983
|
-
* ## **
|
|
1073
|
+
* - **Video material variation:** Uses an existing e-commerce video as a template and replaces only specified products or persons in the video, preserving the original camera angles, rhythm, and marketing expression as much as possible. This is suitable for producing materials with multiple SKUs, models, regions, and versions.
|
|
1074
|
+
* - **New product launch and rapid material generation:** For centrally launched new products, this reduces manual shooting, studio setup, post-production editing, and repetitive production processes. It quickly deploys new product video materials, helping merchants shorten the launch cycle from spotting a viral video to breaking down the script and shooting new content.
|
|
1075
|
+
* - **Product explanation and selling point expression:** Suitable for products such as apparel, beauty and personal care, food and beverages, home and daily necessities, 3C digital products, and small home appliances. It can plan the explanation structure, display actions, and camera rhythm based on the selling points of the original video, and generate explanation videos tailored for the conversion of new products.
|
|
1076
|
+
* - **Multi-selling point and multi-version testing:** Quickly generates multiple versions based on different product selling points, target audiences, scripts, camera angles, and visual styles, supporting merchants in conducting content testing and iterating delivery materials.
|
|
1077
|
+
* ## **Feature overview**
|
|
984
1078
|
* ### **Core capabilities**
|
|
985
1079
|
* * **Supports two replacement modes:**
|
|
986
1080
|
*
|
|
987
|
-
* * **Product replacement (**`product_replacement`**)**: Preserves the identity, actions, scene, and sales structure
|
|
1081
|
+
* * **Product replacement (**`product_replacement`**)**: Preserves the original video\\"s host identity, actions, scene, and sales structure, and replaces the original product with the target product.
|
|
988
1082
|
*
|
|
989
|
-
* * **Person replacement (**`person_replacement`**)**: Preserves the product, actions, scene, and sales structure
|
|
1083
|
+
* * **Person replacement (**`person_replacement`**)**: Preserves the original video\\"s product, actions, scene, and sales structure, and replaces the on-screen person with the target person from reference images or descriptions.
|
|
990
1084
|
*
|
|
991
1085
|
* * **Supports two generation modes:**
|
|
992
1086
|
*
|
|
993
|
-
* * **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
|
|
1087
|
+
* * **Reference generation (**`reference`**)**: 1:1 replication. Uses the original video as a complete reference to automatically generate a new video with the same duration as the original video. It preserves the original script, storyboard, actions, scene, and rhythm, and only performs targeted replacement of specified content such as persons or products.
|
|
994
1088
|
*
|
|
995
|
-
* * **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
|
|
1089
|
+
* * **Rebuild generation (**`rebuild`**)**: Breaks down the script, storyboard, and key elements of the original video, retains only core content such as specified persons or products, and then redesigns and generates a new video. It is not limited by the original video duration and supports inputting a target duration.
|
|
996
1090
|
*
|
|
997
|
-
* * **Fully automated end-to-end generation with zero prompt
|
|
1091
|
+
* * **Fully automated end-to-end generation with zero prompt threshold**: Only requires passing the reference video and target product or person images. The system automatically completes the entire process of video understanding, script planning, storyboard design, first-frame generation, and video synthesis.
|
|
998
1092
|
*
|
|
999
|
-
* * **Product understanding and information structuring**: Identifies product categories, appearance, materials, colors, structures, and key components, and combines them with
|
|
1093
|
+
* * **Product understanding and information structuring**: Identifies product categories, appearance, materials, colors, structures, and key components, and combines them with titles, attributes, and selling points provided by merchants to generate usable video expression information.
|
|
1000
1094
|
*
|
|
1001
1095
|
* * **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.
|
|
1002
1096
|
*
|
|
1003
|
-
* * **Product subject consistency**: Maintains the stability of the product\\"s shape, color, texture, pattern, packaging, and logo across different camera
|
|
1097
|
+
* * **Product subject consistency**: Maintains the stability of the product\\"s shape, color, texture, pattern, packaging, and logo as much as possible across different camera angles, perspectives, actions, and scenes.
|
|
1004
1098
|
*
|
|
1005
1099
|
* * **Product fidelity**: Multi-round VL quality inspection locks the product state (color, texture, structure, print) throughout the process to prevent product feature drift.
|
|
1006
1100
|
*
|
|
1007
|
-
* * **Selling point script and storyboard replication**:
|
|
1101
|
+
* * **Selling point script and storyboard replication**: Follows the selling point planning, video structure, camera sequence, display actions, voiceover content, and ending style of the original video.
|
|
1008
1102
|
*
|
|
1009
|
-
* * **Commercial model adaptation**: Supports matching corresponding model images and
|
|
1103
|
+
* * **Commercial model adaptation**: Supports matching corresponding model images and display methods based on product style, fit, target audience, and market demand.
|
|
1010
1104
|
*
|
|
1011
|
-
* * **Quality verification and result feedback**: Performs multi-dimensional checks on the product subject, person,
|
|
1105
|
+
* * **Quality verification and result feedback**: Performs multi-dimensional checks on the product subject, person, clothing, text, picture integrity, audio, and overall usability, and outputs result information for manual review.
|
|
1012
1106
|
*
|
|
1013
1107
|
* @param tmpReq - EcomVideoRecreationRequest
|
|
1014
1108
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -1053,45 +1147,45 @@ export default class Client extends OpenApi {
|
|
|
1053
1147
|
}
|
|
1054
1148
|
|
|
1055
1149
|
/**
|
|
1056
|
-
*
|
|
1150
|
+
* Provides an AI video service for e-commerce content production, covering video understanding, element replacement, quality verification, and result delivery. The service focuses on product and person consistency, detail restoration, conversion expression, and scaled production. It supports targeted replacement of products or persons based on viral video templates, quickly generating multiple versions of content while preserving original actions, camera rhythms, and marketing structures to reduce shooting, editing, and adaptation costs.
|
|
1057
1151
|
*
|
|
1058
1152
|
* @remarks
|
|
1059
1153
|
* ## **Product introduction**
|
|
1060
|
-
* E-commerce video
|
|
1154
|
+
* E-commerce video variation is an AI video service for product content production, covering video understanding, element replacement, quality verification, and result delivery. The service focuses on product and person consistency, detail restoration, conversion expression, and scaled production. It supports targeted replacement of products or persons based on viral video templates, quickly generating multiple versions of content while preserving original actions, camera rhythms, and marketing structures to reduce shooting, editing, and adaptation costs.
|
|
1061
1155
|
* ## **Scenarios**
|
|
1062
|
-
* - **Video material
|
|
1063
|
-
* - **
|
|
1064
|
-
* - **Product explanation and selling point expression:** Suitable for products such as apparel, beauty and personal care, food and
|
|
1065
|
-
* - **Multi-selling point and multi-version testing:**
|
|
1066
|
-
* ## **
|
|
1156
|
+
* - **Video material variation:** Uses an existing e-commerce video as a template and replaces only specified products or persons in the video, preserving the original camera angles, rhythm, and marketing expression as much as possible. This is suitable for producing materials with multiple SKUs, models, regions, and versions.
|
|
1157
|
+
* - **New product launch and rapid material generation:** For centrally launched new products, this reduces manual shooting, studio setup, post-production editing, and repetitive production processes. It quickly deploys new product video materials, helping merchants shorten the launch cycle from spotting a viral video to breaking down the script and shooting new content.
|
|
1158
|
+
* - **Product explanation and selling point expression:** Suitable for products such as apparel, beauty and personal care, food and beverages, home and daily necessities, 3C digital products, and small home appliances. It can plan the explanation structure, display actions, and camera rhythm based on the selling points of the original video, and generate explanation videos tailored for the conversion of new products.
|
|
1159
|
+
* - **Multi-selling point and multi-version testing:** Quickly generates multiple versions based on different product selling points, target audiences, scripts, camera angles, and visual styles, supporting merchants in conducting content testing and iterating delivery materials.
|
|
1160
|
+
* ## **Feature overview**
|
|
1067
1161
|
* ### **Core capabilities**
|
|
1068
1162
|
* * **Supports two replacement modes:**
|
|
1069
1163
|
*
|
|
1070
|
-
* * **Product replacement (**`product_replacement`**)**: Preserves the identity, actions, scene, and sales structure
|
|
1164
|
+
* * **Product replacement (**`product_replacement`**)**: Preserves the original video\\"s host identity, actions, scene, and sales structure, and replaces the original product with the target product.
|
|
1071
1165
|
*
|
|
1072
|
-
* * **Person replacement (**`person_replacement`**)**: Preserves the product, actions, scene, and sales structure
|
|
1166
|
+
* * **Person replacement (**`person_replacement`**)**: Preserves the original video\\"s product, actions, scene, and sales structure, and replaces the on-screen person with the target person from reference images or descriptions.
|
|
1073
1167
|
*
|
|
1074
1168
|
* * **Supports two generation modes:**
|
|
1075
1169
|
*
|
|
1076
|
-
* * **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
|
|
1170
|
+
* * **Reference generation (**`reference`**)**: 1:1 replication. Uses the original video as a complete reference to automatically generate a new video with the same duration as the original video. It preserves the original script, storyboard, actions, scene, and rhythm, and only performs targeted replacement of specified content such as persons or products.
|
|
1077
1171
|
*
|
|
1078
|
-
* * **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
|
|
1172
|
+
* * **Rebuild generation (**`rebuild`**)**: Breaks down the script, storyboard, and key elements of the original video, retains only core content such as specified persons or products, and then redesigns and generates a new video. It is not limited by the original video duration and supports inputting a target duration.
|
|
1079
1173
|
*
|
|
1080
|
-
* * **Fully automated end-to-end generation with zero prompt
|
|
1174
|
+
* * **Fully automated end-to-end generation with zero prompt threshold**: Only requires passing the reference video and target product or person images. The system automatically completes the entire process of video understanding, script planning, storyboard design, first-frame generation, and video synthesis.
|
|
1081
1175
|
*
|
|
1082
|
-
* * **Product understanding and information structuring**: Identifies product categories, appearance, materials, colors, structures, and key components, and combines them with
|
|
1176
|
+
* * **Product understanding and information structuring**: Identifies product categories, appearance, materials, colors, structures, and key components, and combines them with titles, attributes, and selling points provided by merchants to generate usable video expression information.
|
|
1083
1177
|
*
|
|
1084
1178
|
* * **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.
|
|
1085
1179
|
*
|
|
1086
|
-
* * **Product subject consistency**: Maintains the stability of the product\\"s shape, color, texture, pattern, packaging, and logo across different camera
|
|
1180
|
+
* * **Product subject consistency**: Maintains the stability of the product\\"s shape, color, texture, pattern, packaging, and logo as much as possible across different camera angles, perspectives, actions, and scenes.
|
|
1087
1181
|
*
|
|
1088
1182
|
* * **Product fidelity**: Multi-round VL quality inspection locks the product state (color, texture, structure, print) throughout the process to prevent product feature drift.
|
|
1089
1183
|
*
|
|
1090
|
-
* * **Selling point script and storyboard replication**:
|
|
1184
|
+
* * **Selling point script and storyboard replication**: Follows the selling point planning, video structure, camera sequence, display actions, voiceover content, and ending style of the original video.
|
|
1091
1185
|
*
|
|
1092
|
-
* * **Commercial model adaptation**: Supports matching corresponding model images and
|
|
1186
|
+
* * **Commercial model adaptation**: Supports matching corresponding model images and display methods based on product style, fit, target audience, and market demand.
|
|
1093
1187
|
*
|
|
1094
|
-
* * **Quality verification and result feedback**: Performs multi-dimensional checks on the product subject, person,
|
|
1188
|
+
* * **Quality verification and result feedback**: Performs multi-dimensional checks on the product subject, person, clothing, text, picture integrity, audio, and overall usability, and outputs result information for manual review.
|
|
1095
1189
|
*
|
|
1096
1190
|
* @param request - EcomVideoRecreationRequest
|
|
1097
1191
|
* @returns EcomVideoRecreationResponse
|
|
@@ -1102,18 +1196,18 @@ export default class Client extends OpenApi {
|
|
|
1102
1196
|
}
|
|
1103
1197
|
|
|
1104
1198
|
/**
|
|
1105
|
-
* Detects whether an image is recaptured and
|
|
1199
|
+
* Detects whether an image is recaptured and locates main physical products, screen display areas, printed photos, and visible recapture clues based on recapture recognition and multimodal large model element localization. This general-purpose image moderation service applies to risk screening and manual review of store inspection photos across multiple categories.
|
|
1106
1200
|
*
|
|
1107
1201
|
* @remarks
|
|
1108
1202
|
* *Scenarios**
|
|
1109
|
-
* 1. Inspection photo review: Screens
|
|
1110
|
-
* 2. Screen or printed photo recapture verification:
|
|
1203
|
+
* 1. Inspection photo review: Screens photos submitted by stores for recapture risks.
|
|
1204
|
+
* 2. Screen or printed photo recapture verification: Locates visible screens, printed photos, and other media.
|
|
1111
1205
|
* 3. Review clue display: Annotates products and visible clues on the original image to assist in manual review.
|
|
1112
1206
|
* **Features**
|
|
1113
|
-
* 1. General recapture detection: Outputs a Boolean
|
|
1207
|
+
* 1. General recapture detection: Outputs a Boolean conclusion for isFake.
|
|
1114
1208
|
* 2. Review element localization: Distinguishes physical products, screens, printed photos, and visible recapture clues. Products inside screens are not repeatedly output as physical products.
|
|
1115
1209
|
* 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.
|
|
1116
|
-
* Supports
|
|
1210
|
+
* Supports single HTTPS image input. Supplementary localization returns up to 12 targets. Each target includes a category, a bounding box, and up to 24 characters of visible text, and uses coverage to indicate whether the localization is complete.
|
|
1117
1211
|
*
|
|
1118
1212
|
* @param request - GeneralRephotographyDetectionRequest
|
|
1119
1213
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -1144,18 +1238,18 @@ export default class Client extends OpenApi {
|
|
|
1144
1238
|
}
|
|
1145
1239
|
|
|
1146
1240
|
/**
|
|
1147
|
-
* Detects whether an image is recaptured and
|
|
1241
|
+
* Detects whether an image is recaptured and locates main physical products, screen display areas, printed photos, and visible recapture clues based on recapture recognition and multimodal large model element localization. This general-purpose image moderation service applies to risk screening and manual review of store inspection photos across multiple categories.
|
|
1148
1242
|
*
|
|
1149
1243
|
* @remarks
|
|
1150
1244
|
* *Scenarios**
|
|
1151
|
-
* 1. Inspection photo review: Screens
|
|
1152
|
-
* 2. Screen or printed photo recapture verification:
|
|
1245
|
+
* 1. Inspection photo review: Screens photos submitted by stores for recapture risks.
|
|
1246
|
+
* 2. Screen or printed photo recapture verification: Locates visible screens, printed photos, and other media.
|
|
1153
1247
|
* 3. Review clue display: Annotates products and visible clues on the original image to assist in manual review.
|
|
1154
1248
|
* **Features**
|
|
1155
|
-
* 1. General recapture detection: Outputs a Boolean
|
|
1249
|
+
* 1. General recapture detection: Outputs a Boolean conclusion for isFake.
|
|
1156
1250
|
* 2. Review element localization: Distinguishes physical products, screens, printed photos, and visible recapture clues. Products inside screens are not repeatedly output as physical products.
|
|
1157
1251
|
* 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.
|
|
1158
|
-
* Supports
|
|
1252
|
+
* Supports single HTTPS image input. Supplementary localization returns up to 12 targets. Each target includes a category, a bounding box, and up to 24 characters of visible text, and uses coverage to indicate whether the localization is complete.
|
|
1159
1253
|
*
|
|
1160
1254
|
* @param request - GeneralRephotographyDetectionRequest
|
|
1161
1255
|
* @returns GeneralRephotographyDetectionResponse
|
|
@@ -1166,22 +1260,22 @@ export default class Client extends OpenApi {
|
|
|
1166
1260
|
}
|
|
1167
1261
|
|
|
1168
1262
|
/**
|
|
1169
|
-
* Generates or rewrites e-commerce product copy,
|
|
1263
|
+
* Generates or rewrites e-commerce product copy, such as titles, short highlights, search keywords, bulleted selling points, and product descriptions, based on input product information or existing copy, and adapts the content type and length to the requirements of the target platform. Supports Chinese and English input materials and optional multilingual translation for scenarios such as domestic product listing, cross-border product distribution, and product copy localization. Uses synchronous invocation to process one copy type for a single product per request.
|
|
1170
1264
|
*
|
|
1171
1265
|
* @remarks
|
|
1172
1266
|
* # Product introduction
|
|
1173
|
-
*
|
|
1174
|
-
*
|
|
1267
|
+
* E-commerce product copy generation is an AI text service for e-commerce product content production. By inputting product materials or existing copy, you can generate or rewrite product titles, short highlights, search keywords, bullet points, and product descriptions, and adapt the content type and length to the target platform as needed.
|
|
1268
|
+
* It supports Chinese and English material inputs and optional multilingual translation, and applies to scenarios such as domestic product listing, cross-border distribution, and product copy localization. The API uses synchronous calls and processes one copy type for one product per request.
|
|
1175
1269
|
* # Scenarios
|
|
1176
1270
|
* | **Scenario** | **Description** |
|
|
1177
1271
|
* | --- | --- |
|
|
1178
|
-
* | Same-platform localization | Select rewrite
|
|
1272
|
+
* | Same-platform localization | Select rewrite and translate as needed to retain the original facts and type structure. |
|
|
1179
1273
|
* | 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. |
|
|
1180
|
-
* | New product material
|
|
1181
|
-
* | Batch operation tool integration | The caller submits requests product by product. The workflow itself does not provide batch task or
|
|
1274
|
+
* | New product material production | Select generate to generate the target type based on product materials. Categories and attributes can be used to supplement facts. |
|
|
1275
|
+
* | Batch operation tool integration | The caller submits requests product by product. The workflow itself does not provide batch task or queue APIs. |
|
|
1182
1276
|
* # Features
|
|
1183
1277
|
* ## Core capabilities
|
|
1184
|
-
* This capability supports the
|
|
1278
|
+
* This capability supports the production of different copy content types in domestic and cross-border e-commerce scenarios. It can produce titles, detailed descriptions, keywords, highlights, and descriptions that adapt to the content rules (length requirements and writing styles) of different platforms, and supports cross-language production.
|
|
1185
1279
|
* | Content type | Platform | | | | | | Target language |
|
|
1186
1280
|
* | --- | --- | --- | --- | --- | --- | --- | --- |
|
|
1187
1281
|
* | | Amazon | Temu | TikTok | Shopify | Wildberries | Tmall |
|
|
@@ -1191,19 +1285,19 @@ export default class Client extends OpenApi {
|
|
|
1191
1285
|
* | **bulletPoint** | ✓ | | | ✓ | | |
|
|
1192
1286
|
* | **keywords** | ✓ | | | | | |
|
|
1193
1287
|
* | **description** | ✓ | ✓ | ✓ | ✓ | ✓ | |
|
|
1194
|
-
* Based on the
|
|
1288
|
+
* Based on the content inputs provided by users, two production modes are supported:
|
|
1195
1289
|
* | **Mode** | **Description** | **Recommended scenario** |
|
|
1196
1290
|
* | --- | --- | --- |
|
|
1197
|
-
* | Generate | Reorganizes and writes copy based on product
|
|
1198
|
-
* | Rewrite | Retains the original information and main structure
|
|
1291
|
+
* | Generate | Reorganizes and writes copy based on product materials. | Only product parameters, attributes, or selling points are available, or other types of product materials are available, and new titles, keywords, product descriptions, and other copy need to be created. |
|
|
1292
|
+
* | Rewrite | Retains the original information and main structure, and optimizes the expression. | Existing product copy is available, and you want to adjust the wording, improve readability, or localize it with translation. |
|
|
1199
1293
|
* # Examples
|
|
1200
1294
|
* The following examples use the Amazon platform:
|
|
1201
1295
|
* | **Content type** | **Source language** | **Source content** | **Target language** | **Generated result** | **Capability advantage** |
|
|
1202
1296
|
* | --- | --- | --- | --- | --- | --- |
|
|
1203
|
-
* | 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
|
|
1297
|
+
* | bulletPoint | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | [Vielseitiges Harz-Filtersystem\\] Silikontrichter und Metallfiltergitter für 3D-Druck; Einfüllen von gebrauchtem lichtempfindlichem Harz in Flaschen mit 15 mm Halsweite | Extracts core selling points, retains key information such as bottle neck size, and presents it in German bullet points for quick reading. |
|
|
1204
1298
|
* | 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. |
|
|
1205
|
-
* | 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 |
|
|
1206
|
-
* | 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
|
|
1299
|
+
* | highlight | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | [Vielseitiges Harz-Filtrationssystem\\] Silikontrichter, Metallfilternetz, für 3D-Druck-Harz | Simplifies long materials, highlights core components and purposes, and makes it easy to grasp product features at a glance. |
|
|
1300
|
+
* | keywords | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | Silikontrichter Metallfilter Harz Filterungssystem 3D Drucker Harz umfüllen Metall Sieb für Photosensitive Harze | Extracts German search terms related to materials, categories, and purposes to reduce manual sorting and translation. |
|
|
1207
1301
|
* | 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. |
|
|
1208
1302
|
*
|
|
1209
1303
|
* @param request - GenerateProductContentRequest
|
|
@@ -1279,22 +1373,22 @@ export default class Client extends OpenApi {
|
|
|
1279
1373
|
}
|
|
1280
1374
|
|
|
1281
1375
|
/**
|
|
1282
|
-
* Generates or rewrites e-commerce product copy,
|
|
1376
|
+
* Generates or rewrites e-commerce product copy, such as titles, short highlights, search keywords, bulleted selling points, and product descriptions, based on input product information or existing copy, and adapts the content type and length to the requirements of the target platform. Supports Chinese and English input materials and optional multilingual translation for scenarios such as domestic product listing, cross-border product distribution, and product copy localization. Uses synchronous invocation to process one copy type for a single product per request.
|
|
1283
1377
|
*
|
|
1284
1378
|
* @remarks
|
|
1285
1379
|
* # Product introduction
|
|
1286
|
-
*
|
|
1287
|
-
*
|
|
1380
|
+
* E-commerce product copy generation is an AI text service for e-commerce product content production. By inputting product materials or existing copy, you can generate or rewrite product titles, short highlights, search keywords, bullet points, and product descriptions, and adapt the content type and length to the target platform as needed.
|
|
1381
|
+
* It supports Chinese and English material inputs and optional multilingual translation, and applies to scenarios such as domestic product listing, cross-border distribution, and product copy localization. The API uses synchronous calls and processes one copy type for one product per request.
|
|
1288
1382
|
* # Scenarios
|
|
1289
1383
|
* | **Scenario** | **Description** |
|
|
1290
1384
|
* | --- | --- |
|
|
1291
|
-
* | Same-platform localization | Select rewrite
|
|
1385
|
+
* | Same-platform localization | Select rewrite and translate as needed to retain the original facts and type structure. |
|
|
1292
1386
|
* | 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. |
|
|
1293
|
-
* | New product material
|
|
1294
|
-
* | Batch operation tool integration | The caller submits requests product by product. The workflow itself does not provide batch task or
|
|
1387
|
+
* | New product material production | Select generate to generate the target type based on product materials. Categories and attributes can be used to supplement facts. |
|
|
1388
|
+
* | Batch operation tool integration | The caller submits requests product by product. The workflow itself does not provide batch task or queue APIs. |
|
|
1295
1389
|
* # Features
|
|
1296
1390
|
* ## Core capabilities
|
|
1297
|
-
* This capability supports the
|
|
1391
|
+
* This capability supports the production of different copy content types in domestic and cross-border e-commerce scenarios. It can produce titles, detailed descriptions, keywords, highlights, and descriptions that adapt to the content rules (length requirements and writing styles) of different platforms, and supports cross-language production.
|
|
1298
1392
|
* | Content type | Platform | | | | | | Target language |
|
|
1299
1393
|
* | --- | --- | --- | --- | --- | --- | --- | --- |
|
|
1300
1394
|
* | | Amazon | Temu | TikTok | Shopify | Wildberries | Tmall |
|
|
@@ -1304,19 +1398,19 @@ export default class Client extends OpenApi {
|
|
|
1304
1398
|
* | **bulletPoint** | ✓ | | | ✓ | | |
|
|
1305
1399
|
* | **keywords** | ✓ | | | | | |
|
|
1306
1400
|
* | **description** | ✓ | ✓ | ✓ | ✓ | ✓ | |
|
|
1307
|
-
* Based on the
|
|
1401
|
+
* Based on the content inputs provided by users, two production modes are supported:
|
|
1308
1402
|
* | **Mode** | **Description** | **Recommended scenario** |
|
|
1309
1403
|
* | --- | --- | --- |
|
|
1310
|
-
* | Generate | Reorganizes and writes copy based on product
|
|
1311
|
-
* | Rewrite | Retains the original information and main structure
|
|
1404
|
+
* | Generate | Reorganizes and writes copy based on product materials. | Only product parameters, attributes, or selling points are available, or other types of product materials are available, and new titles, keywords, product descriptions, and other copy need to be created. |
|
|
1405
|
+
* | Rewrite | Retains the original information and main structure, and optimizes the expression. | Existing product copy is available, and you want to adjust the wording, improve readability, or localize it with translation. |
|
|
1312
1406
|
* # Examples
|
|
1313
1407
|
* The following examples use the Amazon platform:
|
|
1314
1408
|
* | **Content type** | **Source language** | **Source content** | **Target language** | **Generated result** | **Capability advantage** |
|
|
1315
1409
|
* | --- | --- | --- | --- | --- | --- |
|
|
1316
|
-
* | 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
|
|
1410
|
+
* | bulletPoint | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | [Vielseitiges Harz-Filtersystem\\] Silikontrichter und Metallfiltergitter für 3D-Druck; Einfüllen von gebrauchtem lichtempfindlichem Harz in Flaschen mit 15 mm Halsweite | Extracts core selling points, retains key information such as bottle neck size, and presents it in German bullet points for quick reading. |
|
|
1317
1411
|
* | 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. |
|
|
1318
|
-
* | 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 |
|
|
1319
|
-
* | 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
|
|
1412
|
+
* | highlight | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | [Vielseitiges Harz-Filtrationssystem\\] Silikontrichter, Metallfilternetz, für 3D-Druck-Harz | Simplifies long materials, highlights core components and purposes, and makes it easy to grasp product features at a glance. |
|
|
1413
|
+
* | keywords | en | [VERSATILE RESIN FILTRATION SYSTEM\\] This silicone funnel and metal filter mesh combination is designed for all 3D printing enthusiasts. It is ideal for pouring used photosensitive resin back into standard bottles with a 15mm neck width ensuring a clean transfer every time. The durable metal filter effectively catches all solidified debris protecting your valuable resin from and extending its usability. | de | Silikontrichter Metallfilter Harz Filterungssystem 3D Drucker Harz umfüllen Metall Sieb für Photosensitive Harze | Extracts German search terms related to materials, categories, and purposes to reduce manual sorting and translation. |
|
|
1320
1414
|
* | 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. |
|
|
1321
1415
|
*
|
|
1322
1416
|
* @param request - GenerateProductContentRequest
|
|
@@ -1522,24 +1616,24 @@ export default class Client extends OpenApi {
|
|
|
1522
1616
|
}
|
|
1523
1617
|
|
|
1524
1618
|
/**
|
|
1525
|
-
*
|
|
1619
|
+
* Automatically identifies the salient subject in an image, separates the subject from the background, and returns the subject image with the background removed. This operation also provides multiple background options and custom size options to optimize product displays.
|
|
1526
1620
|
*
|
|
1527
1621
|
* @remarks
|
|
1528
1622
|
* # Scenarios
|
|
1529
1623
|
* * Supports secondary editing of materials: After separating the image subject from the background, you can further edit the image.
|
|
1530
1624
|
*
|
|
1531
|
-
* * Improves material processing efficiency: Quickly extracts the subjects of various material images
|
|
1625
|
+
* * Improves material processing efficiency: Quickly extracts the subjects of various material images for background replacement, improving the production efficiency of advertising images and marketing posters.
|
|
1532
1626
|
* # Features.
|
|
1533
|
-
* #### 1. One-click
|
|
1534
|
-
* * **AI-based automatic recognition**: Based on deep learning models, intelligently distinguishes foreground subjects (portraits, products, objects, etc.) from the background without manual outlining.
|
|
1627
|
+
* #### 1. One-click accurate subject recognition
|
|
1628
|
+
* * **AI-based automatic recognition**: Based on deep learning models, it intelligently distinguishes foreground subjects (portraits, products, objects, etc.) from the background without manual outlining.
|
|
1535
1629
|
*
|
|
1536
|
-
* * **Multi-scenario adaptation**: Supports
|
|
1630
|
+
* * **Multi-scenario adaptation**: Supports accurate segmentation in complex scenarios (such as hair, transparent objects, and fur edges) with an accuracy rate of over 95%.
|
|
1537
1631
|
* #### 2. Intelligent edge optimization
|
|
1538
1632
|
* * **Detail-level processing**: Performs automatic optimization on edge jaggies and semi-transparent areas (such as smoke and glass) to retain natural transition effects.
|
|
1539
1633
|
* #### 3. Multi-format output and background operations
|
|
1540
1634
|
* * **Transparent background export**: Directly generates PNG images with transparent backgrounds and white backgrounds, adapting to e-commerce and design scenarios.
|
|
1541
1635
|
*
|
|
1542
|
-
* * **
|
|
1636
|
+
* * **Custom background color support**
|
|
1543
1637
|
* # Effect comparison
|
|
1544
1638
|
* | **Original image (input)** | **Result image (output)** |
|
|
1545
1639
|
* | --- | --- |
|
|
@@ -1596,24 +1690,24 @@ export default class Client extends OpenApi {
|
|
|
1596
1690
|
}
|
|
1597
1691
|
|
|
1598
1692
|
/**
|
|
1599
|
-
*
|
|
1693
|
+
* Automatically identifies the salient subject in an image, separates the subject from the background, and returns the subject image with the background removed. This operation also provides multiple background options and custom size options to optimize product displays.
|
|
1600
1694
|
*
|
|
1601
1695
|
* @remarks
|
|
1602
1696
|
* # Scenarios
|
|
1603
1697
|
* * Supports secondary editing of materials: After separating the image subject from the background, you can further edit the image.
|
|
1604
1698
|
*
|
|
1605
|
-
* * Improves material processing efficiency: Quickly extracts the subjects of various material images
|
|
1699
|
+
* * Improves material processing efficiency: Quickly extracts the subjects of various material images for background replacement, improving the production efficiency of advertising images and marketing posters.
|
|
1606
1700
|
* # Features.
|
|
1607
|
-
* #### 1. One-click
|
|
1608
|
-
* * **AI-based automatic recognition**: Based on deep learning models, intelligently distinguishes foreground subjects (portraits, products, objects, etc.) from the background without manual outlining.
|
|
1701
|
+
* #### 1. One-click accurate subject recognition
|
|
1702
|
+
* * **AI-based automatic recognition**: Based on deep learning models, it intelligently distinguishes foreground subjects (portraits, products, objects, etc.) from the background without manual outlining.
|
|
1609
1703
|
*
|
|
1610
|
-
* * **Multi-scenario adaptation**: Supports
|
|
1704
|
+
* * **Multi-scenario adaptation**: Supports accurate segmentation in complex scenarios (such as hair, transparent objects, and fur edges) with an accuracy rate of over 95%.
|
|
1611
1705
|
* #### 2. Intelligent edge optimization
|
|
1612
1706
|
* * **Detail-level processing**: Performs automatic optimization on edge jaggies and semi-transparent areas (such as smoke and glass) to retain natural transition effects.
|
|
1613
1707
|
* #### 3. Multi-format output and background operations
|
|
1614
1708
|
* * **Transparent background export**: Directly generates PNG images with transparent backgrounds and white backgrounds, adapting to e-commerce and design scenarios.
|
|
1615
1709
|
*
|
|
1616
|
-
* * **
|
|
1710
|
+
* * **Custom background color support**
|
|
1617
1711
|
* # Effect comparison
|
|
1618
1712
|
* | **Original image (input)** | **Result image (output)** |
|
|
1619
1713
|
* | --- | --- |
|
|
@@ -1846,15 +1940,15 @@ export default class Client extends OpenApi {
|
|
|
1846
1940
|
}
|
|
1847
1941
|
|
|
1848
1942
|
/**
|
|
1849
|
-
* Identifies specific elements in e-commerce images.
|
|
1943
|
+
* Identifies specific elements in e-commerce images. This API extracts image details to help users quickly identify text, logos, watermarks, and text-containing color blocks in the main subject and background, significantly improving the efficiency and accuracy of image filtering.
|
|
1850
1944
|
*
|
|
1851
1945
|
* @remarks
|
|
1852
1946
|
* # Scenarios
|
|
1853
1947
|
* 1. Intelligent image filtering and optimization:
|
|
1854
|
-
* 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
|
|
1948
|
+
* 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.
|
|
1855
1949
|
* 2. Automated image processing and efficiency improvement:
|
|
1856
1950
|
* 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.
|
|
1857
|
-
* #
|
|
1951
|
+
* # Feature description
|
|
1858
1952
|
* **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).**
|
|
1859
1953
|
* * Image subject: The core product area in the image.
|
|
1860
1954
|
*
|
|
@@ -1864,11 +1958,11 @@ export default class Client extends OpenApi {
|
|
|
1864
1958
|
*
|
|
1865
1959
|
* * Logo: A logo or trademark.
|
|
1866
1960
|
*
|
|
1867
|
-
* * Watermark: Monochrome transparent text, logos, images, URLs,
|
|
1961
|
+
* * Watermark: Monochrome transparent text, logos, images, URLs, store names, etc.
|
|
1868
1962
|
*
|
|
1869
|
-
* * Text-containing color block: A color block containing text outside the subject.
|
|
1963
|
+
* * Text-containing color block: A color block containing text outside the main subject.
|
|
1870
1964
|
*
|
|
1871
|
-
* **2. The
|
|
1965
|
+
* **2. The intelligent element recognition API provides the following features:**
|
|
1872
1966
|
* * Element recognition: Identifies whether elements such as text, logos, watermarks, and text-containing color blocks exist in the image subject and background.
|
|
1873
1967
|
*
|
|
1874
1968
|
* * 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.
|
|
@@ -1986,15 +2080,15 @@ export default class Client extends OpenApi {
|
|
|
1986
2080
|
}
|
|
1987
2081
|
|
|
1988
2082
|
/**
|
|
1989
|
-
* Identifies specific elements in e-commerce images.
|
|
2083
|
+
* Identifies specific elements in e-commerce images. This API extracts image details to help users quickly identify text, logos, watermarks, and text-containing color blocks in the main subject and background, significantly improving the efficiency and accuracy of image filtering.
|
|
1990
2084
|
*
|
|
1991
2085
|
* @remarks
|
|
1992
2086
|
* # Scenarios
|
|
1993
2087
|
* 1. Intelligent image filtering and optimization:
|
|
1994
|
-
* 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
|
|
2088
|
+
* 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.
|
|
1995
2089
|
* 2. Automated image processing and efficiency improvement:
|
|
1996
2090
|
* 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.
|
|
1997
|
-
* #
|
|
2091
|
+
* # Feature description
|
|
1998
2092
|
* **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).**
|
|
1999
2093
|
* * Image subject: The core product area in the image.
|
|
2000
2094
|
*
|
|
@@ -2004,11 +2098,11 @@ export default class Client extends OpenApi {
|
|
|
2004
2098
|
*
|
|
2005
2099
|
* * Logo: A logo or trademark.
|
|
2006
2100
|
*
|
|
2007
|
-
* * Watermark: Monochrome transparent text, logos, images, URLs,
|
|
2101
|
+
* * Watermark: Monochrome transparent text, logos, images, URLs, store names, etc.
|
|
2008
2102
|
*
|
|
2009
|
-
* * Text-containing color block: A color block containing text outside the subject.
|
|
2103
|
+
* * Text-containing color block: A color block containing text outside the main subject.
|
|
2010
2104
|
*
|
|
2011
|
-
* **2. The
|
|
2105
|
+
* **2. The intelligent element recognition API provides the following features:**
|
|
2012
2106
|
* * Element recognition: Identifies whether elements such as text, logos, watermarks, and text-containing color blocks exist in the image subject and background.
|
|
2013
2107
|
*
|
|
2014
2108
|
* * 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.
|
|
@@ -2158,27 +2252,27 @@ export default class Client extends OpenApi {
|
|
|
2158
2252
|
}
|
|
2159
2253
|
|
|
2160
2254
|
/**
|
|
2161
|
-
*
|
|
2255
|
+
* Provides intelligent image erasure tailored for e-commerce images, automatically identifying and removing text, specific names, transparent text blocks, and unwanted overlays. It allows you to specify objects to remove as needed, enabling efficient and precise processing of large image batches and simplifying image editing workflows.
|
|
2162
2256
|
*
|
|
2163
2257
|
* @remarks
|
|
2164
2258
|
* ## Scenarios
|
|
2165
|
-
* * **Efficient e-commerce
|
|
2259
|
+
* * **Efficient processing of e-commerce images:**
|
|
2166
2260
|
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
2167
|
-
* * **
|
|
2168
|
-
*
|
|
2261
|
+
* * **Synchronization of product information across multiple platforms:**
|
|
2262
|
+
* When merchants list products on different e-commerce platforms, they can quickly remove specific text and watermarks to comply with the image specifications of different platforms.
|
|
2169
2263
|
* ## Features
|
|
2170
|
-
* 1. First,
|
|
2264
|
+
* 1. First, clarify the definitions of the image subject and the image background. When specifying the objects to remove, you can choose to remove them from the image subject or the image background. Both API and editor integration methods are supported.
|
|
2171
2265
|
*
|
|
2172
|
-
* 1. Image subject:
|
|
2266
|
+
* 1. Image subject: The core product area in the image.
|
|
2173
2267
|
*
|
|
2174
|
-
* 2. Image background:
|
|
2268
|
+
* 2. Image background: The rest of the image excluding the product subject.
|
|
2175
2269
|
*
|
|
2176
|
-
* 2. Second, the objects to be removed
|
|
2177
|
-
* ##
|
|
2270
|
+
* 2. Second, the objects to be removed support the following four types: text, specific names, transparent text blocks, and watermarks. Refer to the following examples to clarify your requirements and perform targeted operations:
|
|
2271
|
+
* ## Before and after
|
|
2178
2272
|
* | **Original image** | **Processed image** |
|
|
2179
2273
|
* | --- | --- |
|
|
2180
|
-
* |  |  |
|
|
2275
|
+
* |  |  |
|
|
2182
2276
|
*
|
|
2183
2277
|
* @param request - ImageRemovalProAsyncRequest
|
|
2184
2278
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -2213,27 +2307,27 @@ export default class Client extends OpenApi {
|
|
|
2213
2307
|
}
|
|
2214
2308
|
|
|
2215
2309
|
/**
|
|
2216
|
-
*
|
|
2310
|
+
* Provides intelligent image erasure tailored for e-commerce images, automatically identifying and removing text, specific names, transparent text blocks, and unwanted overlays. It allows you to specify objects to remove as needed, enabling efficient and precise processing of large image batches and simplifying image editing workflows.
|
|
2217
2311
|
*
|
|
2218
2312
|
* @remarks
|
|
2219
2313
|
* ## Scenarios
|
|
2220
|
-
* * **Efficient e-commerce
|
|
2314
|
+
* * **Efficient processing of e-commerce images:**
|
|
2221
2315
|
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
2222
|
-
* * **
|
|
2223
|
-
*
|
|
2316
|
+
* * **Synchronization of product information across multiple platforms:**
|
|
2317
|
+
* When merchants list products on different e-commerce platforms, they can quickly remove specific text and watermarks to comply with the image specifications of different platforms.
|
|
2224
2318
|
* ## Features
|
|
2225
|
-
* 1. First,
|
|
2319
|
+
* 1. First, clarify the definitions of the image subject and the image background. When specifying the objects to remove, you can choose to remove them from the image subject or the image background. Both API and editor integration methods are supported.
|
|
2226
2320
|
*
|
|
2227
|
-
* 1. Image subject:
|
|
2321
|
+
* 1. Image subject: The core product area in the image.
|
|
2228
2322
|
*
|
|
2229
|
-
* 2. Image background:
|
|
2323
|
+
* 2. Image background: The rest of the image excluding the product subject.
|
|
2230
2324
|
*
|
|
2231
|
-
* 2. Second, the objects to be removed
|
|
2232
|
-
* ##
|
|
2325
|
+
* 2. Second, the objects to be removed support the following four types: text, specific names, transparent text blocks, and watermarks. Refer to the following examples to clarify your requirements and perform targeted operations:
|
|
2326
|
+
* ## Before and after
|
|
2233
2327
|
* | **Original image** | **Processed image** |
|
|
2234
2328
|
* | --- | --- |
|
|
2235
|
-
* |  |  |
|
|
2330
|
+
* |  |  |
|
|
2237
2331
|
*
|
|
2238
2332
|
* @param request - ImageRemovalProAsyncRequest
|
|
2239
2333
|
* @returns ImageRemovalProAsyncResponse
|
|
@@ -2496,35 +2590,35 @@ export default class Client extends OpenApi {
|
|
|
2496
2590
|
}
|
|
2497
2591
|
|
|
2498
2592
|
/**
|
|
2499
|
-
*
|
|
2593
|
+
* Provides intelligent object removal tailored for e-commerce images. It automatically identifies and removes text, specific names, transparent text blocks, and watermarks. You can also specify objects for removal as needed, enabling efficient and accurate processing of large image batches and simplifying image editing workflows.
|
|
2500
2594
|
*
|
|
2501
2595
|
* @remarks
|
|
2502
2596
|
* ## Scenarios
|
|
2503
2597
|
* * **Efficient processing of e-commerce images:**
|
|
2504
2598
|
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
2505
2599
|
* * **Multi-platform product information synchronization:**
|
|
2506
|
-
* When merchants
|
|
2600
|
+
* When merchants list products on different e-commerce platforms, they can quickly remove specific text and watermarks to comply with the image specifications of different platforms.
|
|
2507
2601
|
* * **Marketing material preparation:**
|
|
2508
2602
|
* Merchants can easily remove original promotional information and quickly update it with the latest campaign information.
|
|
2509
|
-
* > Note: Merchants or platforms can
|
|
2603
|
+
* > Note: Merchants or platforms can remove impurities from images in batches to optimize image quality. Use this API in combination with the Intelligent Recognition API (coming soon) to first filter images containing text, specific names, transparent text blocks, and watermarks, and then use the Intelligent Erasure API for batch removal. The Intelligent Recognition API focuses on recognition, while the Intelligent Erasure API focuses on erasure. Calling them in sequence maximizes the erasure effect and reduces false removals and false recognitions.
|
|
2510
2604
|
* ## Features
|
|
2511
|
-
* 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
|
|
2605
|
+
* 1. First, clarify the definitions of the image subject and the image background. In actual use, when specifying the objects to remove, you can choose whether the removal scope is the image subject or the image background. Both API and editor integration methods are supported to meet different needs.
|
|
2512
2606
|
*
|
|
2513
2607
|
* 1. Image subject: the core product area in the image.
|
|
2514
2608
|
*
|
|
2515
2609
|
* 2. Image background: the rest of the image other than the product subject.
|
|
2516
2610
|
*
|
|
2517
|
-
* 2. Second, the
|
|
2611
|
+
* 2. Second, the following three types of objects can be removed:
|
|
2518
2612
|
*
|
|
2519
|
-
* 1.
|
|
2613
|
+
* 1. Select by type: You can select text, specific names, transparent text blocks, and watermarks. Refer to the following examples to clarify your requirements and perform targeted operations.
|
|
2520
2614
|
*
|
|
2521
|
-
* 2. (Upgraded)
|
|
2615
|
+
* 2. (Upgraded) Specify images to remove: You can specify multiple images at a time.
|
|
2522
2616
|
*
|
|
2523
|
-
* 3. (Upgraded)
|
|
2617
|
+
* 3. (Upgraded) Specify text to remove: You can specify multiple text strings at a time.
|
|
2524
2618
|
*
|
|
2525
|
-
* Processing flow:
|
|
2619
|
+
* Processing flow: Pass the original image URL -> The OCR and VLM models detect text or image positions -> Determine the coordinates of the area to be inpainted -> AI inpainting generates a clean image -> Return the result image URL.
|
|
2526
2620
|
* ## Effect comparison
|
|
2527
|
-
* | **Objects that can be removed
|
|
2621
|
+
* | **Objects that can be removed** | **Original image** | **Processed image** |
|
|
2528
2622
|
* | --- | --- | --- |
|
|
2529
2623
|
* | Text | * Involves the image subject area
|
|
2530
2624
|
*
|
|
@@ -2574,8 +2668,8 @@ export default class Client extends OpenApi {
|
|
|
2574
2668
|
* * Does not involve the image subject area
|
|
2575
2669
|
*
|
|
2576
2670
|
*  |
|
|
2577
|
-
* | Specified image element
|
|
2578
|
-
* | Specified text
|
|
2671
|
+
* | Specified image element removal (supports multiple image URLs) |  |  |
|
|
2672
|
+
* | Specified text removal (supports multiple text strings) |  |  |
|
|
2579
2673
|
*
|
|
2580
2674
|
* @param tmpReq - ImageRemoveAsyncRequest
|
|
2581
2675
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -2652,35 +2746,35 @@ export default class Client extends OpenApi {
|
|
|
2652
2746
|
}
|
|
2653
2747
|
|
|
2654
2748
|
/**
|
|
2655
|
-
*
|
|
2749
|
+
* Provides intelligent object removal tailored for e-commerce images. It automatically identifies and removes text, specific names, transparent text blocks, and watermarks. You can also specify objects for removal as needed, enabling efficient and accurate processing of large image batches and simplifying image editing workflows.
|
|
2656
2750
|
*
|
|
2657
2751
|
* @remarks
|
|
2658
2752
|
* ## Scenarios
|
|
2659
2753
|
* * **Efficient processing of e-commerce images:**
|
|
2660
2754
|
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
2661
2755
|
* * **Multi-platform product information synchronization:**
|
|
2662
|
-
* When merchants
|
|
2756
|
+
* When merchants list products on different e-commerce platforms, they can quickly remove specific text and watermarks to comply with the image specifications of different platforms.
|
|
2663
2757
|
* * **Marketing material preparation:**
|
|
2664
2758
|
* Merchants can easily remove original promotional information and quickly update it with the latest campaign information.
|
|
2665
|
-
* > Note: Merchants or platforms can
|
|
2759
|
+
* > Note: Merchants or platforms can remove impurities from images in batches to optimize image quality. Use this API in combination with the Intelligent Recognition API (coming soon) to first filter images containing text, specific names, transparent text blocks, and watermarks, and then use the Intelligent Erasure API for batch removal. The Intelligent Recognition API focuses on recognition, while the Intelligent Erasure API focuses on erasure. Calling them in sequence maximizes the erasure effect and reduces false removals and false recognitions.
|
|
2666
2760
|
* ## Features
|
|
2667
|
-
* 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
|
|
2761
|
+
* 1. First, clarify the definitions of the image subject and the image background. In actual use, when specifying the objects to remove, you can choose whether the removal scope is the image subject or the image background. Both API and editor integration methods are supported to meet different needs.
|
|
2668
2762
|
*
|
|
2669
2763
|
* 1. Image subject: the core product area in the image.
|
|
2670
2764
|
*
|
|
2671
2765
|
* 2. Image background: the rest of the image other than the product subject.
|
|
2672
2766
|
*
|
|
2673
|
-
* 2. Second, the
|
|
2767
|
+
* 2. Second, the following three types of objects can be removed:
|
|
2674
2768
|
*
|
|
2675
|
-
* 1.
|
|
2769
|
+
* 1. Select by type: You can select text, specific names, transparent text blocks, and watermarks. Refer to the following examples to clarify your requirements and perform targeted operations.
|
|
2676
2770
|
*
|
|
2677
|
-
* 2. (Upgraded)
|
|
2771
|
+
* 2. (Upgraded) Specify images to remove: You can specify multiple images at a time.
|
|
2678
2772
|
*
|
|
2679
|
-
* 3. (Upgraded)
|
|
2773
|
+
* 3. (Upgraded) Specify text to remove: You can specify multiple text strings at a time.
|
|
2680
2774
|
*
|
|
2681
|
-
* Processing flow:
|
|
2775
|
+
* Processing flow: Pass the original image URL -> The OCR and VLM models detect text or image positions -> Determine the coordinates of the area to be inpainted -> AI inpainting generates a clean image -> Return the result image URL.
|
|
2682
2776
|
* ## Effect comparison
|
|
2683
|
-
* | **Objects that can be removed
|
|
2777
|
+
* | **Objects that can be removed** | **Original image** | **Processed image** |
|
|
2684
2778
|
* | --- | --- | --- |
|
|
2685
2779
|
* | Text | * Involves the image subject area
|
|
2686
2780
|
*
|
|
@@ -2730,8 +2824,8 @@ export default class Client extends OpenApi {
|
|
|
2730
2824
|
* * Does not involve the image subject area
|
|
2731
2825
|
*
|
|
2732
2826
|
*  |
|
|
2733
|
-
* | Specified image element
|
|
2734
|
-
* | Specified text
|
|
2827
|
+
* | Specified image element removal (supports multiple image URLs) |  |  |
|
|
2828
|
+
* | Specified text removal (supports multiple text strings) |  |  |
|
|
2735
2829
|
*
|
|
2736
2830
|
* @param request - ImageRemoveAsyncRequest
|
|
2737
2831
|
* @returns ImageRemoveAsyncResponse
|
|
@@ -2864,17 +2958,17 @@ export default class Client extends OpenApi {
|
|
|
2864
2958
|
}
|
|
2865
2959
|
|
|
2866
2960
|
/**
|
|
2867
|
-
*
|
|
2961
|
+
* Translates e-commerce images by using the Image Translation Plus edition. This edition adopts the Mixture of Experts (MoE) architecture and delivers higher translation accuracy for multiple minor languages compared with the Lite and Pro editions.
|
|
2868
2962
|
*
|
|
2869
2963
|
* @remarks
|
|
2870
2964
|
* ## Scenarios
|
|
2871
2965
|
* Main images and detail images for cross-border e-commerce.
|
|
2872
2966
|
* ## Features
|
|
2873
|
-
* * **Product subject information protection**:
|
|
2967
|
+
* * **Product subject information protection**: Allows you to specify whether to translate the text on the product subject. This helps you protect the subject information, such as the embedded product name, from being translated.
|
|
2874
2968
|
*
|
|
2875
|
-
* * **Brand name protection**:
|
|
2969
|
+
* * **Brand name protection**: Allows you to specify whether to translate the brand names in the image. This helps you protect the brand name information from being translated.
|
|
2876
2970
|
*
|
|
2877
|
-
* * **Translation intervention**:
|
|
2971
|
+
* * **Translation intervention**: Allows you to customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), and skipping translation (ABC-null). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when you call the API operation. This meets your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention words. If you need more, contact the platform for assistance.
|
|
2878
2972
|
* ## Supported language pairs
|
|
2879
2973
|
* | **No.** | **Source language** | | **Target language** | |
|
|
2880
2974
|
* | --- | --- | --- | --- | --- |
|
|
@@ -2892,8 +2986,8 @@ export default class Client extends OpenApi {
|
|
|
2892
2986
|
* | 11 | en | English | de | German |
|
|
2893
2987
|
* | 12 | en | English | pl | Polish |
|
|
2894
2988
|
* ## Preparations and call process
|
|
2895
|
-
* Image Translation Plus and other
|
|
2896
|
-
* For the
|
|
2989
|
+
* The asynchronous API operations for Image Translation Plus and other features share the same result retrieval process, RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
2990
|
+
* For the asynchronous call process, subscription rules, message formats and encryption protocols, and detailed integration solutions, refer to [Asynchronous API operation call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
2897
2991
|
*
|
|
2898
2992
|
* @param request - ImageTranslationPlusAsyncRequest
|
|
2899
2993
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -2952,17 +3046,17 @@ export default class Client extends OpenApi {
|
|
|
2952
3046
|
}
|
|
2953
3047
|
|
|
2954
3048
|
/**
|
|
2955
|
-
*
|
|
3049
|
+
* Translates e-commerce images by using the Image Translation Plus edition. This edition adopts the Mixture of Experts (MoE) architecture and delivers higher translation accuracy for multiple minor languages compared with the Lite and Pro editions.
|
|
2956
3050
|
*
|
|
2957
3051
|
* @remarks
|
|
2958
3052
|
* ## Scenarios
|
|
2959
3053
|
* Main images and detail images for cross-border e-commerce.
|
|
2960
3054
|
* ## Features
|
|
2961
|
-
* * **Product subject information protection**:
|
|
3055
|
+
* * **Product subject information protection**: Allows you to specify whether to translate the text on the product subject. This helps you protect the subject information, such as the embedded product name, from being translated.
|
|
2962
3056
|
*
|
|
2963
|
-
* * **Brand name protection**:
|
|
3057
|
+
* * **Brand name protection**: Allows you to specify whether to translate the brand names in the image. This helps you protect the brand name information from being translated.
|
|
2964
3058
|
*
|
|
2965
|
-
* * **Translation intervention**:
|
|
3059
|
+
* * **Translation intervention**: Allows you to customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), and skipping translation (ABC-null). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when you call the API operation. This meets your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention words. If you need more, contact the platform for assistance.
|
|
2966
3060
|
* ## Supported language pairs
|
|
2967
3061
|
* | **No.** | **Source language** | | **Target language** | |
|
|
2968
3062
|
* | --- | --- | --- | --- | --- |
|
|
@@ -2980,8 +3074,8 @@ export default class Client extends OpenApi {
|
|
|
2980
3074
|
* | 11 | en | English | de | German |
|
|
2981
3075
|
* | 12 | en | English | pl | Polish |
|
|
2982
3076
|
* ## Preparations and call process
|
|
2983
|
-
* Image Translation Plus and other
|
|
2984
|
-
* For the
|
|
3077
|
+
* The asynchronous API operations for Image Translation Plus and other features share the same result retrieval process, RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
3078
|
+
* For the asynchronous call process, subscription rules, message formats and encryption protocols, and detailed integration solutions, refer to [Asynchronous API operation call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
2985
3079
|
*
|
|
2986
3080
|
* @param request - ImageTranslationPlusAsyncRequest
|
|
2987
3081
|
* @returns ImageTranslationPlusAsyncResponse
|
|
@@ -3086,22 +3180,22 @@ export default class Client extends OpenApi {
|
|
|
3086
3180
|
}
|
|
3087
3181
|
|
|
3088
3182
|
/**
|
|
3089
|
-
* Translates images by using Image Translation Pro, which is designed
|
|
3183
|
+
* Translates images by using the Image Translation Pro edition, which is designed for e-commerce images, integrates multimodal large model technology for more accurate image understanding, significantly improves translation quality, and continuously expands and optimizes multilingual translation capabilities, supporting more than 400 language pairs including bridged languages.
|
|
3090
3184
|
*
|
|
3091
3185
|
* @remarks
|
|
3092
3186
|
* ## Scenarios
|
|
3093
|
-
* E-commerce product images, marketing images, and images
|
|
3187
|
+
* E-commerce product images, marketing images, and images in various other scenarios.
|
|
3094
3188
|
* ## Features
|
|
3095
|
-
* * 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.
|
|
3189
|
+
* * Product subject information protection: You can specify whether to translate the text on the product subject. This helps you protect the subject information, such as the embedded product name, from being translated.
|
|
3096
3190
|
*
|
|
3097
3191
|
* * 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.
|
|
3098
3192
|
*
|
|
3099
3193
|
* * Brand name protection: You can specify whether to translate brand names in the image. This helps you protect brand name information from being translated.
|
|
3100
3194
|
*
|
|
3101
|
-
* * 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
|
|
3195
|
+
* * Translation intervention: You can customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), or omitting the translation (ABC-null). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API, which meets your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention entries. If you need more, contact the platform for assistance.
|
|
3102
3196
|
* ## Preparations and call process
|
|
3103
3197
|
* 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).
|
|
3104
|
-
*
|
|
3198
|
+
* 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.
|
|
3105
3199
|
* 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).
|
|
3106
3200
|
*
|
|
3107
3201
|
* @param request - ImageTranslationProAsyncRequest
|
|
@@ -3161,22 +3255,22 @@ export default class Client extends OpenApi {
|
|
|
3161
3255
|
}
|
|
3162
3256
|
|
|
3163
3257
|
/**
|
|
3164
|
-
* Translates images by using Image Translation Pro, which is designed
|
|
3258
|
+
* Translates images by using the Image Translation Pro edition, which is designed for e-commerce images, integrates multimodal large model technology for more accurate image understanding, significantly improves translation quality, and continuously expands and optimizes multilingual translation capabilities, supporting more than 400 language pairs including bridged languages.
|
|
3165
3259
|
*
|
|
3166
3260
|
* @remarks
|
|
3167
3261
|
* ## Scenarios
|
|
3168
|
-
* E-commerce product images, marketing images, and images
|
|
3262
|
+
* E-commerce product images, marketing images, and images in various other scenarios.
|
|
3169
3263
|
* ## Features
|
|
3170
|
-
* * 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.
|
|
3264
|
+
* * Product subject information protection: You can specify whether to translate the text on the product subject. This helps you protect the subject information, such as the embedded product name, from being translated.
|
|
3171
3265
|
*
|
|
3172
3266
|
* * 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.
|
|
3173
3267
|
*
|
|
3174
3268
|
* * Brand name protection: You can specify whether to translate brand names in the image. This helps you protect brand name information from being translated.
|
|
3175
3269
|
*
|
|
3176
|
-
* * 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
|
|
3270
|
+
* * Translation intervention: You can customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), or omitting the translation (ABC-null). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API, which meets your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention entries. If you need more, contact the platform for assistance.
|
|
3177
3271
|
* ## Preparations and call process
|
|
3178
3272
|
* 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).
|
|
3179
|
-
*
|
|
3273
|
+
* 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.
|
|
3180
3274
|
* 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).
|
|
3181
3275
|
*
|
|
3182
3276
|
* @param request - ImageTranslationProAsyncRequest
|
|
@@ -3188,22 +3282,22 @@ export default class Client extends OpenApi {
|
|
|
3188
3282
|
}
|
|
3189
3283
|
|
|
3190
3284
|
/**
|
|
3191
|
-
*
|
|
3285
|
+
* Provides image translation tailored for e-commerce, supporting over 400 language pairs, including bridged pairs. Accurately processes complex text layouts within images and ensures translated content aligns with the image context, helping e-commerce platforms and developers easily achieve multilingual conversion and presentation. Additionally, returns layer information such as text position, font, and color to facilitate secondary editing through image editors.
|
|
3192
3286
|
*
|
|
3193
3287
|
* @remarks
|
|
3194
|
-
* # 1. Product
|
|
3195
|
-
* The image translation product is tailored for e-commerce images, supporting over 400 language pairs
|
|
3288
|
+
* # 1. Product introduction
|
|
3289
|
+
* The image translation product is tailored for e-commerce images, supporting over 400 language pairs, including bridged pairs. It accurately processes complex text layouts within images and ensures that the translated content aligns with the image context, helping e-commerce platforms and developers easily achieve multilingual conversion and presentation. Additionally, it returns layer information such as text position, font, and color to facilitate secondary editing through image editors.
|
|
3196
3290
|
* # 2. Scenarios
|
|
3197
3291
|
* E-commerce product images, marketing images, and images for various other scenarios.
|
|
3198
3292
|
* # 3. Features
|
|
3199
|
-
* * **Product subject information protection**: Allows you to
|
|
3293
|
+
* * **Product subject information protection**: Allows you to choose whether to translate the text on the product subject. This helps protect the subject information from being translated, avoiding the translation of embedded information such as product names.
|
|
3200
3294
|
*
|
|
3201
|
-
* * **Brand name protection**: Allows you to
|
|
3295
|
+
* * **Brand name protection**: Allows you to choose whether to translate brand names in the image. This helps protect brand name information from being translated.
|
|
3202
3296
|
*
|
|
3203
|
-
* * **Secondary editing after translation (layer information)**: Allows you to
|
|
3297
|
+
* * **Secondary editing after translation (layer information)**: Allows you to choose whether to return layer information such as text position, font, and color. This information can be used to integrate with image editors for secondary editing of the translation results. For updates on the release of the editor SDK package, refer to platform notifications.
|
|
3204
3298
|
*
|
|
3205
|
-
* * **Translation intervention**: Allows you to customize translation results, including
|
|
3206
|
-
* <props="china">* **Image editor integration**: For more information, see [Image
|
|
3299
|
+
* * **Translation intervention**: Allows you to customize translation results, including do not translate (ABC-ABC), specify translation (ABC-DEF), and skip translation (ABC-null value). This is commonly used in scenarios such as brand word protection. You can achieve this by passing the corresponding intervention glossary ID when calling the API, meeting your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance.
|
|
3300
|
+
* <props="china">* **Image editor integration**: For more information, see [Image translation editor protocol](https://www.alibabacloud.com/help/en/document_detail/3042647.html).
|
|
3207
3301
|
*
|
|
3208
3302
|
* @param request - ImageTranslationStandardRequest
|
|
3209
3303
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3258,22 +3352,22 @@ export default class Client extends OpenApi {
|
|
|
3258
3352
|
}
|
|
3259
3353
|
|
|
3260
3354
|
/**
|
|
3261
|
-
*
|
|
3355
|
+
* Provides image translation tailored for e-commerce, supporting over 400 language pairs, including bridged pairs. Accurately processes complex text layouts within images and ensures translated content aligns with the image context, helping e-commerce platforms and developers easily achieve multilingual conversion and presentation. Additionally, returns layer information such as text position, font, and color to facilitate secondary editing through image editors.
|
|
3262
3356
|
*
|
|
3263
3357
|
* @remarks
|
|
3264
|
-
* # 1. Product
|
|
3265
|
-
* The image translation product is tailored for e-commerce images, supporting over 400 language pairs
|
|
3358
|
+
* # 1. Product introduction
|
|
3359
|
+
* The image translation product is tailored for e-commerce images, supporting over 400 language pairs, including bridged pairs. It accurately processes complex text layouts within images and ensures that the translated content aligns with the image context, helping e-commerce platforms and developers easily achieve multilingual conversion and presentation. Additionally, it returns layer information such as text position, font, and color to facilitate secondary editing through image editors.
|
|
3266
3360
|
* # 2. Scenarios
|
|
3267
3361
|
* E-commerce product images, marketing images, and images for various other scenarios.
|
|
3268
3362
|
* # 3. Features
|
|
3269
|
-
* * **Product subject information protection**: Allows you to
|
|
3363
|
+
* * **Product subject information protection**: Allows you to choose whether to translate the text on the product subject. This helps protect the subject information from being translated, avoiding the translation of embedded information such as product names.
|
|
3270
3364
|
*
|
|
3271
|
-
* * **Brand name protection**: Allows you to
|
|
3365
|
+
* * **Brand name protection**: Allows you to choose whether to translate brand names in the image. This helps protect brand name information from being translated.
|
|
3272
3366
|
*
|
|
3273
|
-
* * **Secondary editing after translation (layer information)**: Allows you to
|
|
3367
|
+
* * **Secondary editing after translation (layer information)**: Allows you to choose whether to return layer information such as text position, font, and color. This information can be used to integrate with image editors for secondary editing of the translation results. For updates on the release of the editor SDK package, refer to platform notifications.
|
|
3274
3368
|
*
|
|
3275
|
-
* * **Translation intervention**: Allows you to customize translation results, including
|
|
3276
|
-
* <props="china">* **Image editor integration**: For more information, see [Image
|
|
3369
|
+
* * **Translation intervention**: Allows you to customize translation results, including do not translate (ABC-ABC), specify translation (ABC-DEF), and skip translation (ABC-null value). This is commonly used in scenarios such as brand word protection. You can achieve this by passing the corresponding intervention glossary ID when calling the API, meeting your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance.
|
|
3370
|
+
* <props="china">* **Image editor integration**: For more information, see [Image translation editor protocol](https://www.alibabacloud.com/help/en/document_detail/3042647.html).
|
|
3277
3371
|
*
|
|
3278
3372
|
* @param request - ImageTranslationStandardRequest
|
|
3279
3373
|
* @returns ImageTranslationStandardResponse
|
|
@@ -3284,23 +3378,23 @@ export default class Client extends OpenApi {
|
|
|
3284
3378
|
}
|
|
3285
3379
|
|
|
3286
3380
|
/**
|
|
3287
|
-
* Translates
|
|
3381
|
+
* Translates e-commerce images and supports over 400 language pairs, including bridged pairs. Accurately processes complex text layouts within images and ensures that the translated content matches the image context, which helps e-commerce platforms and developers easily achieve multilingual conversion and presentation of image content. Additionally, the service returns layer information such as the position, font, and color of text in the image to facilitate secondary editing of translation results by using image editors.
|
|
3288
3382
|
*
|
|
3289
3383
|
* @remarks
|
|
3290
3384
|
* ## Scenarios
|
|
3291
|
-
*
|
|
3385
|
+
* Product images, marketing images, and images for various other scenarios in e-commerce.
|
|
3292
3386
|
* ## Features
|
|
3293
|
-
* * **Product subject information protection**: Allows you to specify whether to translate text on the product subject. This
|
|
3387
|
+
* * **Product subject information protection**: Allows you to specify whether to translate the text on the product subject. This helps protect the subject information from being translated and prevents embedded information such as product names from being translated.
|
|
3294
3388
|
*
|
|
3295
|
-
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image. This
|
|
3389
|
+
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image. This helps protect brand name information from being translated.
|
|
3296
3390
|
*
|
|
3297
|
-
* * **Secondary editing after translation (layer information)**: Allows you to specify whether to return layer information such as
|
|
3391
|
+
* * **Secondary editing after translation (layer information)**: Allows you to specify whether to return layer information such as the position, font, and color of the text. This information can be used to integrate with image editors for secondary editing of translation results. For the release progress of the editor SDK package, refer to platform notifications.
|
|
3298
3392
|
*
|
|
3299
|
-
* * **Translation intervention**: Allows you to customize translation results, including
|
|
3393
|
+
* * **Translation intervention**: Allows you to customize translation results, including no translation (ABC-ABC), specified translation (ABC-DEF), and skip translation (ABC-null value). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API operation to meet your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention words. If you need more, contact the platform for assistance.
|
|
3300
3394
|
* ## Preparations and call process
|
|
3301
|
-
* * Image Translation Standard Edition supports both synchronous and asynchronous
|
|
3302
|
-
* * The asynchronous
|
|
3303
|
-
* * 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).
|
|
3395
|
+
* * Image Translation Standard Edition supports both synchronous and asynchronous call methods. This topic describes the asynchronous call API operation. For synchronous calls, refer to [Image Translation Standard Edition](https://www.alibabacloud.com/help/en/aidge/image-translation).
|
|
3396
|
+
* * The asynchronous API operations for Image Translation Standard Edition and other features share the same result retrieval process, ApsaraMQ for RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
3397
|
+
* * For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls, refer to [Asynchronous API operation call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
3304
3398
|
*
|
|
3305
3399
|
* @param request - ImageTranslationStandardAsyncRequest
|
|
3306
3400
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3359,23 +3453,23 @@ export default class Client extends OpenApi {
|
|
|
3359
3453
|
}
|
|
3360
3454
|
|
|
3361
3455
|
/**
|
|
3362
|
-
* Translates
|
|
3456
|
+
* Translates e-commerce images and supports over 400 language pairs, including bridged pairs. Accurately processes complex text layouts within images and ensures that the translated content matches the image context, which helps e-commerce platforms and developers easily achieve multilingual conversion and presentation of image content. Additionally, the service returns layer information such as the position, font, and color of text in the image to facilitate secondary editing of translation results by using image editors.
|
|
3363
3457
|
*
|
|
3364
3458
|
* @remarks
|
|
3365
3459
|
* ## Scenarios
|
|
3366
|
-
*
|
|
3460
|
+
* Product images, marketing images, and images for various other scenarios in e-commerce.
|
|
3367
3461
|
* ## Features
|
|
3368
|
-
* * **Product subject information protection**: Allows you to specify whether to translate text on the product subject. This
|
|
3462
|
+
* * **Product subject information protection**: Allows you to specify whether to translate the text on the product subject. This helps protect the subject information from being translated and prevents embedded information such as product names from being translated.
|
|
3369
3463
|
*
|
|
3370
|
-
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image. This
|
|
3464
|
+
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image. This helps protect brand name information from being translated.
|
|
3371
3465
|
*
|
|
3372
|
-
* * **Secondary editing after translation (layer information)**: Allows you to specify whether to return layer information such as
|
|
3466
|
+
* * **Secondary editing after translation (layer information)**: Allows you to specify whether to return layer information such as the position, font, and color of the text. This information can be used to integrate with image editors for secondary editing of translation results. For the release progress of the editor SDK package, refer to platform notifications.
|
|
3373
3467
|
*
|
|
3374
|
-
* * **Translation intervention**: Allows you to customize translation results, including
|
|
3468
|
+
* * **Translation intervention**: Allows you to customize translation results, including no translation (ABC-ABC), specified translation (ABC-DEF), and skip translation (ABC-null value). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API operation to meet your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention words. If you need more, contact the platform for assistance.
|
|
3375
3469
|
* ## Preparations and call process
|
|
3376
|
-
* * Image Translation Standard Edition supports both synchronous and asynchronous
|
|
3377
|
-
* * The asynchronous
|
|
3378
|
-
* * 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).
|
|
3470
|
+
* * Image Translation Standard Edition supports both synchronous and asynchronous call methods. This topic describes the asynchronous call API operation. For synchronous calls, refer to [Image Translation Standard Edition](https://www.alibabacloud.com/help/en/aidge/image-translation).
|
|
3471
|
+
* * The asynchronous API operations for Image Translation Standard Edition and other features share the same result retrieval process, ApsaraMQ for RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
3472
|
+
* * For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls, refer to [Asynchronous API operation call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
3379
3473
|
*
|
|
3380
3474
|
* @param request - ImageTranslationStandardAsyncRequest
|
|
3381
3475
|
* @returns ImageTranslationStandardAsyncResponse
|
|
@@ -3386,22 +3480,24 @@ export default class Client extends OpenApi {
|
|
|
3386
3480
|
}
|
|
3387
3481
|
|
|
3388
3482
|
/**
|
|
3389
|
-
* Upscales e-commerce images by intelligently enhancing resolution and details, improving textures and image quality during the upscaling process. Supports high-definition outputs such as 2K and 4K to meet the requirements for product main images, detail images, and marketing materials, and
|
|
3483
|
+
* Upscales e-commerce images by intelligently enhancing resolution and details, improving textures and image quality during the upscaling process. Supports high-definition outputs such as 2K and 4K to meet the requirements for product main images, detail images, and marketing materials, enabling efficient and clear processing of large batches of images to improve product image quality. (Synchronous)
|
|
3390
3484
|
*
|
|
3391
3485
|
* @remarks
|
|
3392
|
-
* # Product
|
|
3393
|
-
* The high-definition upscaling product is customized for e-commerce images. It intelligently enhances image resolution and
|
|
3486
|
+
* # Product Introduction
|
|
3487
|
+
* The high-definition upscaling product is customized for e-commerce images. It intelligently enhances image resolution and detail performance, and provides texture enhancement and image quality optimization during the upscaling procedure. It supports high-definition outputs such as 2K and 4K to meet the high-definition requirements for product main images, detail images, and marketing materials. It enables efficient and clear processing of large batches of images to improve product image quality. (synchronous)
|
|
3394
3488
|
* # Scenarios
|
|
3395
|
-
* * 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
|
|
3396
|
-
*
|
|
3397
|
-
* *
|
|
3489
|
+
* * High-definition e-commerce product images: Enhances the resolution and details of product main images, detail images, and marketing materials to make details such as product textures and materials clearer, improving the quality of product displays.
|
|
3490
|
+
*
|
|
3491
|
+
* * Multi-platform product material adaptation: Upscales existing product images in high definition to meet the image display requirements of different e-commerce platforms, satisfying the material usage needs across multiple platforms and scenarios.
|
|
3492
|
+
*
|
|
3493
|
+
* * Batch optimization of existing images: Enhances existing low-resolution product images in high definition to reduce reshooting and production costs, improving the reuse efficiency of image materials.
|
|
3398
3494
|
* # Features
|
|
3399
|
-
* 1. Intelligent high-definition upscaling: Based on AI image enhancement technology, it improves the resolution and optimizes the details of input images to enhance image clarity and texture
|
|
3495
|
+
* 1. Intelligent high-definition upscaling: Based on AI image enhancement technology, it improves the resolution and optimizes the details of input images to enhance image clarity and texture performance.
|
|
3400
3496
|
*
|
|
3401
3497
|
* 2. Multiple upscaling factors: Supports 2x and 4x upscaling factors, allowing flexible selection based on image quality and business requirements.
|
|
3402
3498
|
*
|
|
3403
3499
|
* 3. Synchronous API calls: Supports synchronous submission of images and retrieval of processing results through APIs, facilitating integration into e-commerce image processing workflows.
|
|
3404
|
-
* #
|
|
3500
|
+
* # Before and after
|
|
3405
3501
|
* | **Original image** | **Upscaled image** |
|
|
3406
3502
|
* | --- | --- |
|
|
3407
3503
|
* |  |  |
|
|
@@ -3439,22 +3535,24 @@ export default class Client extends OpenApi {
|
|
|
3439
3535
|
}
|
|
3440
3536
|
|
|
3441
3537
|
/**
|
|
3442
|
-
* Upscales e-commerce images by intelligently enhancing resolution and details, improving textures and image quality during the upscaling process. Supports high-definition outputs such as 2K and 4K to meet the requirements for product main images, detail images, and marketing materials, and
|
|
3538
|
+
* Upscales e-commerce images by intelligently enhancing resolution and details, improving textures and image quality during the upscaling process. Supports high-definition outputs such as 2K and 4K to meet the requirements for product main images, detail images, and marketing materials, enabling efficient and clear processing of large batches of images to improve product image quality. (Synchronous)
|
|
3443
3539
|
*
|
|
3444
3540
|
* @remarks
|
|
3445
|
-
* # Product
|
|
3446
|
-
* The high-definition upscaling product is customized for e-commerce images. It intelligently enhances image resolution and
|
|
3541
|
+
* # Product Introduction
|
|
3542
|
+
* The high-definition upscaling product is customized for e-commerce images. It intelligently enhances image resolution and detail performance, and provides texture enhancement and image quality optimization during the upscaling procedure. It supports high-definition outputs such as 2K and 4K to meet the high-definition requirements for product main images, detail images, and marketing materials. It enables efficient and clear processing of large batches of images to improve product image quality. (synchronous)
|
|
3447
3543
|
* # Scenarios
|
|
3448
|
-
* * 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
|
|
3449
|
-
*
|
|
3450
|
-
* *
|
|
3544
|
+
* * High-definition e-commerce product images: Enhances the resolution and details of product main images, detail images, and marketing materials to make details such as product textures and materials clearer, improving the quality of product displays.
|
|
3545
|
+
*
|
|
3546
|
+
* * Multi-platform product material adaptation: Upscales existing product images in high definition to meet the image display requirements of different e-commerce platforms, satisfying the material usage needs across multiple platforms and scenarios.
|
|
3547
|
+
*
|
|
3548
|
+
* * Batch optimization of existing images: Enhances existing low-resolution product images in high definition to reduce reshooting and production costs, improving the reuse efficiency of image materials.
|
|
3451
3549
|
* # Features
|
|
3452
|
-
* 1. Intelligent high-definition upscaling: Based on AI image enhancement technology, it improves the resolution and optimizes the details of input images to enhance image clarity and texture
|
|
3550
|
+
* 1. Intelligent high-definition upscaling: Based on AI image enhancement technology, it improves the resolution and optimizes the details of input images to enhance image clarity and texture performance.
|
|
3453
3551
|
*
|
|
3454
3552
|
* 2. Multiple upscaling factors: Supports 2x and 4x upscaling factors, allowing flexible selection based on image quality and business requirements.
|
|
3455
3553
|
*
|
|
3456
3554
|
* 3. Synchronous API calls: Supports synchronous submission of images and retrieval of processing results through APIs, facilitating integration into e-commerce image processing workflows.
|
|
3457
|
-
* #
|
|
3555
|
+
* # Before and after
|
|
3458
3556
|
* | **Original image** | **Upscaled image** |
|
|
3459
3557
|
* | --- | --- |
|
|
3460
3558
|
* |  |  |
|
|
@@ -3522,29 +3620,29 @@ export default class Client extends OpenApi {
|
|
|
3522
3620
|
}
|
|
3523
3621
|
|
|
3524
3622
|
/**
|
|
3525
|
-
*
|
|
3623
|
+
* Inspects the compliance of in-store marketing material displays based on a multimodal large language model (MLLM) for offline retail and channel store inspection scenarios. It evaluates standard materials such as functional table cards, posters, and door-shaped display stands, along with long-tail materials like light cloths, KT boards, floor stickers, and light boxes in actual store photos against inspection rules at the natural language level. The operation outputs structured conclusions and Chinese evidence descriptions that can be directly integrated into business systems. This is a **synchronous** call that returns results in a single request.
|
|
3526
3624
|
*
|
|
3527
3625
|
* @remarks
|
|
3528
3626
|
* ## **Scenarios**
|
|
3529
|
-
* - **
|
|
3627
|
+
* - **Store marketing material compliance inspection**: Automatically determines whether specified marketing materials (feature table cards, posters, door-shaped display stands, etc.) are placed or posted in the store according to the standard display guidelines issued by the headquarters. Identifies typical issues such as missing materials, placement faults, and content mismatch.
|
|
3530
3628
|
*
|
|
3531
|
-
* - **New product
|
|
3629
|
+
* - **New product or campaign material verification**: During new product releases or sales promotions, automatically verifies in batches the listing of campaign materials in actual store photos as required, replacing manual sampling inspections.
|
|
3532
3630
|
*
|
|
3533
|
-
* - **Adaptive dual-image comparison and single-image detection**: A single API supports both
|
|
3631
|
+
* - **Adaptive dual-image comparison and single-image detection**: A single API operation supports both dual-image comparison (reference image + target image, Pattern A) and single-image detection (target image only, Pattern B). An automatic switchover is performed based on whether `ImageRefer` is provided, so callers do not need to distinguish between invoke methods.
|
|
3534
3632
|
* ## **Features**
|
|
3535
|
-
* - **Multi-mode intelligent routing**: Built-in material type parsing capability
|
|
3633
|
+
* - **Multi-mode intelligent routing**: Built-in material type parsing capability. Automatically identifies the target material type based on the natural language text in `Rules` and routes the request to the corresponding material detection pipeline. Callers only need to pass the image URL and rule text. Currently supports routing for four detection items: functional table cards, posters, door-shaped display stands, and other materials. More specific marketing material detection pipelines will be added in the future.
|
|
3536
3634
|
*
|
|
3537
|
-
* - **MLLM semantic
|
|
3635
|
+
* - **MLLM semantic understanding + structured rule collaboration**: Uses a multimodal large language model to perform semantic-level understanding such as material recognition, content comparison, and text OCR. Combines rule cleaning and structured models to break down natural language rules into step-by-step verifiable steps (S1, S2, etc.), ensuring accuracy while maintaining rule flexibility and traceability.
|
|
3538
3636
|
*
|
|
3539
|
-
* - **Structured
|
|
3637
|
+
* - **Structured audit conclusion output**: The output is unified into the structure of `Result.OverallResult` + `Result.Steps[]` + `Result.Evidence`. The overall conclusion is derived from the logical AND of all steps. Each step is independently visible, making it easy to directly drive downstream business systems and support case-level manual review tracing.
|
|
3540
3638
|
*
|
|
3541
|
-
* - **Supported input formats**: Currently supports publicly accessible image URLs.
|
|
3542
|
-
* ## **
|
|
3543
|
-
* - **Synchronous call**:
|
|
3639
|
+
* - **Supported input formats**: Currently supports publicly accessible image URLs. Supports both single-image (Mode B) and dual-image (Mode A) calling formats, with completely identical output structures.
|
|
3640
|
+
* ## **Invoke methods**
|
|
3641
|
+
* - **Synchronous call**: Returns the detection result in a single request without the need for polling. The response uses a unified envelope containing `Code`, `Message`, `RequestId`, `Success`, and `Data`.
|
|
3544
3642
|
*
|
|
3545
|
-
* - **Authentication and signing**: Invoked through the Aidge gateway. Authentication, signing, and common parameters follow the platform
|
|
3643
|
+
* - **Authentication and signing**: Invoked through the Aidge gateway. Authentication, signing, and common parameters follow the unified platform access methods. Refer to the officially published API documentation for the specific request path.
|
|
3546
3644
|
*
|
|
3547
|
-
* - **Timeout settings**: Set the request timeout to no less than the maximum response time of the API
|
|
3645
|
+
* - **Timeout settings**: Set the request timeout to a value no less than the maximum response time of the API operation. Refer to the officially published documentation for the specific value.
|
|
3548
3646
|
*
|
|
3549
3647
|
* @param request - MaterialInspectionRequest
|
|
3550
3648
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3591,29 +3689,29 @@ export default class Client extends OpenApi {
|
|
|
3591
3689
|
}
|
|
3592
3690
|
|
|
3593
3691
|
/**
|
|
3594
|
-
*
|
|
3692
|
+
* Inspects the compliance of in-store marketing material displays based on a multimodal large language model (MLLM) for offline retail and channel store inspection scenarios. It evaluates standard materials such as functional table cards, posters, and door-shaped display stands, along with long-tail materials like light cloths, KT boards, floor stickers, and light boxes in actual store photos against inspection rules at the natural language level. The operation outputs structured conclusions and Chinese evidence descriptions that can be directly integrated into business systems. This is a **synchronous** call that returns results in a single request.
|
|
3595
3693
|
*
|
|
3596
3694
|
* @remarks
|
|
3597
3695
|
* ## **Scenarios**
|
|
3598
|
-
* - **
|
|
3696
|
+
* - **Store marketing material compliance inspection**: Automatically determines whether specified marketing materials (feature table cards, posters, door-shaped display stands, etc.) are placed or posted in the store according to the standard display guidelines issued by the headquarters. Identifies typical issues such as missing materials, placement faults, and content mismatch.
|
|
3599
3697
|
*
|
|
3600
|
-
* - **New product
|
|
3698
|
+
* - **New product or campaign material verification**: During new product releases or sales promotions, automatically verifies in batches the listing of campaign materials in actual store photos as required, replacing manual sampling inspections.
|
|
3601
3699
|
*
|
|
3602
|
-
* - **Adaptive dual-image comparison and single-image detection**: A single API supports both
|
|
3700
|
+
* - **Adaptive dual-image comparison and single-image detection**: A single API operation supports both dual-image comparison (reference image + target image, Pattern A) and single-image detection (target image only, Pattern B). An automatic switchover is performed based on whether `ImageRefer` is provided, so callers do not need to distinguish between invoke methods.
|
|
3603
3701
|
* ## **Features**
|
|
3604
|
-
* - **Multi-mode intelligent routing**: Built-in material type parsing capability
|
|
3702
|
+
* - **Multi-mode intelligent routing**: Built-in material type parsing capability. Automatically identifies the target material type based on the natural language text in `Rules` and routes the request to the corresponding material detection pipeline. Callers only need to pass the image URL and rule text. Currently supports routing for four detection items: functional table cards, posters, door-shaped display stands, and other materials. More specific marketing material detection pipelines will be added in the future.
|
|
3605
3703
|
*
|
|
3606
|
-
* - **MLLM semantic
|
|
3704
|
+
* - **MLLM semantic understanding + structured rule collaboration**: Uses a multimodal large language model to perform semantic-level understanding such as material recognition, content comparison, and text OCR. Combines rule cleaning and structured models to break down natural language rules into step-by-step verifiable steps (S1, S2, etc.), ensuring accuracy while maintaining rule flexibility and traceability.
|
|
3607
3705
|
*
|
|
3608
|
-
* - **Structured
|
|
3706
|
+
* - **Structured audit conclusion output**: The output is unified into the structure of `Result.OverallResult` + `Result.Steps[]` + `Result.Evidence`. The overall conclusion is derived from the logical AND of all steps. Each step is independently visible, making it easy to directly drive downstream business systems and support case-level manual review tracing.
|
|
3609
3707
|
*
|
|
3610
|
-
* - **Supported input formats**: Currently supports publicly accessible image URLs.
|
|
3611
|
-
* ## **
|
|
3612
|
-
* - **Synchronous call**:
|
|
3708
|
+
* - **Supported input formats**: Currently supports publicly accessible image URLs. Supports both single-image (Mode B) and dual-image (Mode A) calling formats, with completely identical output structures.
|
|
3709
|
+
* ## **Invoke methods**
|
|
3710
|
+
* - **Synchronous call**: Returns the detection result in a single request without the need for polling. The response uses a unified envelope containing `Code`, `Message`, `RequestId`, `Success`, and `Data`.
|
|
3613
3711
|
*
|
|
3614
|
-
* - **Authentication and signing**: Invoked through the Aidge gateway. Authentication, signing, and common parameters follow the platform
|
|
3712
|
+
* - **Authentication and signing**: Invoked through the Aidge gateway. Authentication, signing, and common parameters follow the unified platform access methods. Refer to the officially published API documentation for the specific request path.
|
|
3615
3713
|
*
|
|
3616
|
-
* - **Timeout settings**: Set the request timeout to no less than the maximum response time of the API
|
|
3714
|
+
* - **Timeout settings**: Set the request timeout to a value no less than the maximum response time of the API operation. Refer to the officially published documentation for the specific value.
|
|
3617
3715
|
*
|
|
3618
3716
|
* @param request - MaterialInspectionRequest
|
|
3619
3717
|
* @returns MaterialInspectionResponse
|
|
@@ -3624,25 +3722,25 @@ export default class Client extends OpenApi {
|
|
|
3624
3722
|
}
|
|
3625
3723
|
|
|
3626
3724
|
/**
|
|
3627
|
-
* Detects
|
|
3725
|
+
* Detects product displays in physical stores based on multimodal large language models (MLLMs) and visual vector recall. This capability is designed for shelf and floor display inspection scenarios in offline retail and channel stores. The service first uses an MLLM to detect the bounding boxes and preliminary names of each product in real-world shelf and floor display photos, and then performs similarity recall against a customer-specific SKU vector database, enabling an exact match for each product to the customer\\"s own SKUs. It outputs item-by-item structured results that can be directly integrated with business systems. This service is suitable for large-scale, highly concurrent visual recognition pipelines such as remote auditing of offline store displays by headquarters, SKU distribution verification, and display compliance inspections.
|
|
3628
3726
|
*
|
|
3629
3727
|
* @remarks
|
|
3630
3728
|
* ## **Product Introduction**
|
|
3631
|
-
* Display detection is an intelligent
|
|
3729
|
+
* Display detection is an intelligent recognition capability for store product displays built on multimodal large language models (MLLMs) and visual vector recall. It is designed for shelf and floor display inspection scenarios in offline retail and channel stores. For real-world shelf and floor display photos taken in stores, the service first uses an MLLM to detect the bounding boxes and preliminary names of each product, and then performs similarity recall against a customer-specific SKU vector database, enabling an exact match for each product to the customer\\"s own SKUs. It outputs item-by-item structured results that can be directly integrated with business systems. This service is suitable for large-scale, highly concurrent visual recognition pipelines such as remote auditing of offline store displays by headquarters, SKU distribution verification, and display compliance inspections.
|
|
3632
3730
|
* ## **Scenarios**
|
|
3633
|
-
* - **Shelf
|
|
3731
|
+
* - **Shelf and floor display recognition and inventory**: Recognizes each product in a shelf or floor display image and matches it to the customer\\"s SKU database. It outputs an item-by-item list (product name, location, and similarity score) to replace manual item-by-item counting.
|
|
3634
3732
|
*
|
|
3635
|
-
* - **Distribution verification
|
|
3733
|
+
* - **Distribution verification and SKU compliance**: Verifies whether stores display specified SKUs as required by headquarters, and checks for out-of-stock or misplaced items. This supports batch automatic verification during sales promotions or new product launches.
|
|
3636
3734
|
*
|
|
3637
|
-
* - **Customer-specific SKU
|
|
3638
|
-
* ## **
|
|
3639
|
-
* - **Two-stage detection
|
|
3735
|
+
* - **Customer-specific SKU database**: Customers can upload their own standard SKU images to create a dedicated vector database (isolated by RagId). During recognition, retrieval is performed only within this customer\\"s database to ensure accurate naming and data isolation between customers.
|
|
3736
|
+
* ## **Features**
|
|
3737
|
+
* - **Two-stage collaboration of detection and retrieval**: The MLLM detects the bounding box and preliminary name of each product in the entire image (semantic-level understanding, adapted for dense displays and partial occlusion). Then, visual embedding vectors are used to perform similarity retrieval within the customer\\"s SKU database. The preliminary name is replaced with the exact SKU name of the top-1 result, balancing the recall rate and naming accuracy.
|
|
3640
3738
|
*
|
|
3641
|
-
* - **Isolated retrieval with dedicated vector
|
|
3739
|
+
* - **Isolated retrieval with dedicated vector databases**: A dedicated SKU vector database is maintained for each customer based on RagId. Recognition retrieves data only within the corresponding database, ensuring strict isolation between customers. Added or updated SKUs take effect in real time.
|
|
3642
3740
|
*
|
|
3643
|
-
* - **
|
|
3741
|
+
* - **Item-by-item structured output**: The output is unified as Result.Items[]. Each product independently provides the bounding box, retrieved SKU name, SKU code, and similarity score. This facilitates direct integration with downstream inventory and verification systems and supports case-level manual review and tracing.
|
|
3644
3742
|
*
|
|
3645
|
-
* - **Supported input formats**: Currently supports image URLs accessible over the Internet or
|
|
3743
|
+
* - **Supported input formats**: Currently supports image URLs accessible over the Internet or from OSS. A single shelf or floor display image is sufficient for recognition, and the output structure is unified.
|
|
3646
3744
|
*
|
|
3647
3745
|
* @param request - MerchandisePlacementDetectionRequest
|
|
3648
3746
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3689,25 +3787,25 @@ export default class Client extends OpenApi {
|
|
|
3689
3787
|
}
|
|
3690
3788
|
|
|
3691
3789
|
/**
|
|
3692
|
-
* Detects
|
|
3790
|
+
* Detects product displays in physical stores based on multimodal large language models (MLLMs) and visual vector recall. This capability is designed for shelf and floor display inspection scenarios in offline retail and channel stores. The service first uses an MLLM to detect the bounding boxes and preliminary names of each product in real-world shelf and floor display photos, and then performs similarity recall against a customer-specific SKU vector database, enabling an exact match for each product to the customer\\"s own SKUs. It outputs item-by-item structured results that can be directly integrated with business systems. This service is suitable for large-scale, highly concurrent visual recognition pipelines such as remote auditing of offline store displays by headquarters, SKU distribution verification, and display compliance inspections.
|
|
3693
3791
|
*
|
|
3694
3792
|
* @remarks
|
|
3695
3793
|
* ## **Product Introduction**
|
|
3696
|
-
* Display detection is an intelligent
|
|
3794
|
+
* Display detection is an intelligent recognition capability for store product displays built on multimodal large language models (MLLMs) and visual vector recall. It is designed for shelf and floor display inspection scenarios in offline retail and channel stores. For real-world shelf and floor display photos taken in stores, the service first uses an MLLM to detect the bounding boxes and preliminary names of each product, and then performs similarity recall against a customer-specific SKU vector database, enabling an exact match for each product to the customer\\"s own SKUs. It outputs item-by-item structured results that can be directly integrated with business systems. This service is suitable for large-scale, highly concurrent visual recognition pipelines such as remote auditing of offline store displays by headquarters, SKU distribution verification, and display compliance inspections.
|
|
3697
3795
|
* ## **Scenarios**
|
|
3698
|
-
* - **Shelf
|
|
3796
|
+
* - **Shelf and floor display recognition and inventory**: Recognizes each product in a shelf or floor display image and matches it to the customer\\"s SKU database. It outputs an item-by-item list (product name, location, and similarity score) to replace manual item-by-item counting.
|
|
3699
3797
|
*
|
|
3700
|
-
* - **Distribution verification
|
|
3798
|
+
* - **Distribution verification and SKU compliance**: Verifies whether stores display specified SKUs as required by headquarters, and checks for out-of-stock or misplaced items. This supports batch automatic verification during sales promotions or new product launches.
|
|
3701
3799
|
*
|
|
3702
|
-
* - **Customer-specific SKU
|
|
3703
|
-
* ## **
|
|
3704
|
-
* - **Two-stage detection
|
|
3800
|
+
* - **Customer-specific SKU database**: Customers can upload their own standard SKU images to create a dedicated vector database (isolated by RagId). During recognition, retrieval is performed only within this customer\\"s database to ensure accurate naming and data isolation between customers.
|
|
3801
|
+
* ## **Features**
|
|
3802
|
+
* - **Two-stage collaboration of detection and retrieval**: The MLLM detects the bounding box and preliminary name of each product in the entire image (semantic-level understanding, adapted for dense displays and partial occlusion). Then, visual embedding vectors are used to perform similarity retrieval within the customer\\"s SKU database. The preliminary name is replaced with the exact SKU name of the top-1 result, balancing the recall rate and naming accuracy.
|
|
3705
3803
|
*
|
|
3706
|
-
* - **Isolated retrieval with dedicated vector
|
|
3804
|
+
* - **Isolated retrieval with dedicated vector databases**: A dedicated SKU vector database is maintained for each customer based on RagId. Recognition retrieves data only within the corresponding database, ensuring strict isolation between customers. Added or updated SKUs take effect in real time.
|
|
3707
3805
|
*
|
|
3708
|
-
* - **
|
|
3806
|
+
* - **Item-by-item structured output**: The output is unified as Result.Items[]. Each product independently provides the bounding box, retrieved SKU name, SKU code, and similarity score. This facilitates direct integration with downstream inventory and verification systems and supports case-level manual review and tracing.
|
|
3709
3807
|
*
|
|
3710
|
-
* - **Supported input formats**: Currently supports image URLs accessible over the Internet or
|
|
3808
|
+
* - **Supported input formats**: Currently supports image URLs accessible over the Internet or from OSS. A single shelf or floor display image is sufficient for recognition, and the output structure is unified.
|
|
3711
3809
|
*
|
|
3712
3810
|
* @param request - MerchandisePlacementDetectionRequest
|
|
3713
3811
|
* @returns MerchandisePlacementDetectionResponse
|
|
@@ -3718,18 +3816,18 @@ export default class Client extends OpenApi {
|
|
|
3718
3816
|
}
|
|
3719
3817
|
|
|
3720
3818
|
/**
|
|
3721
|
-
* Detects product displays in photos of shelves, endcaps, freezers, display
|
|
3819
|
+
* Detects product displays in photos of shelves, endcaps, freezers, display stands, and dump bins by using product SKU recognition and multimodal large model grounding, aggregates product locations by SKU, and supplements the results with visible single-item grounding and short names to facilitate product location display, inventory counting, and distribution verification.
|
|
3722
3820
|
*
|
|
3723
3821
|
* @remarks
|
|
3724
3822
|
* ## Scenarios
|
|
3725
|
-
* - Display
|
|
3726
|
-
* - Distribution
|
|
3823
|
+
* - Display inventory: Aggregates recognized product bounding boxes by SKU for business system statistics.
|
|
3824
|
+
* - Distribution checklist verification: Compares the recognized SKU list with the target checklist on the business side.
|
|
3727
3825
|
* - Single-item location review: Assists in checking recognition results by combining product bounding boxes and visible names.
|
|
3728
3826
|
* ## Features
|
|
3729
|
-
* - Aggregation by SKU: Aggregates multiple
|
|
3730
|
-
* - Supplementary single-item grounding: The multimodal model
|
|
3827
|
+
* - Aggregation by SKU: Aggregates multiple bounding boxes for the same SkuId in Products, and returns a deduplicated list of SKU codes in skuIds.
|
|
3828
|
+
* - Supplementary single-item grounding: The multimodal model locates each recognizable sales package and provides a confirmable short name.
|
|
3731
3829
|
* - Independent use of two result sets: Products comes from SKU recognition, and grounding comes from supplementary grounding. Grounding does not return SKU codes and does not guarantee item-by-item correspondence with Products.
|
|
3732
|
-
* - Supports single HTTPS image input. Supplementary grounding returns up to 12 targets
|
|
3830
|
+
* - Supports a single HTTPS image as input. Supplementary grounding returns up to 12 targets. Each target includes a category, a bounding box, and visible text of up to 24 characters. The coverage field indicates whether the grounding is complete.
|
|
3733
3831
|
*
|
|
3734
3832
|
* @param request - MerchandisePlacementDetectionLiteRequest
|
|
3735
3833
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3760,18 +3858,18 @@ export default class Client extends OpenApi {
|
|
|
3760
3858
|
}
|
|
3761
3859
|
|
|
3762
3860
|
/**
|
|
3763
|
-
* Detects product displays in photos of shelves, endcaps, freezers, display
|
|
3861
|
+
* Detects product displays in photos of shelves, endcaps, freezers, display stands, and dump bins by using product SKU recognition and multimodal large model grounding, aggregates product locations by SKU, and supplements the results with visible single-item grounding and short names to facilitate product location display, inventory counting, and distribution verification.
|
|
3764
3862
|
*
|
|
3765
3863
|
* @remarks
|
|
3766
3864
|
* ## Scenarios
|
|
3767
|
-
* - Display
|
|
3768
|
-
* - Distribution
|
|
3865
|
+
* - Display inventory: Aggregates recognized product bounding boxes by SKU for business system statistics.
|
|
3866
|
+
* - Distribution checklist verification: Compares the recognized SKU list with the target checklist on the business side.
|
|
3769
3867
|
* - Single-item location review: Assists in checking recognition results by combining product bounding boxes and visible names.
|
|
3770
3868
|
* ## Features
|
|
3771
|
-
* - Aggregation by SKU: Aggregates multiple
|
|
3772
|
-
* - Supplementary single-item grounding: The multimodal model
|
|
3869
|
+
* - Aggregation by SKU: Aggregates multiple bounding boxes for the same SkuId in Products, and returns a deduplicated list of SKU codes in skuIds.
|
|
3870
|
+
* - Supplementary single-item grounding: The multimodal model locates each recognizable sales package and provides a confirmable short name.
|
|
3773
3871
|
* - Independent use of two result sets: Products comes from SKU recognition, and grounding comes from supplementary grounding. Grounding does not return SKU codes and does not guarantee item-by-item correspondence with Products.
|
|
3774
|
-
* - Supports single HTTPS image input. Supplementary grounding returns up to 12 targets
|
|
3872
|
+
* - Supports a single HTTPS image as input. Supplementary grounding returns up to 12 targets. Each target includes a category, a bounding box, and visible text of up to 24 characters. The coverage field indicates whether the grounding is complete.
|
|
3775
3873
|
*
|
|
3776
3874
|
* @param request - MerchandisePlacementDetectionLiteRequest
|
|
3777
3875
|
* @returns MerchandisePlacementDetectionLiteResponse
|
|
@@ -3782,18 +3880,18 @@ export default class Client extends OpenApi {
|
|
|
3782
3880
|
}
|
|
3783
3881
|
|
|
3784
3882
|
/**
|
|
3785
|
-
* Detects the positions and names of visible products in an image
|
|
3883
|
+
* Detects the positions and names of visible products in an image. Built on a dedicated visual model, this product display detection service supports default recognition rules for the Genki Forest business type and allows the caller to invoke custom rules. It outputs the position and name of each product, and is applicable to beverage display inspection and product positioning.
|
|
3786
3884
|
*
|
|
3787
3885
|
* @remarks
|
|
3788
3886
|
* ## Scenarios
|
|
3789
|
-
* - Beverage display recognition: Uses default rules for the Genki Forest business type to recognize visible beverage products.
|
|
3790
|
-
* - Custom detection rules: Specifies product recognition
|
|
3791
|
-
* - Product
|
|
3887
|
+
* - Beverage display recognition: Uses the default rules for the Genki Forest business type to recognize visible beverage products.
|
|
3888
|
+
* - Custom detection rules: Specifies a product recognition task that meets output constraints by using the rule parameter.
|
|
3889
|
+
* - Product positioning display: Uses the name and bounding box of each product for display, statistics, or manual review.
|
|
3792
3890
|
* ## Features
|
|
3793
|
-
* - Direct product recognition:
|
|
3794
|
-
* - Two rule
|
|
3795
|
-
* - Unified result validation:
|
|
3796
|
-
* - Result scope: Currently outputs detected names and positions
|
|
3891
|
+
* - Direct product recognition: Outputs a bounding box and a name for each product. If the name cannot be determined, unknown is returned.
|
|
3892
|
+
* - Two rule entries: A non-empty rule takes precedence. If no valid rule is provided, the type must be Genki Forest.
|
|
3893
|
+
* - Unified result validation: Converts bounding box coordinates to integers and limits them to 0-1000, and swaps reverse coordinates. Uses unknown when the name is missing. The entire batch fails if any item is not a valid product object, the bounding box is invalid, or the bounding box has no area.
|
|
3894
|
+
* - Result scope: Currently outputs the detected names and positions, and does not include vector database recall, SKU codes, or similarity scores.
|
|
3797
3895
|
*
|
|
3798
3896
|
* @param request - MerchandisePlacementDetectionProRequest
|
|
3799
3897
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3832,18 +3930,18 @@ export default class Client extends OpenApi {
|
|
|
3832
3930
|
}
|
|
3833
3931
|
|
|
3834
3932
|
/**
|
|
3835
|
-
* Detects the positions and names of visible products in an image
|
|
3933
|
+
* Detects the positions and names of visible products in an image. Built on a dedicated visual model, this product display detection service supports default recognition rules for the Genki Forest business type and allows the caller to invoke custom rules. It outputs the position and name of each product, and is applicable to beverage display inspection and product positioning.
|
|
3836
3934
|
*
|
|
3837
3935
|
* @remarks
|
|
3838
3936
|
* ## Scenarios
|
|
3839
|
-
* - Beverage display recognition: Uses default rules for the Genki Forest business type to recognize visible beverage products.
|
|
3840
|
-
* - Custom detection rules: Specifies product recognition
|
|
3841
|
-
* - Product
|
|
3937
|
+
* - Beverage display recognition: Uses the default rules for the Genki Forest business type to recognize visible beverage products.
|
|
3938
|
+
* - Custom detection rules: Specifies a product recognition task that meets output constraints by using the rule parameter.
|
|
3939
|
+
* - Product positioning display: Uses the name and bounding box of each product for display, statistics, or manual review.
|
|
3842
3940
|
* ## Features
|
|
3843
|
-
* - Direct product recognition:
|
|
3844
|
-
* - Two rule
|
|
3845
|
-
* - Unified result validation:
|
|
3846
|
-
* - Result scope: Currently outputs detected names and positions
|
|
3941
|
+
* - Direct product recognition: Outputs a bounding box and a name for each product. If the name cannot be determined, unknown is returned.
|
|
3942
|
+
* - Two rule entries: A non-empty rule takes precedence. If no valid rule is provided, the type must be Genki Forest.
|
|
3943
|
+
* - Unified result validation: Converts bounding box coordinates to integers and limits them to 0-1000, and swaps reverse coordinates. Uses unknown when the name is missing. The entire batch fails if any item is not a valid product object, the bounding box is invalid, or the bounding box has no area.
|
|
3944
|
+
* - Result scope: Currently outputs the detected names and positions, and does not include vector database recall, SKU codes, or similarity scores.
|
|
3847
3945
|
*
|
|
3848
3946
|
* @param request - MerchandisePlacementDetectionProRequest
|
|
3849
3947
|
* @returns MerchandisePlacementDetectionProResponse
|
|
@@ -3854,18 +3952,18 @@ export default class Client extends OpenApi {
|
|
|
3854
3952
|
}
|
|
3855
3953
|
|
|
3856
3954
|
/**
|
|
3857
|
-
* Detects display price tags based on price tag recognition and multimodal large model
|
|
3955
|
+
* Detects display price tags based on price tag recognition and multimodal large model grounding. This operation extracts product information, selling prices, original prices, and locations from price tags, and provides visible bounding boxes for paper price tags, electronic price tags, and promotional price tags. It is applicable to store price collection, price tag inspection, and business-side price verification.
|
|
3858
3956
|
*
|
|
3859
3957
|
* @remarks
|
|
3860
3958
|
* ## Scenarios
|
|
3861
|
-
* - Store price collection: Reads the
|
|
3959
|
+
* - Store price collection: Reads and recognizes the selling prices and available original prices of price tags.
|
|
3862
3960
|
* - Price execution verification: Compares the recognized prices with the business-side price list.
|
|
3863
|
-
* - Manual price tag review: Locates paper, electronic, and promotional price tags
|
|
3961
|
+
* - Manual price tag review: Locates paper, electronic, and promotional price tags for easy review of the original images.
|
|
3864
3962
|
* ## Features
|
|
3865
3963
|
* - Structured price output: Returns the product name, code, price, and location item by item. Prices are retained as strings.
|
|
3866
|
-
* - Multi-type price tag
|
|
3867
|
-
* - Original text and location-assisted review: Prioritizes extracting clear selling prices
|
|
3868
|
-
* - Supports single HTTPS image input. Supplementary
|
|
3964
|
+
* - Multi-type price tag grounding: Covers ordinary paper price tags, electronic price tags, and promotional tags with clear selling prices.
|
|
3965
|
+
* - Original text and location-assisted review: Prioritizes extracting clear selling prices based on located text. Leaves the field empty if the text is unreadable. Supplementary grounding does not infer that a price tag necessarily corresponds to a specific SKU based on its location.
|
|
3966
|
+
* - Supports single HTTPS image input. Supplementary grounding returns up to 12 targets. Each target includes a category, a bounding box, and up to 24 characters of visible text, and uses the coverage field to indicate whether the grounding is complete.
|
|
3869
3967
|
*
|
|
3870
3968
|
* @param request - MerchandisePriceTagDetectionRequest
|
|
3871
3969
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3896,18 +3994,18 @@ export default class Client extends OpenApi {
|
|
|
3896
3994
|
}
|
|
3897
3995
|
|
|
3898
3996
|
/**
|
|
3899
|
-
* Detects display price tags based on price tag recognition and multimodal large model
|
|
3997
|
+
* Detects display price tags based on price tag recognition and multimodal large model grounding. This operation extracts product information, selling prices, original prices, and locations from price tags, and provides visible bounding boxes for paper price tags, electronic price tags, and promotional price tags. It is applicable to store price collection, price tag inspection, and business-side price verification.
|
|
3900
3998
|
*
|
|
3901
3999
|
* @remarks
|
|
3902
4000
|
* ## Scenarios
|
|
3903
|
-
* - Store price collection: Reads the
|
|
4001
|
+
* - Store price collection: Reads and recognizes the selling prices and available original prices of price tags.
|
|
3904
4002
|
* - Price execution verification: Compares the recognized prices with the business-side price list.
|
|
3905
|
-
* - Manual price tag review: Locates paper, electronic, and promotional price tags
|
|
4003
|
+
* - Manual price tag review: Locates paper, electronic, and promotional price tags for easy review of the original images.
|
|
3906
4004
|
* ## Features
|
|
3907
4005
|
* - Structured price output: Returns the product name, code, price, and location item by item. Prices are retained as strings.
|
|
3908
|
-
* - Multi-type price tag
|
|
3909
|
-
* - Original text and location-assisted review: Prioritizes extracting clear selling prices
|
|
3910
|
-
* - Supports single HTTPS image input. Supplementary
|
|
4006
|
+
* - Multi-type price tag grounding: Covers ordinary paper price tags, electronic price tags, and promotional tags with clear selling prices.
|
|
4007
|
+
* - Original text and location-assisted review: Prioritizes extracting clear selling prices based on located text. Leaves the field empty if the text is unreadable. Supplementary grounding does not infer that a price tag necessarily corresponds to a specific SKU based on its location.
|
|
4008
|
+
* - Supports single HTTPS image input. Supplementary grounding returns up to 12 targets. Each target includes a category, a bounding box, and up to 24 characters of visible text, and uses the coverage field to indicate whether the grounding is complete.
|
|
3911
4009
|
*
|
|
3912
4010
|
* @param request - MerchandisePriceTagDetectionRequest
|
|
3913
4011
|
* @returns MerchandisePriceTagDetectionResponse
|
|
@@ -3918,18 +4016,18 @@ export default class Client extends OpenApi {
|
|
|
3918
4016
|
}
|
|
3919
4017
|
|
|
3920
4018
|
/**
|
|
3921
|
-
* Detects store displays based on display scene recognition and holistic positioning
|
|
4019
|
+
* Detects store displays based on display scene recognition and holistic positioning of multimodal large models. Identifies display areas such as shelves, refrigerators, and floor displays, outputs available scene names, locations, and display metrics, and supplements overall facility bounding boxes for display facility inspection, area visualization, and display metric verification.
|
|
3922
4020
|
*
|
|
3923
4021
|
* @remarks
|
|
3924
4022
|
* ## Scenarios
|
|
3925
|
-
* - Display facility inspection:
|
|
3926
|
-
* - Display metric verification:
|
|
3927
|
-
* - Display area visualization:
|
|
4023
|
+
* - Display facility inspection: Identifies facilities such as shelves, endcaps, floor displays, upright refrigerators, and chest freezers.
|
|
4024
|
+
* - Display metric verification: Reads active metrics such as proportion, purity, and fullness for further evaluation by business systems.
|
|
4025
|
+
* - Display area visualization: Displays area locations and overall facility bounding boxes on the original image.
|
|
3928
4026
|
* ## Features
|
|
3929
|
-
* - Scene structured output:
|
|
3930
|
-
* - Holistic facility positioning:
|
|
3931
|
-
* - Retains two types of coordinates:
|
|
3932
|
-
* - Supports
|
|
4027
|
+
* - Scene structured output: Returns scene names, center points, area contours, and active metrics.
|
|
4028
|
+
* - Holistic facility positioning: Uses one bounding box for an independent facility or promotional display, which is suitable for overall area review.
|
|
4029
|
+
* - Retains two types of coordinates: The positions in scenes retain the original normalization coordinates of the recognition service, while grounding uses 0-1000 integer bounding boxes.
|
|
4030
|
+
* - Supports single HTTPS image input. The supplementary positioning returns up to 12 targets. Each target includes a category, a bounding box, and up to 24 characters of visible text, and uses coverage to indicate whether the positioning is complete.
|
|
3933
4031
|
*
|
|
3934
4032
|
* @param request - MerchandiseSceneDetectionRequest
|
|
3935
4033
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3960,18 +4058,18 @@ export default class Client extends OpenApi {
|
|
|
3960
4058
|
}
|
|
3961
4059
|
|
|
3962
4060
|
/**
|
|
3963
|
-
* Detects store displays based on display scene recognition and holistic positioning
|
|
4061
|
+
* Detects store displays based on display scene recognition and holistic positioning of multimodal large models. Identifies display areas such as shelves, refrigerators, and floor displays, outputs available scene names, locations, and display metrics, and supplements overall facility bounding boxes for display facility inspection, area visualization, and display metric verification.
|
|
3964
4062
|
*
|
|
3965
4063
|
* @remarks
|
|
3966
4064
|
* ## Scenarios
|
|
3967
|
-
* - Display facility inspection:
|
|
3968
|
-
* - Display metric verification:
|
|
3969
|
-
* - Display area visualization:
|
|
4065
|
+
* - Display facility inspection: Identifies facilities such as shelves, endcaps, floor displays, upright refrigerators, and chest freezers.
|
|
4066
|
+
* - Display metric verification: Reads active metrics such as proportion, purity, and fullness for further evaluation by business systems.
|
|
4067
|
+
* - Display area visualization: Displays area locations and overall facility bounding boxes on the original image.
|
|
3970
4068
|
* ## Features
|
|
3971
|
-
* - Scene structured output:
|
|
3972
|
-
* - Holistic facility positioning:
|
|
3973
|
-
* - Retains two types of coordinates:
|
|
3974
|
-
* - Supports
|
|
4069
|
+
* - Scene structured output: Returns scene names, center points, area contours, and active metrics.
|
|
4070
|
+
* - Holistic facility positioning: Uses one bounding box for an independent facility or promotional display, which is suitable for overall area review.
|
|
4071
|
+
* - Retains two types of coordinates: The positions in scenes retain the original normalization coordinates of the recognition service, while grounding uses 0-1000 integer bounding boxes.
|
|
4072
|
+
* - Supports single HTTPS image input. The supplementary positioning returns up to 12 targets. Each target includes a category, a bounding box, and up to 24 characters of visible text, and uses coverage to indicate whether the positioning is complete.
|
|
3975
4073
|
*
|
|
3976
4074
|
* @param request - MerchandiseSceneDetectionRequest
|
|
3977
4075
|
* @returns MerchandiseSceneDetectionResponse
|
|
@@ -3982,16 +4080,16 @@ export default class Client extends OpenApi {
|
|
|
3982
4080
|
}
|
|
3983
4081
|
|
|
3984
4082
|
/**
|
|
3985
|
-
*
|
|
4083
|
+
* Detects recaptured images of milk powder can bottom codes and localizes elements based on recapture recognition and multimodal large model capabilities. The operation determines whether an uploaded photo is recaptured and localizes visible milk powder products, can bottoms, and bottom code areas. It applies to milk powder channel inspections, bottom code photo reviews, and manual verifications.
|
|
3986
4084
|
*
|
|
3987
4085
|
* @remarks
|
|
3988
4086
|
* ## Features
|
|
3989
|
-
* - Recapture binary classification: isFake=true indicates a
|
|
3990
|
-
* - Milk powder subject and bottom code localization: Prioritizes the localization of the milk powder subject. Adds
|
|
4087
|
+
* - Recapture binary classification: isFake=true indicates a recaptured image, and false indicates a non-recaptured image. Element localization is performed for both results.
|
|
4088
|
+
* - Milk powder subject and bottom code localization: Prioritizes the localization of the milk powder subject. Adds bounding boxes for the can bottom, spray code, batch code, or traceability code areas when they are clear.
|
|
3991
4089
|
* - Visible information output: Outputs only confirmed short names or text without guessing blurred code values. Localization results do not change the recapture conclusion.
|
|
3992
|
-
* - Supports a single HTTPS image input.
|
|
3993
|
-
* ## Scenarios
|
|
3994
|
-
* -
|
|
4090
|
+
* - Supports a single HTTPS image input. Supplementary localization returns up to 12 targets. Each target includes a category, a bounding box, and up to 24 characters of visible text. The coverage field indicates whether the localization is complete.
|
|
4091
|
+
* ## Scenarios
|
|
4092
|
+
* - Bottom code photo review: Determines whether a photo of a milk powder can bottom code has a recapture risk.
|
|
3995
4093
|
* - Milk powder product inspection: Localizes canned, boxed, or bagged milk powder, as well as clearly visible can bottoms and bottom codes.
|
|
3996
4094
|
* - Review result playback: Displays target bounding boxes on the original image to assist personnel in verifying the photo content.
|
|
3997
4095
|
*
|
|
@@ -4024,16 +4122,16 @@ export default class Client extends OpenApi {
|
|
|
4024
4122
|
}
|
|
4025
4123
|
|
|
4026
4124
|
/**
|
|
4027
|
-
*
|
|
4125
|
+
* Detects recaptured images of milk powder can bottom codes and localizes elements based on recapture recognition and multimodal large model capabilities. The operation determines whether an uploaded photo is recaptured and localizes visible milk powder products, can bottoms, and bottom code areas. It applies to milk powder channel inspections, bottom code photo reviews, and manual verifications.
|
|
4028
4126
|
*
|
|
4029
4127
|
* @remarks
|
|
4030
4128
|
* ## Features
|
|
4031
|
-
* - Recapture binary classification: isFake=true indicates a
|
|
4032
|
-
* - Milk powder subject and bottom code localization: Prioritizes the localization of the milk powder subject. Adds
|
|
4129
|
+
* - Recapture binary classification: isFake=true indicates a recaptured image, and false indicates a non-recaptured image. Element localization is performed for both results.
|
|
4130
|
+
* - Milk powder subject and bottom code localization: Prioritizes the localization of the milk powder subject. Adds bounding boxes for the can bottom, spray code, batch code, or traceability code areas when they are clear.
|
|
4033
4131
|
* - Visible information output: Outputs only confirmed short names or text without guessing blurred code values. Localization results do not change the recapture conclusion.
|
|
4034
|
-
* - Supports a single HTTPS image input.
|
|
4035
|
-
* ## Scenarios
|
|
4036
|
-
* -
|
|
4132
|
+
* - Supports a single HTTPS image input. Supplementary localization returns up to 12 targets. Each target includes a category, a bounding box, and up to 24 characters of visible text. The coverage field indicates whether the localization is complete.
|
|
4133
|
+
* ## Scenarios
|
|
4134
|
+
* - Bottom code photo review: Determines whether a photo of a milk powder can bottom code has a recapture risk.
|
|
4037
4135
|
* - Milk powder product inspection: Localizes canned, boxed, or bagged milk powder, as well as clearly visible can bottoms and bottom codes.
|
|
4038
4136
|
* - Review result playback: Displays target bounding boxes on the original image to assist personnel in verifying the photo content.
|
|
4039
4137
|
*
|
|
@@ -4046,16 +4144,16 @@ export default class Client extends OpenApi {
|
|
|
4046
4144
|
}
|
|
4047
4145
|
|
|
4048
4146
|
/**
|
|
4049
|
-
*
|
|
4147
|
+
* Analyzes milk powder box code images for channel inspection by using recapture detection and multimodal large model element grounding. Outputs non-recapture, recapture, or suspected recapture conclusions, and locates visible milk powder products, outer boxes, and code areas to provide a structured basis for photo review and manual verification.
|
|
4050
4148
|
*
|
|
4051
4149
|
* @remarks
|
|
4052
4150
|
* ## Features
|
|
4053
|
-
* - Three-state recapture detection: When photoStatus is 0, 1, or 2, it indicates non-recapture, recapture, or suspected recapture, respectively. The isFake, isSuspect, and score
|
|
4054
|
-
* - Subject and code area grounding: Prioritizes
|
|
4055
|
-
* - Result
|
|
4056
|
-
* - Supports a single HTTPS image as input. The supplementary grounding returns up to 12 targets
|
|
4151
|
+
* - Three-state recapture detection: When photoStatus is 0, 1, or 2, it indicates non-recapture, recapture, or suspected recapture, respectively. The operation also outputs isFake, isSuspect, and score.
|
|
4152
|
+
* - Subject and code area grounding: Prioritizes grounding of individual milk powder products and outer boxes, and supplements clear box codes, barcodes, and QR code areas. If no box code is present, the milk powder subject can still be grounded.
|
|
4153
|
+
* - Result synergy: Element grounding supplements visible targets without changing the recapture detection conclusion. It does not decode QR codes or provide product authenticity verification.
|
|
4154
|
+
* - Supports a single HTTPS image as input. The supplementary grounding returns up to 12 targets, each containing a category, bounding box, and up to 24 characters of visible text. The coverage field indicates whether the grounding is complete.
|
|
4057
4155
|
* ## Scenarios
|
|
4058
|
-
* - Box code photo review: Checks
|
|
4156
|
+
* - Box code photo review: Checks milk powder outer box photos uploaded by stores or channels for recapture risks.
|
|
4059
4157
|
* - Milk powder display inspection: Locates visible individual milk powder products, full boxes, and clear code areas in photos.
|
|
4060
4158
|
* - Suspected sample review: Filters images that require manual verification based on the suspected status, algorithm score, and bounding boxes.
|
|
4061
4159
|
*
|
|
@@ -4088,16 +4186,16 @@ export default class Client extends OpenApi {
|
|
|
4088
4186
|
}
|
|
4089
4187
|
|
|
4090
4188
|
/**
|
|
4091
|
-
*
|
|
4189
|
+
* Analyzes milk powder box code images for channel inspection by using recapture detection and multimodal large model element grounding. Outputs non-recapture, recapture, or suspected recapture conclusions, and locates visible milk powder products, outer boxes, and code areas to provide a structured basis for photo review and manual verification.
|
|
4092
4190
|
*
|
|
4093
4191
|
* @remarks
|
|
4094
4192
|
* ## Features
|
|
4095
|
-
* - Three-state recapture detection: When photoStatus is 0, 1, or 2, it indicates non-recapture, recapture, or suspected recapture, respectively. The isFake, isSuspect, and score
|
|
4096
|
-
* - Subject and code area grounding: Prioritizes
|
|
4097
|
-
* - Result
|
|
4098
|
-
* - Supports a single HTTPS image as input. The supplementary grounding returns up to 12 targets
|
|
4193
|
+
* - Three-state recapture detection: When photoStatus is 0, 1, or 2, it indicates non-recapture, recapture, or suspected recapture, respectively. The operation also outputs isFake, isSuspect, and score.
|
|
4194
|
+
* - Subject and code area grounding: Prioritizes grounding of individual milk powder products and outer boxes, and supplements clear box codes, barcodes, and QR code areas. If no box code is present, the milk powder subject can still be grounded.
|
|
4195
|
+
* - Result synergy: Element grounding supplements visible targets without changing the recapture detection conclusion. It does not decode QR codes or provide product authenticity verification.
|
|
4196
|
+
* - Supports a single HTTPS image as input. The supplementary grounding returns up to 12 targets, each containing a category, bounding box, and up to 24 characters of visible text. The coverage field indicates whether the grounding is complete.
|
|
4099
4197
|
* ## Scenarios
|
|
4100
|
-
* - Box code photo review: Checks
|
|
4198
|
+
* - Box code photo review: Checks milk powder outer box photos uploaded by stores or channels for recapture risks.
|
|
4101
4199
|
* - Milk powder display inspection: Locates visible individual milk powder products, full boxes, and clear code areas in photos.
|
|
4102
4200
|
* - Suspected sample review: Filters images that require manual verification based on the suspected status, algorithm score, and bounding boxes.
|
|
4103
4201
|
*
|
|
@@ -4242,28 +4340,28 @@ export default class Client extends OpenApi {
|
|
|
4242
4340
|
}
|
|
4243
4341
|
|
|
4244
4342
|
/**
|
|
4245
|
-
* Maas-MT
|
|
4343
|
+
* Provides Maas-MT, an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs, which is continuously optimized for e-commerce-specific terms such as brands, models, materials, and attributes. Supports translation across more than 400 language pairs, including bridged pairs, with a focus on Chinese-English, Chinese-multilingual, and English-multilingual translations. Supports language detection for 24 language pairs and automatically detects the source language if it is not specified.
|
|
4246
4344
|
*
|
|
4247
4345
|
* @remarks
|
|
4248
|
-
* ## Product
|
|
4249
|
-
* Marco MT is an e-commerce translation model trained on over 1 billion
|
|
4250
|
-
* ##
|
|
4251
|
-
* - Product titles: Marco MT large model translation accurately
|
|
4252
|
-
* - Product descriptions: Product descriptions are
|
|
4253
|
-
* - Product attributes: Product attribute terms are
|
|
4254
|
-
* - Customer service conversations: In customer service scenarios,
|
|
4255
|
-
* Marco MT large model translation can also be used for general
|
|
4346
|
+
* ## Product introduction
|
|
4347
|
+
* Marco MT is an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs, continuously optimized for e-commerce-specific terms such as brands, models, materials, and attributes. It supports translation across more than 100 language pairs, including bridged pairs, especially between Chinese and English, Chinese and multiple languages, and English and multiple languages. It supports language detection for 24 language pairs and automatically detects the source language if it is not specified.
|
|
4348
|
+
* ## Scenarios
|
|
4349
|
+
* - Product titles: Marco MT large model translation can accurately translate phrases, keywords, and trending words in product titles into the target language, increasing product exposure on e-commerce platforms.
|
|
4350
|
+
* - Product descriptions: Product descriptions are generally long and have diverse and complex formats. Marco MT large model translation supports long-text translation and HTML format, delivering excellent translation quality and format restoration.
|
|
4351
|
+
* - Product attributes: Product attribute terms are short and contain e-commerce-specific words, such as models and parameters.
|
|
4352
|
+
* - Customer service conversations: In customer service scenarios, it can optimize issues such as missing context and typos, and supports polite expressions in some language pairs.
|
|
4353
|
+
* Additionally, Marco MT large model translation can also be used for translation in general scenarios, such as office work, meetings, and daily conversations.
|
|
4256
4354
|
* ## Features
|
|
4257
|
-
* - **Supported language
|
|
4258
|
-
* - **Ultra-low hallucination rate and high-speed inference
|
|
4259
|
-
* - **Supported text
|
|
4260
|
-
* - **Translation intervention
|
|
4355
|
+
* - **Supported language pairs**: Marco MT large model translation supports translation between more than 100 languages and language detection for 23 languages. For specific language pairs, refer to the language mapping table in Section 5.6.
|
|
4356
|
+
* - **Ultra-low hallucination rate and high-speed inference**: Marco MT large model translation is a large language model aligned with preferences for translation scenarios. Compared with general large language models, it features faster translation inference speed and an extremely low hallucination rate, making it especially suitable for large-scale invocation scenarios.
|
|
4357
|
+
* - **Supported text formats**: Currently supports text and HTML formats.
|
|
4358
|
+
* - **Translation intervention**: Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and skip translation (ABC-null). This is commonly used for brand word protection. You only need to pass the corresponding intervention glossary ID when calling the API. This meets your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention terms. If you need more, contact the platform.
|
|
4261
4359
|
* ## Translation quality comparison
|
|
4262
|
-
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation
|
|
4360
|
+
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation advantages** |
|
|
4263
4361
|
* |----------|---------------|-----------------------|-----------------------|---------------------|
|
|
4264
4362
|
* | 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 |
|
|
4265
|
-
* | 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
|
|
4266
|
-
* | 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
|
|
4363
|
+
* | 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 |
|
|
4364
|
+
* | Men Key Bag Genuine Cow Leather Buckets Key Cases Pouch Zipper Keychain Auto Car Key Case Women Home Key Holder Wallet | Sac à clés pour hommes en cuir de vache véritable, étuis à clés, pochette à fermeture éclair, porte-clés, étui à clé de voiture, porte-clés pour femmes, organisateur de portefeuille | Porte-clés sac en cuir de vache véritable, étuis à clés en forme de seau, pochette à fermeture éclair, porte-clés auto pour voiture, étui à clés pour femmes, organisateur de clés de maison, portefeuille. | Hommes porte-clés en cuir de vache véritable sac/pochette fermature éclair porte-clés Auto voiture porte-clés femmes maison porte-clés organisateur portefeuille | Clearer and more explicit product subject expression, identifying it as a "key bag" rather than a "keychain", whereas other translations may cause ambiguity regarding the product subject |
|
|
4267
4365
|
*
|
|
4268
4366
|
* @param tmpReq - PrepaidTextTranslateRequest
|
|
4269
4367
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -4324,28 +4422,28 @@ export default class Client extends OpenApi {
|
|
|
4324
4422
|
}
|
|
4325
4423
|
|
|
4326
4424
|
/**
|
|
4327
|
-
* Maas-MT
|
|
4425
|
+
* Provides Maas-MT, an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs, which is continuously optimized for e-commerce-specific terms such as brands, models, materials, and attributes. Supports translation across more than 400 language pairs, including bridged pairs, with a focus on Chinese-English, Chinese-multilingual, and English-multilingual translations. Supports language detection for 24 language pairs and automatically detects the source language if it is not specified.
|
|
4328
4426
|
*
|
|
4329
4427
|
* @remarks
|
|
4330
|
-
* ## Product
|
|
4331
|
-
* Marco MT is an e-commerce translation model trained on over 1 billion
|
|
4332
|
-
* ##
|
|
4333
|
-
* - Product titles: Marco MT large model translation accurately
|
|
4334
|
-
* - Product descriptions: Product descriptions are
|
|
4335
|
-
* - Product attributes: Product attribute terms are
|
|
4336
|
-
* - Customer service conversations: In customer service scenarios,
|
|
4337
|
-
* Marco MT large model translation can also be used for general
|
|
4428
|
+
* ## Product introduction
|
|
4429
|
+
* Marco MT is an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs, continuously optimized for e-commerce-specific terms such as brands, models, materials, and attributes. It supports translation across more than 100 language pairs, including bridged pairs, especially between Chinese and English, Chinese and multiple languages, and English and multiple languages. It supports language detection for 24 language pairs and automatically detects the source language if it is not specified.
|
|
4430
|
+
* ## Scenarios
|
|
4431
|
+
* - Product titles: Marco MT large model translation can accurately translate phrases, keywords, and trending words in product titles into the target language, increasing product exposure on e-commerce platforms.
|
|
4432
|
+
* - Product descriptions: Product descriptions are generally long and have diverse and complex formats. Marco MT large model translation supports long-text translation and HTML format, delivering excellent translation quality and format restoration.
|
|
4433
|
+
* - Product attributes: Product attribute terms are short and contain e-commerce-specific words, such as models and parameters.
|
|
4434
|
+
* - Customer service conversations: In customer service scenarios, it can optimize issues such as missing context and typos, and supports polite expressions in some language pairs.
|
|
4435
|
+
* Additionally, Marco MT large model translation can also be used for translation in general scenarios, such as office work, meetings, and daily conversations.
|
|
4338
4436
|
* ## Features
|
|
4339
|
-
* - **Supported language
|
|
4340
|
-
* - **Ultra-low hallucination rate and high-speed inference
|
|
4341
|
-
* - **Supported text
|
|
4342
|
-
* - **Translation intervention
|
|
4437
|
+
* - **Supported language pairs**: Marco MT large model translation supports translation between more than 100 languages and language detection for 23 languages. For specific language pairs, refer to the language mapping table in Section 5.6.
|
|
4438
|
+
* - **Ultra-low hallucination rate and high-speed inference**: Marco MT large model translation is a large language model aligned with preferences for translation scenarios. Compared with general large language models, it features faster translation inference speed and an extremely low hallucination rate, making it especially suitable for large-scale invocation scenarios.
|
|
4439
|
+
* - **Supported text formats**: Currently supports text and HTML formats.
|
|
4440
|
+
* - **Translation intervention**: Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and skip translation (ABC-null). This is commonly used for brand word protection. You only need to pass the corresponding intervention glossary ID when calling the API. This meets your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention terms. If you need more, contact the platform.
|
|
4343
4441
|
* ## Translation quality comparison
|
|
4344
|
-
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation
|
|
4442
|
+
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation advantages** |
|
|
4345
4443
|
* |----------|---------------|-----------------------|-----------------------|---------------------|
|
|
4346
4444
|
* | 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 |
|
|
4347
|
-
* | 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
|
|
4348
|
-
* | 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
|
|
4445
|
+
* | 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 |
|
|
4446
|
+
* | Men Key Bag Genuine Cow Leather Buckets Key Cases Pouch Zipper Keychain Auto Car Key Case Women Home Key Holder Wallet | Sac à clés pour hommes en cuir de vache véritable, étuis à clés, pochette à fermeture éclair, porte-clés, étui à clé de voiture, porte-clés pour femmes, organisateur de portefeuille | Porte-clés sac en cuir de vache véritable, étuis à clés en forme de seau, pochette à fermeture éclair, porte-clés auto pour voiture, étui à clés pour femmes, organisateur de clés de maison, portefeuille. | Hommes porte-clés en cuir de vache véritable sac/pochette fermature éclair porte-clés Auto voiture porte-clés femmes maison porte-clés organisateur portefeuille | Clearer and more explicit product subject expression, identifying it as a "key bag" rather than a "keychain", whereas other translations may cause ambiguity regarding the product subject |
|
|
4349
4447
|
*
|
|
4350
4448
|
* @param request - PrepaidTextTranslateRequest
|
|
4351
4449
|
* @returns PrepaidTextTranslateResponse
|
|
@@ -4433,6 +4531,104 @@ export default class Client extends OpenApi {
|
|
|
4433
4531
|
return await this.productHotspotDetectionWithOptions(request, runtime);
|
|
4434
4532
|
}
|
|
4435
4533
|
|
|
4534
|
+
/**
|
|
4535
|
+
* Generates a single-product showcase video for e-commerce merchants and platforms based on the product title and multiple images of the same product. This API optionally accepts a storyboard script, automatically selects reference images, plans a three-shot storyboard, and generates the video. It uses asynchronous tasks, supports 720p and 1080p resolutions and four aspect ratios, and is suitable for content production of non-apparel products. For apparel products, use the E-commerce Video Enhanced Edition.
|
|
4536
|
+
*
|
|
4537
|
+
* @remarks
|
|
4538
|
+
* # Product introduction
|
|
4539
|
+
* The basic e-commerce video edition is designed for e-commerce merchants and platforms. It generates a single-product showcase video based on the product title and multiple images of the same product. You can optionally provide a storyboard script. The system automatically selects reference images, plans a three-shot storyboard, and generates the video. The API uses asynchronous tasks, supports 720p and 1080p resolutions and four aspect ratios, and is suitable for content production of non-apparel products. For apparel products, use the e-commerce enhanced edition.
|
|
4540
|
+
* # Scenarios
|
|
4541
|
+
* - New product material generation: Provide the product title and images to automatically plan storyboard shots such as product debut, details, or usage demonstrations.
|
|
4542
|
+
* - Video production with existing scripts: Provide a storyboard script or creative description. The system optimizes the storyboard script based on the product images and retains shot intentions that are supported by the images.
|
|
4543
|
+
* - Adaptation to different video placements: Use the aspect ratio parameter to adapt to vertical short videos, main product images, detail pages, and horizontal displays. For batch production, each request corresponds to one product and one video.
|
|
4544
|
+
* # Features
|
|
4545
|
+
* - Automatic image selection and storyboard planning: When no script is provided, the system generates a storyboard based on the product title and images. When a script is provided, the system still performs image selection and planning, eliminating the need for callers to organize video prompts.
|
|
4546
|
+
* - Product appearance consistency constraint: The system uses the selected complete product image as the appearance baseline. It checks the color scheme, structure, proportions, texture, version, and specifications of other images, and selects only reference images that can be confirmed to belong to the same SKU.
|
|
4547
|
+
* - Flexible video specifications: Without a script, the duration is 5 to 15 seconds. With a script, the duration is 5 to 30 seconds. The system supports four aspect ratios (16:9, 1:1, 3:4, and 9:16) and two resolutions (720p and 1080p).
|
|
4548
|
+
* - Asynchronous generation and task query: After a task is created, a task ID is returned. The caller queries the result by using the query API. The final video includes background music, no voiceover, and no additional subtitles or marketing text.
|
|
4549
|
+
* # Examples
|
|
4550
|
+
* [View the attachment "Digital_040_WiFi6_Gigabit_Router.mp4" in the DingTalk document.](https://alidocs.dingtalk.com/i/nodes/gwva2dxOW4vRkd9DUn1g1p6kJbkz3BRL?cid=6760411388:7016395022&corpId=dingd8e1123006514592&iframeQuery=anchorId%3DX02mvsyycduj3nepwoeush&utm_medium=im_card&utm_scene=person_space&utm_source=im)
|
|
4551
|
+
*
|
|
4552
|
+
* @param tmpReq - ProductVideoGenerationRequest
|
|
4553
|
+
* @param runtime - runtime options for this request RuntimeOptions
|
|
4554
|
+
* @returns ProductVideoGenerationResponse
|
|
4555
|
+
*/
|
|
4556
|
+
async productVideoGenerationWithOptions(tmpReq: $_model.ProductVideoGenerationRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ProductVideoGenerationResponse> {
|
|
4557
|
+
tmpReq.validate();
|
|
4558
|
+
let request = new $_model.ProductVideoGenerationShrinkRequest({ });
|
|
4559
|
+
OpenApiUtil.convert(tmpReq, request);
|
|
4560
|
+
if (!$dara.isNull(tmpReq.productImages)) {
|
|
4561
|
+
request.productImagesShrink = OpenApiUtil.arrayToStringWithSpecifiedStyle(tmpReq.productImages, "product_images", "json");
|
|
4562
|
+
}
|
|
4563
|
+
|
|
4564
|
+
let query = { };
|
|
4565
|
+
if (!$dara.isNull(request.aspectRatio)) {
|
|
4566
|
+
query["aspect_ratio"] = request.aspectRatio;
|
|
4567
|
+
}
|
|
4568
|
+
|
|
4569
|
+
if (!$dara.isNull(request.duration)) {
|
|
4570
|
+
query["duration"] = request.duration;
|
|
4571
|
+
}
|
|
4572
|
+
|
|
4573
|
+
if (!$dara.isNull(request.productImagesShrink)) {
|
|
4574
|
+
query["product_images"] = request.productImagesShrink;
|
|
4575
|
+
}
|
|
4576
|
+
|
|
4577
|
+
if (!$dara.isNull(request.productTitle)) {
|
|
4578
|
+
query["product_title"] = request.productTitle;
|
|
4579
|
+
}
|
|
4580
|
+
|
|
4581
|
+
if (!$dara.isNull(request.resolution)) {
|
|
4582
|
+
query["resolution"] = request.resolution;
|
|
4583
|
+
}
|
|
4584
|
+
|
|
4585
|
+
if (!$dara.isNull(request.script)) {
|
|
4586
|
+
query["script"] = request.script;
|
|
4587
|
+
}
|
|
4588
|
+
|
|
4589
|
+
let req = new $OpenApiUtil.OpenApiRequest({
|
|
4590
|
+
query: OpenApiUtil.query(query),
|
|
4591
|
+
});
|
|
4592
|
+
let params = new $OpenApiUtil.Params({
|
|
4593
|
+
action: "ProductVideoGeneration",
|
|
4594
|
+
version: "2026-04-28",
|
|
4595
|
+
protocol: "HTTPS",
|
|
4596
|
+
pathname: "/",
|
|
4597
|
+
method: "POST",
|
|
4598
|
+
authType: "AK",
|
|
4599
|
+
style: "RPC",
|
|
4600
|
+
reqBodyType: "formData",
|
|
4601
|
+
bodyType: "json",
|
|
4602
|
+
});
|
|
4603
|
+
return $dara.cast<$_model.ProductVideoGenerationResponse>(await this.callApi(params, req, runtime), new $_model.ProductVideoGenerationResponse({}));
|
|
4604
|
+
}
|
|
4605
|
+
|
|
4606
|
+
/**
|
|
4607
|
+
* Generates a single-product showcase video for e-commerce merchants and platforms based on the product title and multiple images of the same product. This API optionally accepts a storyboard script, automatically selects reference images, plans a three-shot storyboard, and generates the video. It uses asynchronous tasks, supports 720p and 1080p resolutions and four aspect ratios, and is suitable for content production of non-apparel products. For apparel products, use the E-commerce Video Enhanced Edition.
|
|
4608
|
+
*
|
|
4609
|
+
* @remarks
|
|
4610
|
+
* # Product introduction
|
|
4611
|
+
* The basic e-commerce video edition is designed for e-commerce merchants and platforms. It generates a single-product showcase video based on the product title and multiple images of the same product. You can optionally provide a storyboard script. The system automatically selects reference images, plans a three-shot storyboard, and generates the video. The API uses asynchronous tasks, supports 720p and 1080p resolutions and four aspect ratios, and is suitable for content production of non-apparel products. For apparel products, use the e-commerce enhanced edition.
|
|
4612
|
+
* # Scenarios
|
|
4613
|
+
* - New product material generation: Provide the product title and images to automatically plan storyboard shots such as product debut, details, or usage demonstrations.
|
|
4614
|
+
* - Video production with existing scripts: Provide a storyboard script or creative description. The system optimizes the storyboard script based on the product images and retains shot intentions that are supported by the images.
|
|
4615
|
+
* - Adaptation to different video placements: Use the aspect ratio parameter to adapt to vertical short videos, main product images, detail pages, and horizontal displays. For batch production, each request corresponds to one product and one video.
|
|
4616
|
+
* # Features
|
|
4617
|
+
* - Automatic image selection and storyboard planning: When no script is provided, the system generates a storyboard based on the product title and images. When a script is provided, the system still performs image selection and planning, eliminating the need for callers to organize video prompts.
|
|
4618
|
+
* - Product appearance consistency constraint: The system uses the selected complete product image as the appearance baseline. It checks the color scheme, structure, proportions, texture, version, and specifications of other images, and selects only reference images that can be confirmed to belong to the same SKU.
|
|
4619
|
+
* - Flexible video specifications: Without a script, the duration is 5 to 15 seconds. With a script, the duration is 5 to 30 seconds. The system supports four aspect ratios (16:9, 1:1, 3:4, and 9:16) and two resolutions (720p and 1080p).
|
|
4620
|
+
* - Asynchronous generation and task query: After a task is created, a task ID is returned. The caller queries the result by using the query API. The final video includes background music, no voiceover, and no additional subtitles or marketing text.
|
|
4621
|
+
* # Examples
|
|
4622
|
+
* [View the attachment "Digital_040_WiFi6_Gigabit_Router.mp4" in the DingTalk document.](https://alidocs.dingtalk.com/i/nodes/gwva2dxOW4vRkd9DUn1g1p6kJbkz3BRL?cid=6760411388:7016395022&corpId=dingd8e1123006514592&iframeQuery=anchorId%3DX02mvsyycduj3nepwoeush&utm_medium=im_card&utm_scene=person_space&utm_source=im)
|
|
4623
|
+
*
|
|
4624
|
+
* @param request - ProductVideoGenerationRequest
|
|
4625
|
+
* @returns ProductVideoGenerationResponse
|
|
4626
|
+
*/
|
|
4627
|
+
async productVideoGeneration(request: $_model.ProductVideoGenerationRequest): Promise<$_model.ProductVideoGenerationResponse> {
|
|
4628
|
+
let runtime = new $dara.RuntimeOptions({ });
|
|
4629
|
+
return await this.productVideoGenerationWithOptions(request, runtime);
|
|
4630
|
+
}
|
|
4631
|
+
|
|
4436
4632
|
/**
|
|
4437
4633
|
* Queries the result of an asynchronous task. The API name in the POP gateway is QueryAsyncTaskResult.
|
|
4438
4634
|
*
|
|
@@ -4920,105 +5116,105 @@ export default class Client extends OpenApi {
|
|
|
4920
5116
|
}
|
|
4921
5117
|
|
|
4922
5118
|
/**
|
|
4923
|
-
* Extracts structured information such as size charts and
|
|
5119
|
+
* Extracts structured information such as size charts and package weight and dimensions from images by using a multimodal large language model in asynchronous mode.
|
|
4924
5120
|
*
|
|
4925
5121
|
* @remarks
|
|
4926
5122
|
* ## Scenarios
|
|
4927
5123
|
* Size charts: Extracts size charts of apparel categories into text.
|
|
4928
|
-
*
|
|
5124
|
+
* Package weight and dimensions: Extracts package weight and dimension information from images.
|
|
4929
5125
|
* ## Features
|
|
4930
|
-
* The size chart extraction service is based on a multimodal large model. It automatically recognizes size charts or
|
|
4931
|
-
* Core capabilities: You input an image URL and optional column name configurations, and the system outputs the structured data of the size chart or
|
|
4932
|
-
* ## Comparison
|
|
5126
|
+
* The size chart extraction service is based on a multimodal large language model. It automatically recognizes size charts or package weight and dimension information in images and converts the information into structured text output. You provide an image URL, and the system processes the request as an asynchronous task and returns the extracted structured data. You can specify the column names to be recognized, such as Size, Bust, and Length, by using ColumnNameList to achieve precise and targeted extraction. You can also control the output language by using the LanguageModel parameter. Valid values: cn for Chinese and en for English. If you do not specify this parameter, the original language is retained. This service is applicable to scenarios such as text conversion of size charts for apparel categories and batch structuring of package weight and dimension information for commodities.
|
|
5127
|
+
* Core capabilities: You input an image URL and optional column name configurations, and the system outputs the structured data of the size chart or package weight and dimensions in the image. The API operation uses the asynchronous task mode (background: true). After you submit the task, a task ID is returned. You must poll the task to obtain the final result. This mode is suitable for processing complex images or handling large-scale calls.
|
|
5128
|
+
* ## Comparison of results
|
|
4933
5129
|
* | Input image | Output result |
|
|
4934
5130
|
* | --- | --- |
|
|
4935
5131
|
* |  | {
|
|
4936
5132
|
* "SizeChart": [
|
|
4937
5133
|
* {
|
|
4938
|
-
* "
|
|
5134
|
+
* "Size": {
|
|
4939
5135
|
* "value": "S"
|
|
4940
5136
|
* },
|
|
4941
|
-
* "
|
|
5137
|
+
* "Waist": {
|
|
4942
5138
|
* "unit": "CM",
|
|
4943
5139
|
* "value": 58
|
|
4944
5140
|
* },
|
|
4945
|
-
* "
|
|
5141
|
+
* "Skirt length": {
|
|
4946
5142
|
* "unit": "CM",
|
|
4947
5143
|
* "value": 81
|
|
4948
5144
|
* },
|
|
4949
|
-
* "
|
|
5145
|
+
* "Recommended weight": {
|
|
4950
5146
|
* "unit": "kg",
|
|
4951
5147
|
* "lower_value": 40,
|
|
4952
5148
|
* "upper_value": 47.5
|
|
4953
5149
|
* }
|
|
4954
5150
|
* },
|
|
4955
5151
|
* {
|
|
4956
|
-
* "
|
|
5152
|
+
* "Size": {
|
|
4957
5153
|
* "value": "M"
|
|
4958
5154
|
* },
|
|
4959
|
-
* "
|
|
5155
|
+
* "Waist": {
|
|
4960
5156
|
* "unit": "CM",
|
|
4961
5157
|
* "value": 59
|
|
4962
5158
|
* },
|
|
4963
|
-
* "
|
|
5159
|
+
* "Skirt length": {
|
|
4964
5160
|
* "unit": "CM",
|
|
4965
5161
|
* "value": 82
|
|
4966
5162
|
* },
|
|
4967
|
-
* "
|
|
5163
|
+
* "Recommended weight": {
|
|
4968
5164
|
* "unit": "kg",
|
|
4969
5165
|
* "lower_value": 45,
|
|
4970
5166
|
* "upper_value": 52.5
|
|
4971
5167
|
* }
|
|
4972
5168
|
* },
|
|
4973
5169
|
* {
|
|
4974
|
-
* "
|
|
5170
|
+
* "Size": {
|
|
4975
5171
|
* "value": "L"
|
|
4976
5172
|
* },
|
|
4977
|
-
* "
|
|
5173
|
+
* "Waist": {
|
|
4978
5174
|
* "unit": "CM",
|
|
4979
5175
|
* "value": 60
|
|
4980
5176
|
* },
|
|
4981
|
-
* "
|
|
5177
|
+
* "Skirt length": {
|
|
4982
5178
|
* "unit": "CM",
|
|
4983
5179
|
* "value": 83
|
|
4984
5180
|
* },
|
|
4985
|
-
* "
|
|
5181
|
+
* "Recommended weight": {
|
|
4986
5182
|
* "unit": "kg",
|
|
4987
5183
|
* "lower_value": 50,
|
|
4988
5184
|
* "upper_value": 57.5
|
|
4989
5185
|
* }
|
|
4990
5186
|
* },
|
|
4991
5187
|
* {
|
|
4992
|
-
* "
|
|
5188
|
+
* "Size": {
|
|
4993
5189
|
* "value": "XL"
|
|
4994
5190
|
* },
|
|
4995
|
-
* "
|
|
5191
|
+
* "Waist": {
|
|
4996
5192
|
* "unit": "CM",
|
|
4997
5193
|
* "value": 61
|
|
4998
5194
|
* },
|
|
4999
|
-
* "
|
|
5195
|
+
* "Skirt length": {
|
|
5000
5196
|
* "unit": "CM",
|
|
5001
5197
|
* "value": 84
|
|
5002
5198
|
* },
|
|
5003
|
-
* "
|
|
5199
|
+
* "Recommended weight": {
|
|
5004
5200
|
* "unit": "kg",
|
|
5005
5201
|
* "lower_value": 55,
|
|
5006
5202
|
* "upper_value": 62.5
|
|
5007
5203
|
* }
|
|
5008
5204
|
* },
|
|
5009
5205
|
* {
|
|
5010
|
-
* "
|
|
5206
|
+
* "Size": {
|
|
5011
5207
|
* "value": "2XL"
|
|
5012
5208
|
* },
|
|
5013
|
-
* "
|
|
5209
|
+
* "Waist": {
|
|
5014
5210
|
* "unit": "CM",
|
|
5015
5211
|
* "value": 62
|
|
5016
5212
|
* },
|
|
5017
|
-
* "
|
|
5213
|
+
* "Skirt length": {
|
|
5018
5214
|
* "unit": "CM",
|
|
5019
5215
|
* "value": 85
|
|
5020
5216
|
* },
|
|
5021
|
-
* "
|
|
5217
|
+
* "Recommended weight": {
|
|
5022
5218
|
* "unit": "kg",
|
|
5023
5219
|
* "lower_value": 60,
|
|
5024
5220
|
* "upper_value": 67.5
|
|
@@ -5029,13 +5225,13 @@ export default class Client extends OpenApi {
|
|
|
5029
5225
|
* "Size",
|
|
5030
5226
|
* "Skirt length",
|
|
5031
5227
|
* "Waist",
|
|
5032
|
-
* "
|
|
5228
|
+
* "Recommended weight"
|
|
5033
5229
|
* \\],
|
|
5034
5230
|
* "IntersectionAttributes": [
|
|
5035
5231
|
* "Size",
|
|
5036
5232
|
* "Skirt length",
|
|
5037
|
-
* "Waist (
|
|
5038
|
-
* "
|
|
5233
|
+
* "Waist (stretched)",
|
|
5234
|
+
* "Recommended weight"
|
|
5039
5235
|
* \\]
|
|
5040
5236
|
* } |
|
|
5041
5237
|
*
|
|
@@ -5086,105 +5282,105 @@ export default class Client extends OpenApi {
|
|
|
5086
5282
|
}
|
|
5087
5283
|
|
|
5088
5284
|
/**
|
|
5089
|
-
* Extracts structured information such as size charts and
|
|
5285
|
+
* Extracts structured information such as size charts and package weight and dimensions from images by using a multimodal large language model in asynchronous mode.
|
|
5090
5286
|
*
|
|
5091
5287
|
* @remarks
|
|
5092
5288
|
* ## Scenarios
|
|
5093
5289
|
* Size charts: Extracts size charts of apparel categories into text.
|
|
5094
|
-
*
|
|
5290
|
+
* Package weight and dimensions: Extracts package weight and dimension information from images.
|
|
5095
5291
|
* ## Features
|
|
5096
|
-
* The size chart extraction service is based on a multimodal large model. It automatically recognizes size charts or
|
|
5097
|
-
* Core capabilities: You input an image URL and optional column name configurations, and the system outputs the structured data of the size chart or
|
|
5098
|
-
* ## Comparison
|
|
5292
|
+
* The size chart extraction service is based on a multimodal large language model. It automatically recognizes size charts or package weight and dimension information in images and converts the information into structured text output. You provide an image URL, and the system processes the request as an asynchronous task and returns the extracted structured data. You can specify the column names to be recognized, such as Size, Bust, and Length, by using ColumnNameList to achieve precise and targeted extraction. You can also control the output language by using the LanguageModel parameter. Valid values: cn for Chinese and en for English. If you do not specify this parameter, the original language is retained. This service is applicable to scenarios such as text conversion of size charts for apparel categories and batch structuring of package weight and dimension information for commodities.
|
|
5293
|
+
* Core capabilities: You input an image URL and optional column name configurations, and the system outputs the structured data of the size chart or package weight and dimensions in the image. The API operation uses the asynchronous task mode (background: true). After you submit the task, a task ID is returned. You must poll the task to obtain the final result. This mode is suitable for processing complex images or handling large-scale calls.
|
|
5294
|
+
* ## Comparison of results
|
|
5099
5295
|
* | Input image | Output result |
|
|
5100
5296
|
* | --- | --- |
|
|
5101
5297
|
* |  | {
|
|
5102
5298
|
* "SizeChart": [
|
|
5103
5299
|
* {
|
|
5104
|
-
* "
|
|
5300
|
+
* "Size": {
|
|
5105
5301
|
* "value": "S"
|
|
5106
5302
|
* },
|
|
5107
|
-
* "
|
|
5303
|
+
* "Waist": {
|
|
5108
5304
|
* "unit": "CM",
|
|
5109
5305
|
* "value": 58
|
|
5110
5306
|
* },
|
|
5111
|
-
* "
|
|
5307
|
+
* "Skirt length": {
|
|
5112
5308
|
* "unit": "CM",
|
|
5113
5309
|
* "value": 81
|
|
5114
5310
|
* },
|
|
5115
|
-
* "
|
|
5311
|
+
* "Recommended weight": {
|
|
5116
5312
|
* "unit": "kg",
|
|
5117
5313
|
* "lower_value": 40,
|
|
5118
5314
|
* "upper_value": 47.5
|
|
5119
5315
|
* }
|
|
5120
5316
|
* },
|
|
5121
5317
|
* {
|
|
5122
|
-
* "
|
|
5318
|
+
* "Size": {
|
|
5123
5319
|
* "value": "M"
|
|
5124
5320
|
* },
|
|
5125
|
-
* "
|
|
5321
|
+
* "Waist": {
|
|
5126
5322
|
* "unit": "CM",
|
|
5127
5323
|
* "value": 59
|
|
5128
5324
|
* },
|
|
5129
|
-
* "
|
|
5325
|
+
* "Skirt length": {
|
|
5130
5326
|
* "unit": "CM",
|
|
5131
5327
|
* "value": 82
|
|
5132
5328
|
* },
|
|
5133
|
-
* "
|
|
5329
|
+
* "Recommended weight": {
|
|
5134
5330
|
* "unit": "kg",
|
|
5135
5331
|
* "lower_value": 45,
|
|
5136
5332
|
* "upper_value": 52.5
|
|
5137
5333
|
* }
|
|
5138
5334
|
* },
|
|
5139
5335
|
* {
|
|
5140
|
-
* "
|
|
5336
|
+
* "Size": {
|
|
5141
5337
|
* "value": "L"
|
|
5142
5338
|
* },
|
|
5143
|
-
* "
|
|
5339
|
+
* "Waist": {
|
|
5144
5340
|
* "unit": "CM",
|
|
5145
5341
|
* "value": 60
|
|
5146
5342
|
* },
|
|
5147
|
-
* "
|
|
5343
|
+
* "Skirt length": {
|
|
5148
5344
|
* "unit": "CM",
|
|
5149
5345
|
* "value": 83
|
|
5150
5346
|
* },
|
|
5151
|
-
* "
|
|
5347
|
+
* "Recommended weight": {
|
|
5152
5348
|
* "unit": "kg",
|
|
5153
5349
|
* "lower_value": 50,
|
|
5154
5350
|
* "upper_value": 57.5
|
|
5155
5351
|
* }
|
|
5156
5352
|
* },
|
|
5157
5353
|
* {
|
|
5158
|
-
* "
|
|
5354
|
+
* "Size": {
|
|
5159
5355
|
* "value": "XL"
|
|
5160
5356
|
* },
|
|
5161
|
-
* "
|
|
5357
|
+
* "Waist": {
|
|
5162
5358
|
* "unit": "CM",
|
|
5163
5359
|
* "value": 61
|
|
5164
5360
|
* },
|
|
5165
|
-
* "
|
|
5361
|
+
* "Skirt length": {
|
|
5166
5362
|
* "unit": "CM",
|
|
5167
5363
|
* "value": 84
|
|
5168
5364
|
* },
|
|
5169
|
-
* "
|
|
5365
|
+
* "Recommended weight": {
|
|
5170
5366
|
* "unit": "kg",
|
|
5171
5367
|
* "lower_value": 55,
|
|
5172
5368
|
* "upper_value": 62.5
|
|
5173
5369
|
* }
|
|
5174
5370
|
* },
|
|
5175
5371
|
* {
|
|
5176
|
-
* "
|
|
5372
|
+
* "Size": {
|
|
5177
5373
|
* "value": "2XL"
|
|
5178
5374
|
* },
|
|
5179
|
-
* "
|
|
5375
|
+
* "Waist": {
|
|
5180
5376
|
* "unit": "CM",
|
|
5181
5377
|
* "value": 62
|
|
5182
5378
|
* },
|
|
5183
|
-
* "
|
|
5379
|
+
* "Skirt length": {
|
|
5184
5380
|
* "unit": "CM",
|
|
5185
5381
|
* "value": 85
|
|
5186
5382
|
* },
|
|
5187
|
-
* "
|
|
5383
|
+
* "Recommended weight": {
|
|
5188
5384
|
* "unit": "kg",
|
|
5189
5385
|
* "lower_value": 60,
|
|
5190
5386
|
* "upper_value": 67.5
|
|
@@ -5195,13 +5391,13 @@ export default class Client extends OpenApi {
|
|
|
5195
5391
|
* "Size",
|
|
5196
5392
|
* "Skirt length",
|
|
5197
5393
|
* "Waist",
|
|
5198
|
-
* "
|
|
5394
|
+
* "Recommended weight"
|
|
5199
5395
|
* \\],
|
|
5200
5396
|
* "IntersectionAttributes": [
|
|
5201
5397
|
* "Size",
|
|
5202
5398
|
* "Skirt length",
|
|
5203
|
-
* "Waist (
|
|
5204
|
-
* "
|
|
5399
|
+
* "Waist (stretched)",
|
|
5400
|
+
* "Recommended weight"
|
|
5205
5401
|
* \\]
|
|
5206
5402
|
* } |
|
|
5207
5403
|
*
|
|
@@ -5214,18 +5410,18 @@ export default class Client extends OpenApi {
|
|
|
5214
5410
|
}
|
|
5215
5411
|
|
|
5216
5412
|
/**
|
|
5217
|
-
*
|
|
5413
|
+
* Audits store photos based on storefront scene recognition and multimodal large model element localization. The API outputs storefront scene classifications and confidence details, and localizes storefronts, signboards, entrances, and business signs. It is applicable to store data collection, storefront photo classification, and inspection reviews.
|
|
5218
5414
|
*
|
|
5219
5415
|
* @remarks
|
|
5220
|
-
* ##
|
|
5416
|
+
* ## Scenarios
|
|
5221
5417
|
* - Storefront photo classification: Distinguishes storefront-related photos from non-storefront photos.
|
|
5222
5418
|
* - Store data verification: Localizes signboards and entrances, and extracts clear and readable short text.
|
|
5223
5419
|
* - Multi-store photo review: Localizes visible storefronts and signs of adjacent stores separately.
|
|
5224
5420
|
* ## Features
|
|
5225
|
-
* - Scene classification and details: Returns
|
|
5421
|
+
* - Scene classification and details: Returns a scenes string array and classification details. Non-storefront photos are also valid classification results.
|
|
5226
5422
|
* - Storefront key element localization: Covers storefronts, signboards, store entrances, and business-related signs.
|
|
5227
|
-
* - Readable text extraction: Extracts only clear short text.
|
|
5228
|
-
* - Supports single HTTPS image input. Supplementary localization returns up to 12 targets, each containing a category,
|
|
5423
|
+
* - Readable text extraction: Extracts only clear short text. Does not infer business status based on whether the door is open or closed, and does not infer addresses or store ownership.
|
|
5424
|
+
* - Supports single HTTPS image input. Supplementary localization returns up to 12 targets, each containing a category, bounding box, and up to 24 characters of visible text, with coverage indicating whether the localization is complete.
|
|
5229
5425
|
*
|
|
5230
5426
|
* @param request - StorefrontSceneRecognitionRequest
|
|
5231
5427
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -5256,18 +5452,18 @@ export default class Client extends OpenApi {
|
|
|
5256
5452
|
}
|
|
5257
5453
|
|
|
5258
5454
|
/**
|
|
5259
|
-
*
|
|
5455
|
+
* Audits store photos based on storefront scene recognition and multimodal large model element localization. The API outputs storefront scene classifications and confidence details, and localizes storefronts, signboards, entrances, and business signs. It is applicable to store data collection, storefront photo classification, and inspection reviews.
|
|
5260
5456
|
*
|
|
5261
5457
|
* @remarks
|
|
5262
|
-
* ##
|
|
5458
|
+
* ## Scenarios
|
|
5263
5459
|
* - Storefront photo classification: Distinguishes storefront-related photos from non-storefront photos.
|
|
5264
5460
|
* - Store data verification: Localizes signboards and entrances, and extracts clear and readable short text.
|
|
5265
5461
|
* - Multi-store photo review: Localizes visible storefronts and signs of adjacent stores separately.
|
|
5266
5462
|
* ## Features
|
|
5267
|
-
* - Scene classification and details: Returns
|
|
5463
|
+
* - Scene classification and details: Returns a scenes string array and classification details. Non-storefront photos are also valid classification results.
|
|
5268
5464
|
* - Storefront key element localization: Covers storefronts, signboards, store entrances, and business-related signs.
|
|
5269
|
-
* - Readable text extraction: Extracts only clear short text.
|
|
5270
|
-
* - Supports single HTTPS image input. Supplementary localization returns up to 12 targets, each containing a category,
|
|
5465
|
+
* - Readable text extraction: Extracts only clear short text. Does not infer business status based on whether the door is open or closed, and does not infer addresses or store ownership.
|
|
5466
|
+
* - Supports single HTTPS image input. Supplementary localization returns up to 12 targets, each containing a category, bounding box, and up to 24 characters of visible text, with coverage indicating whether the localization is complete.
|
|
5271
5467
|
*
|
|
5272
5468
|
* @param request - StorefrontSceneRecognitionRequest
|
|
5273
5469
|
* @returns StorefrontSceneRecognitionResponse
|
|
@@ -5278,7 +5474,7 @@ export default class Client extends OpenApi {
|
|
|
5278
5474
|
}
|
|
5279
5475
|
|
|
5280
5476
|
/**
|
|
5281
|
-
* Generates product detail page
|
|
5477
|
+
* Generates product detail page materials automatically based on a multimodal large language model (MLLM) and structured image-text extraction to help e-commerce platforms and brands supplement product detail pages. After the caller pushes product information such as the product ID, title, brand, main image, and shop name, the service automatically locates identical products, performs consistency checks, extracts size information and product attributes, renders them into SVG size and attribute charts for direct use on the detail page, and returns structured detail copy classifications and processing remarks.
|
|
5282
5478
|
*
|
|
5283
5479
|
* @param request - SubmitProductMatchRequest
|
|
5284
5480
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -5333,7 +5529,7 @@ export default class Client extends OpenApi {
|
|
|
5333
5529
|
}
|
|
5334
5530
|
|
|
5335
5531
|
/**
|
|
5336
|
-
* Generates product detail page
|
|
5532
|
+
* Generates product detail page materials automatically based on a multimodal large language model (MLLM) and structured image-text extraction to help e-commerce platforms and brands supplement product detail pages. After the caller pushes product information such as the product ID, title, brand, main image, and shop name, the service automatically locates identical products, performs consistency checks, extracts size information and product attributes, renders them into SVG size and attribute charts for direct use on the detail page, and returns structured detail copy classifications and processing remarks.
|
|
5337
5533
|
*
|
|
5338
5534
|
* @param request - SubmitProductMatchRequest
|
|
5339
5535
|
* @returns SubmitProductMatchResponse
|
|
@@ -5556,7 +5752,7 @@ export default class Client extends OpenApi {
|
|
|
5556
5752
|
}
|
|
5557
5753
|
|
|
5558
5754
|
/**
|
|
5559
|
-
* Translates text by using the Maas MT e-commerce translation model
|
|
5755
|
+
* Translates text asynchronously by using the Maas MT model, an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs. The model is continuously optimized for e-commerce-specific terms such as brands, models, materials, and attributes. It supports 156 languages with over 400 language pairs and supports automatic language detection for source languages.
|
|
5560
5756
|
*
|
|
5561
5757
|
* @remarks
|
|
5562
5758
|
* ## Scenarios
|
|
@@ -5570,22 +5766,22 @@ export default class Client extends OpenApi {
|
|
|
5570
5766
|
*
|
|
5571
5767
|
* The Maas MT large language model can also be used for translation in general scenarios, such as office work, meetings, and daily conversations.
|
|
5572
5768
|
* ## Features
|
|
5573
|
-
* * **Ultra-low hallucination rate and high-speed inference
|
|
5769
|
+
* * **Ultra-low hallucination rate and high-speed inference** The Maas MT large language model is aligned with preferences for translation scenarios. Compared with general-purpose large language models, it features faster translation inference and an extremely low hallucination rate, making it especially suitable for large-scale invocation scenarios.
|
|
5574
5770
|
*
|
|
5575
|
-
* * **Supported text formats
|
|
5771
|
+
* * **Supported text formats** The model supports text and HTML formats.
|
|
5576
5772
|
*
|
|
5577
|
-
* * **Translation intervention
|
|
5773
|
+
* * **Translation intervention** You can customize translation results, including keeping words untranslated (ABC-ABC), specifying translations (ABC-DEF), and omitting translations (ABC-null value). This is commonly used for brand word protection. You only need to pass the corresponding intervention glossary ID when calling the API. This meets your translation needs in different scenarios. You can upload up to 100,000 intervention words. If you need more, contact the platform.
|
|
5578
5774
|
*
|
|
5579
|
-
* * **Translation
|
|
5775
|
+
* * **Translation quality comparison**
|
|
5580
5776
|
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation advantages** |
|
|
5581
5777
|
* | --- | --- | --- | --- | --- |
|
|
5582
5778
|
* | 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 |
|
|
5583
5779
|
* | 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 |
|
|
5584
|
-
* | 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
|
|
5585
|
-
* ## Preparations and
|
|
5586
|
-
* Text translation supports both synchronization and asynchronous
|
|
5780
|
+
* | Men Key Bag Genuine Cow Leather Buckets Key Cases Pouch Zipper Keychain Auto Car Key Case Women Home Key Holder Wallet | Sac à clés pour hommes en cuir de vache véritable, étuis à clés, pochette à fermeture éclair, porte-clés, étui à clé de voiture, porte-clés pour femmes, organisateur de portefeuille | Porte-clés sac en cuir de vache véritable, étuis à clés en forme de seau, pochette à fermeture éclair, porte-clés auto pour voiture, étui à clés pour femmes, organisateur de clés de maison, portefeuille. | Hommes porte-clés en cuir de vache véritable sac/pochette fermeture éclair porte-clés Auto voiture porte-clés femmes maison porte-clés organisateur portefeuille | Clearer and more explicit product subject. It translates to "key bag" rather than "keychain", avoiding ambiguity in other translations |
|
|
5781
|
+
* ## Preparations and invoke flow
|
|
5782
|
+
* Text translation supports both synchronization and asynchronous invoke methods. This topic describes the asynchronous invoke API. If you need to use synchronous call, see [Text translation - Synchronous API](https://api.aliyun.com/document/Aidge/2026-04-28/TextTranslate).
|
|
5587
5783
|
* 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.
|
|
5588
|
-
* For the asynchronous
|
|
5784
|
+
* For the asynchronous invoke integration flow, subscribe rules, message formats and encryption protocols, and detailed integration solutions, see [Asynchronous API invoke instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
5589
5785
|
*
|
|
5590
5786
|
* @param tmpReq - TextTranslateAsyncRequest
|
|
5591
5787
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -5650,7 +5846,7 @@ export default class Client extends OpenApi {
|
|
|
5650
5846
|
}
|
|
5651
5847
|
|
|
5652
5848
|
/**
|
|
5653
|
-
* Translates text by using the Maas MT e-commerce translation model
|
|
5849
|
+
* Translates text asynchronously by using the Maas MT model, an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs. The model is continuously optimized for e-commerce-specific terms such as brands, models, materials, and attributes. It supports 156 languages with over 400 language pairs and supports automatic language detection for source languages.
|
|
5654
5850
|
*
|
|
5655
5851
|
* @remarks
|
|
5656
5852
|
* ## Scenarios
|
|
@@ -5664,22 +5860,22 @@ export default class Client extends OpenApi {
|
|
|
5664
5860
|
*
|
|
5665
5861
|
* The Maas MT large language model can also be used for translation in general scenarios, such as office work, meetings, and daily conversations.
|
|
5666
5862
|
* ## Features
|
|
5667
|
-
* * **Ultra-low hallucination rate and high-speed inference
|
|
5863
|
+
* * **Ultra-low hallucination rate and high-speed inference** The Maas MT large language model is aligned with preferences for translation scenarios. Compared with general-purpose large language models, it features faster translation inference and an extremely low hallucination rate, making it especially suitable for large-scale invocation scenarios.
|
|
5668
5864
|
*
|
|
5669
|
-
* * **Supported text formats
|
|
5865
|
+
* * **Supported text formats** The model supports text and HTML formats.
|
|
5670
5866
|
*
|
|
5671
|
-
* * **Translation intervention
|
|
5867
|
+
* * **Translation intervention** You can customize translation results, including keeping words untranslated (ABC-ABC), specifying translations (ABC-DEF), and omitting translations (ABC-null value). This is commonly used for brand word protection. You only need to pass the corresponding intervention glossary ID when calling the API. This meets your translation needs in different scenarios. You can upload up to 100,000 intervention words. If you need more, contact the platform.
|
|
5672
5868
|
*
|
|
5673
|
-
* * **Translation
|
|
5869
|
+
* * **Translation quality comparison**
|
|
5674
5870
|
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation advantages** |
|
|
5675
5871
|
* | --- | --- | --- | --- | --- |
|
|
5676
5872
|
* | 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 |
|
|
5677
5873
|
* | 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 |
|
|
5678
|
-
* | 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
|
|
5679
|
-
* ## Preparations and
|
|
5680
|
-
* Text translation supports both synchronization and asynchronous
|
|
5874
|
+
* | Men Key Bag Genuine Cow Leather Buckets Key Cases Pouch Zipper Keychain Auto Car Key Case Women Home Key Holder Wallet | Sac à clés pour hommes en cuir de vache véritable, étuis à clés, pochette à fermeture éclair, porte-clés, étui à clé de voiture, porte-clés pour femmes, organisateur de portefeuille | Porte-clés sac en cuir de vache véritable, étuis à clés en forme de seau, pochette à fermeture éclair, porte-clés auto pour voiture, étui à clés pour femmes, organisateur de clés de maison, portefeuille. | Hommes porte-clés en cuir de vache véritable sac/pochette fermeture éclair porte-clés Auto voiture porte-clés femmes maison porte-clés organisateur portefeuille | Clearer and more explicit product subject. It translates to "key bag" rather than "keychain", avoiding ambiguity in other translations |
|
|
5875
|
+
* ## Preparations and invoke flow
|
|
5876
|
+
* Text translation supports both synchronization and asynchronous invoke methods. This topic describes the asynchronous invoke API. If you need to use synchronous call, see [Text translation - Synchronous API](https://api.aliyun.com/document/Aidge/2026-04-28/TextTranslate).
|
|
5681
5877
|
* 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.
|
|
5682
|
-
* For the asynchronous
|
|
5878
|
+
* For the asynchronous invoke integration flow, subscribe rules, message formats and encryption protocols, and detailed integration solutions, see [Asynchronous API invoke instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
5683
5879
|
*
|
|
5684
5880
|
* @param request - TextTranslateAsyncRequest
|
|
5685
5881
|
* @returns TextTranslateAsyncResponse
|
|
@@ -5742,25 +5938,75 @@ export default class Client extends OpenApi {
|
|
|
5742
5938
|
}
|
|
5743
5939
|
|
|
5744
5940
|
/**
|
|
5745
|
-
*
|
|
5941
|
+
* Detects vacancies (asynchronous commit).
|
|
5942
|
+
*
|
|
5943
|
+
* @param request - VacancyDetectionRequest
|
|
5944
|
+
* @param runtime - runtime options for this request RuntimeOptions
|
|
5945
|
+
* @returns VacancyDetectionResponse
|
|
5946
|
+
*/
|
|
5947
|
+
async vacancyDetectionWithOptions(request: $_model.VacancyDetectionRequest, runtime: $dara.RuntimeOptions): Promise<$_model.VacancyDetectionResponse> {
|
|
5948
|
+
request.validate();
|
|
5949
|
+
let query = { };
|
|
5950
|
+
if (!$dara.isNull(request.imageUrl)) {
|
|
5951
|
+
query["ImageUrl"] = request.imageUrl;
|
|
5952
|
+
}
|
|
5953
|
+
|
|
5954
|
+
if (!$dara.isNull(request.systemPrompt)) {
|
|
5955
|
+
query["SystemPrompt"] = request.systemPrompt;
|
|
5956
|
+
}
|
|
5957
|
+
|
|
5958
|
+
if (!$dara.isNull(request.userPrompt)) {
|
|
5959
|
+
query["UserPrompt"] = request.userPrompt;
|
|
5960
|
+
}
|
|
5961
|
+
|
|
5962
|
+
let req = new $OpenApiUtil.OpenApiRequest({
|
|
5963
|
+
query: OpenApiUtil.query(query),
|
|
5964
|
+
});
|
|
5965
|
+
let params = new $OpenApiUtil.Params({
|
|
5966
|
+
action: "VacancyDetection",
|
|
5967
|
+
version: "2026-04-28",
|
|
5968
|
+
protocol: "HTTPS",
|
|
5969
|
+
pathname: "/",
|
|
5970
|
+
method: "POST",
|
|
5971
|
+
authType: "AK",
|
|
5972
|
+
style: "RPC",
|
|
5973
|
+
reqBodyType: "formData",
|
|
5974
|
+
bodyType: "json",
|
|
5975
|
+
});
|
|
5976
|
+
return $dara.cast<$_model.VacancyDetectionResponse>(await this.callApi(params, req, runtime), new $_model.VacancyDetectionResponse({}));
|
|
5977
|
+
}
|
|
5978
|
+
|
|
5979
|
+
/**
|
|
5980
|
+
* Detects vacancies (asynchronous commit).
|
|
5981
|
+
*
|
|
5982
|
+
* @param request - VacancyDetectionRequest
|
|
5983
|
+
* @returns VacancyDetectionResponse
|
|
5984
|
+
*/
|
|
5985
|
+
async vacancyDetection(request: $_model.VacancyDetectionRequest): Promise<$_model.VacancyDetectionResponse> {
|
|
5986
|
+
let runtime = new $dara.RuntimeOptions({ });
|
|
5987
|
+
return await this.vacancyDetectionWithOptions(request, runtime);
|
|
5988
|
+
}
|
|
5989
|
+
|
|
5990
|
+
/**
|
|
5991
|
+
* Generates 5- to 30-second product showcase short videos through the e-commerce AI video generation agent for e-commerce merchants and platforms based on product main images, titles, and selling points, helping customers efficiently produce and distribute e-commerce content. The product supports multiple resolutions such as 720P and 1080P, and allows you to invoke single products quickly and generate multiple products in batches, meeting the needs of daily operations and large-scale product content production. Current capabilities overwrite all clothing categories (tops, pants, skirts, suits, underwear, swimwear, etc.), and the service is gradually expanding to core e-commerce categories such as skincare, cosmetics, food and beverages, and home appliances.
|
|
5746
5992
|
*
|
|
5747
5993
|
* @remarks
|
|
5748
5994
|
* # Scenarios
|
|
5749
|
-
* - Batch generation of product short videos for sellers and platforms: Supports multiple video aspect ratios and sizes (3:4, 9:16), adapting to product detail page video slots, product homepage displays, information feed placements, short video promotions, and event venue materials.
|
|
5750
|
-
* - Quick generation of the first batch of video materials for new product launches: When merchants have a large number of new products to launch, they only need to upload basic information such as product images and titles to quickly generate product showcase videos, model wearing videos, and
|
|
5751
|
-
* - High-fidelity clothing display: Generates model display videos that are closer to real commercial shooting effects
|
|
5752
|
-
* - Generation of high-quality commercial shooting models: Built-in target audience model library, covering plus-size women, plus-size men, swimwear,
|
|
5995
|
+
* - Batch generation of product short videos for sellers and platforms: Supports multiple video aspect ratios and sizes (3:4, 9:16), adapting to scenarios such as product detail page video slots, product homepage displays, information feed placements, short video promotions, and event venue materials.
|
|
5996
|
+
* - Quick generation of the first batch of video materials for new product launches: When merchants have a large number of new products to launch at once, they only need to upload basic information such as product images and titles to quickly generate product showcase videos, model wearing videos, and voiceover explanation videos, helping merchants quickly complete material deployment during the launch phase.
|
|
5997
|
+
* - High-fidelity clothing display: Generates model display videos based on product main images that are closer to real commercial shooting effects, focusing on optimizing capabilities such as pattern restoration, fabric texture retention, accurate color presentation, and stable and consistent details. It supports common e-commerce display methods such as wearing, turning, walking, close-up shots, and multi-angle switching.
|
|
5998
|
+
* - Generation of high-quality commercial shooting models: Built-in target audience model library, covering plus-size women, plus-size men, swimwear, girly style, light mature commuting, youth casual, business menswear, sports and fitness, and other body types, skin colors, and races. It supports various commercial shooting expressions such as standing display, side display, walking display, and partial close-ups.
|
|
5753
5999
|
* - High-frequency e-commerce scenarios such as standard product explanations: Applicable to standardized product categories such as skincare, cosmetics, personal care small appliances, food and beverages, home cleaning daily necessities, and 3C digital products. It can quickly generate product explanation videos based on product main images, titles, selling point information, and explanation scripts.
|
|
5754
|
-
* - Multi-product and multi-selling point testing to improve delivery efficiency: For information feed advertising, short video
|
|
6000
|
+
* - Multi-product and multi-selling point testing to improve delivery efficiency: For information feed advertising, short video placement, and content promotion scenarios, it can quickly generate multiple versions of video materials, making it easy for enterprises to verify the conversion effects of different selling points and presentation forms at a low cost, and improve delivery ROI.
|
|
5755
6001
|
* # Features
|
|
5756
|
-
* - Fully automatic end-to-end batch generation with zero prompt threshold: Callers only need to pass in the product image URL and title, and the system automatically completes the entire process from product understanding
|
|
5757
|
-
* - Highly stable generation with a low waste rate: Adopts a deterministic generation process and multi-layer quality control mechanism to output usable materials with fewer retries, reducing invalid generation and resource waste, and making the overall production cost more controllable.
|
|
5758
|
-
* - E-commerce exclusive product fidelity capability: Built-in multi-round quality inspection
|
|
5759
|
-
* - Reference image first + 6-axis consistency check: Adopts the Reference-Image-First generation paradigm, using the original product image as the only visual source of truth, and automatically performs 6-dimensional VL diagnosis (color drift, pattern missing, contour deviation, structure addition
|
|
5760
|
-
* - Flexible storyboard arrangement and duration control: Supports adjustable video duration of 5 to 30 seconds
|
|
5761
|
-
* - Cinematic camera movement capabilities: Built-in advanced camera movement modes such as bullet time, Grammy slow motion, 360° surround rotation, and
|
|
6002
|
+
* - Fully automatic end-to-end batch generation with zero prompt threshold: Callers only need to pass in the product image URL and title, and the system automatically completes the entire process from product understanding and storyboard planning to video generation, without the need to manually write prompts, select templates, or repeatedly adjust parameters. Built-in multiple agents such as product understanding, image quality inspection, script planning, and director camera movement greatly lower the threshold for use.
|
|
6003
|
+
* - Highly stable generation with a low waste rate: Adopts a deterministic generation process and a multi-layer quality control mechanism to output usable materials with fewer retries, reducing invalid generation and resource waste, and making the overall production cost more controllable.
|
|
6004
|
+
* - E-commerce exclusive product fidelity capability: Built-in multi-round quality inspection agents lock the product state throughout the video generation process (such as zippers will not be pulled open, sleeves will not be rolled down, and prints will not disappear), ensuring product consistency through multi-layer defense of script rewriting, explicit constraint injection, and failure-aware retry.
|
|
6005
|
+
* - Reference image first + 6-axis consistency check: Adopts the Reference-Image-First generation paradigm, using the original product image as the only visual source of truth, and automatically performs 6-dimensional VL diagnosis (color drift, pattern missing, contour deviation, structure addition or reduction, model matching, and dirt detection) to fundamentally eliminate the problem of generated images not looking like the product.
|
|
6006
|
+
* - Flexible storyboard arrangement and duration control: Supports adjustable video duration of 5 to 30 seconds. Agents independently plan independent storyboards to display the product effects in different scenarios. It also supports fixed scene mode to deeply display product tonality under a unified visual style.
|
|
6007
|
+
* - Cinematic camera movement capabilities: Built-in advanced camera movement modes such as bullet time, Grammy slow motion, 360° surround rotation, and full-body model rotation display, achieving deterministic output through precise segmented control.
|
|
5762
6008
|
* - Model library and customization services: Built-in multi-type model resource library, supporting merchants to specify fixed models, customize exclusive model images, and bind brand visual personas for a long time to ensure brand visual consistency.
|
|
5763
|
-
* -
|
|
6009
|
+
* - Adaptation to high-frequency e-commerce content scenarios: Supports multiple resolutions such as 720P and 1080P and multiple aspect ratios such as 3:4 and 9:16, adapting to product detail page video slots, product homepage video displays, waterfall or information feed placements, event venue materials, and new product and promotional video generation.
|
|
5764
6010
|
*
|
|
5765
6011
|
* @param tmpReq - VideoGenerationRequest
|
|
5766
6012
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -5813,25 +6059,25 @@ export default class Client extends OpenApi {
|
|
|
5813
6059
|
}
|
|
5814
6060
|
|
|
5815
6061
|
/**
|
|
5816
|
-
*
|
|
6062
|
+
* Generates 5- to 30-second product showcase short videos through the e-commerce AI video generation agent for e-commerce merchants and platforms based on product main images, titles, and selling points, helping customers efficiently produce and distribute e-commerce content. The product supports multiple resolutions such as 720P and 1080P, and allows you to invoke single products quickly and generate multiple products in batches, meeting the needs of daily operations and large-scale product content production. Current capabilities overwrite all clothing categories (tops, pants, skirts, suits, underwear, swimwear, etc.), and the service is gradually expanding to core e-commerce categories such as skincare, cosmetics, food and beverages, and home appliances.
|
|
5817
6063
|
*
|
|
5818
6064
|
* @remarks
|
|
5819
6065
|
* # Scenarios
|
|
5820
|
-
* - Batch generation of product short videos for sellers and platforms: Supports multiple video aspect ratios and sizes (3:4, 9:16), adapting to product detail page video slots, product homepage displays, information feed placements, short video promotions, and event venue materials.
|
|
5821
|
-
* - Quick generation of the first batch of video materials for new product launches: When merchants have a large number of new products to launch, they only need to upload basic information such as product images and titles to quickly generate product showcase videos, model wearing videos, and
|
|
5822
|
-
* - High-fidelity clothing display: Generates model display videos that are closer to real commercial shooting effects
|
|
5823
|
-
* - Generation of high-quality commercial shooting models: Built-in target audience model library, covering plus-size women, plus-size men, swimwear,
|
|
6066
|
+
* - Batch generation of product short videos for sellers and platforms: Supports multiple video aspect ratios and sizes (3:4, 9:16), adapting to scenarios such as product detail page video slots, product homepage displays, information feed placements, short video promotions, and event venue materials.
|
|
6067
|
+
* - Quick generation of the first batch of video materials for new product launches: When merchants have a large number of new products to launch at once, they only need to upload basic information such as product images and titles to quickly generate product showcase videos, model wearing videos, and voiceover explanation videos, helping merchants quickly complete material deployment during the launch phase.
|
|
6068
|
+
* - High-fidelity clothing display: Generates model display videos based on product main images that are closer to real commercial shooting effects, focusing on optimizing capabilities such as pattern restoration, fabric texture retention, accurate color presentation, and stable and consistent details. It supports common e-commerce display methods such as wearing, turning, walking, close-up shots, and multi-angle switching.
|
|
6069
|
+
* - Generation of high-quality commercial shooting models: Built-in target audience model library, covering plus-size women, plus-size men, swimwear, girly style, light mature commuting, youth casual, business menswear, sports and fitness, and other body types, skin colors, and races. It supports various commercial shooting expressions such as standing display, side display, walking display, and partial close-ups.
|
|
5824
6070
|
* - High-frequency e-commerce scenarios such as standard product explanations: Applicable to standardized product categories such as skincare, cosmetics, personal care small appliances, food and beverages, home cleaning daily necessities, and 3C digital products. It can quickly generate product explanation videos based on product main images, titles, selling point information, and explanation scripts.
|
|
5825
|
-
* - Multi-product and multi-selling point testing to improve delivery efficiency: For information feed advertising, short video
|
|
6071
|
+
* - Multi-product and multi-selling point testing to improve delivery efficiency: For information feed advertising, short video placement, and content promotion scenarios, it can quickly generate multiple versions of video materials, making it easy for enterprises to verify the conversion effects of different selling points and presentation forms at a low cost, and improve delivery ROI.
|
|
5826
6072
|
* # Features
|
|
5827
|
-
* - Fully automatic end-to-end batch generation with zero prompt threshold: Callers only need to pass in the product image URL and title, and the system automatically completes the entire process from product understanding
|
|
5828
|
-
* - Highly stable generation with a low waste rate: Adopts a deterministic generation process and multi-layer quality control mechanism to output usable materials with fewer retries, reducing invalid generation and resource waste, and making the overall production cost more controllable.
|
|
5829
|
-
* - E-commerce exclusive product fidelity capability: Built-in multi-round quality inspection
|
|
5830
|
-
* - Reference image first + 6-axis consistency check: Adopts the Reference-Image-First generation paradigm, using the original product image as the only visual source of truth, and automatically performs 6-dimensional VL diagnosis (color drift, pattern missing, contour deviation, structure addition
|
|
5831
|
-
* - Flexible storyboard arrangement and duration control: Supports adjustable video duration of 5 to 30 seconds
|
|
5832
|
-
* - Cinematic camera movement capabilities: Built-in advanced camera movement modes such as bullet time, Grammy slow motion, 360° surround rotation, and
|
|
6073
|
+
* - Fully automatic end-to-end batch generation with zero prompt threshold: Callers only need to pass in the product image URL and title, and the system automatically completes the entire process from product understanding and storyboard planning to video generation, without the need to manually write prompts, select templates, or repeatedly adjust parameters. Built-in multiple agents such as product understanding, image quality inspection, script planning, and director camera movement greatly lower the threshold for use.
|
|
6074
|
+
* - Highly stable generation with a low waste rate: Adopts a deterministic generation process and a multi-layer quality control mechanism to output usable materials with fewer retries, reducing invalid generation and resource waste, and making the overall production cost more controllable.
|
|
6075
|
+
* - E-commerce exclusive product fidelity capability: Built-in multi-round quality inspection agents lock the product state throughout the video generation process (such as zippers will not be pulled open, sleeves will not be rolled down, and prints will not disappear), ensuring product consistency through multi-layer defense of script rewriting, explicit constraint injection, and failure-aware retry.
|
|
6076
|
+
* - Reference image first + 6-axis consistency check: Adopts the Reference-Image-First generation paradigm, using the original product image as the only visual source of truth, and automatically performs 6-dimensional VL diagnosis (color drift, pattern missing, contour deviation, structure addition or reduction, model matching, and dirt detection) to fundamentally eliminate the problem of generated images not looking like the product.
|
|
6077
|
+
* - Flexible storyboard arrangement and duration control: Supports adjustable video duration of 5 to 30 seconds. Agents independently plan independent storyboards to display the product effects in different scenarios. It also supports fixed scene mode to deeply display product tonality under a unified visual style.
|
|
6078
|
+
* - Cinematic camera movement capabilities: Built-in advanced camera movement modes such as bullet time, Grammy slow motion, 360° surround rotation, and full-body model rotation display, achieving deterministic output through precise segmented control.
|
|
5833
6079
|
* - Model library and customization services: Built-in multi-type model resource library, supporting merchants to specify fixed models, customize exclusive model images, and bind brand visual personas for a long time to ensure brand visual consistency.
|
|
5834
|
-
* -
|
|
6080
|
+
* - Adaptation to high-frequency e-commerce content scenarios: Supports multiple resolutions such as 720P and 1080P and multiple aspect ratios such as 3:4 and 9:16, adapting to product detail page video slots, product homepage video displays, waterfall or information feed placements, event venue materials, and new product and promotional video generation.
|
|
5835
6081
|
*
|
|
5836
6082
|
* @param request - VideoGenerationRequest
|
|
5837
6083
|
* @returns VideoGenerationResponse
|
|
@@ -5847,23 +6093,23 @@ export default class Client extends OpenApi {
|
|
|
5847
6093
|
* @remarks
|
|
5848
6094
|
* ## Product introduction
|
|
5849
6095
|
* 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.
|
|
5850
|
-
* 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.
|
|
6096
|
+
* 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.
|
|
5851
6097
|
* ## Scenarios
|
|
5852
|
-
* * **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
|
|
6098
|
+
* * **Cross-border e-commerce video localization**: Translates the speech subtitles and selling point text in product introduction videos into the language of the target market to promote products on overseas platforms.
|
|
5853
6099
|
*
|
|
5854
6100
|
* * **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.
|
|
5855
6101
|
*
|
|
5856
|
-
* * **Global brand advertising**: Automatically generates video versions in the languages
|
|
6102
|
+
* * **Global brand advertising**: Automatically generates video versions in the corresponding languages based on the target regions to reduce manual production costs.
|
|
5857
6103
|
*
|
|
5858
6104
|
* * **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.
|
|
5859
6105
|
* ## Features
|
|
5860
|
-
* |
|
|
6106
|
+
* | Capability | Identifier | Description |
|
|
5861
6107
|
* | --- | --- | --- |
|
|
5862
|
-
* | Speech subtitle translation | speech | Translates the video speech into target language dubbing. You can choose to
|
|
5863
|
-
* | 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. |
|
|
5864
|
-
* Speech subtitle translation (speech) generates target language dubbing based on the spoken content in the video, processes the subtitles
|
|
5865
|
-
* 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.
|
|
5866
|
-
* When both speech and visual are selected, the speech subtitle translation is completed and the video is synthesized first
|
|
6108
|
+
* | Speech subtitle translation | `speech` | Translates the video speech into target language dubbing. You can choose to erase the original subtitles only or replace them with translated subtitles. By default, the original subtitles are not processed and no new subtitles are added. |
|
|
6109
|
+
* | 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. |
|
|
6110
|
+
* Speech subtitle translation (speech) generates target language dubbing based on the spoken content in the video, processes the subtitles based on the original subtitle processing option, and synthesizes the final video. Original subtitles refer to the existing subtitles in the video frames that correspond to the spoken content. Replacing with translated subtitles erases the original subtitles first and then adds subtitles synchronized with the translated speech.
|
|
6111
|
+
* On-screen text translation (visual) targets the recognizable original video language text in the video frames, such as titles, product selling points, and descriptive text. It can be used independently without selecting speech subtitle translation first, and does not require the text to appear in the speech. Original subtitles within the processing scope may also be processed.
|
|
6112
|
+
* When both speech and visual are selected, the speech subtitle translation is completed and the video is synthesized first, and then the on-screen text processing is performed on this video. The translated dubbing is retained, and a final video is output. The order of capabilities in the array does not affect the execution order. Therefore, not processing original subtitles only means that no subtitles are erased or added during the speech subtitle phase, and subsequent on-screen text processing may still change the original subtitles. Subtitles that have been replaced with translated subtitles are retained during subsequent on-screen text processing.
|
|
5867
6113
|
*
|
|
5868
6114
|
* @param tmpReq - VideoTranslationRequest
|
|
5869
6115
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -5935,23 +6181,23 @@ export default class Client extends OpenApi {
|
|
|
5935
6181
|
* @remarks
|
|
5936
6182
|
* ## Product introduction
|
|
5937
6183
|
* 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.
|
|
5938
|
-
* 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.
|
|
6184
|
+
* 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.
|
|
5939
6185
|
* ## Scenarios
|
|
5940
|
-
* * **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
|
|
6186
|
+
* * **Cross-border e-commerce video localization**: Translates the speech subtitles and selling point text in product introduction videos into the language of the target market to promote products on overseas platforms.
|
|
5941
6187
|
*
|
|
5942
6188
|
* * **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.
|
|
5943
6189
|
*
|
|
5944
|
-
* * **Global brand advertising**: Automatically generates video versions in the languages
|
|
6190
|
+
* * **Global brand advertising**: Automatically generates video versions in the corresponding languages based on the target regions to reduce manual production costs.
|
|
5945
6191
|
*
|
|
5946
6192
|
* * **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.
|
|
5947
6193
|
* ## Features
|
|
5948
|
-
* |
|
|
6194
|
+
* | Capability | Identifier | Description |
|
|
5949
6195
|
* | --- | --- | --- |
|
|
5950
|
-
* | Speech subtitle translation | speech | Translates the video speech into target language dubbing. You can choose to
|
|
5951
|
-
* | 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. |
|
|
5952
|
-
* Speech subtitle translation (speech) generates target language dubbing based on the spoken content in the video, processes the subtitles
|
|
5953
|
-
* 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.
|
|
5954
|
-
* When both speech and visual are selected, the speech subtitle translation is completed and the video is synthesized first
|
|
6196
|
+
* | Speech subtitle translation | `speech` | Translates the video speech into target language dubbing. You can choose to erase the original subtitles only or replace them with translated subtitles. By default, the original subtitles are not processed and no new subtitles are added. |
|
|
6197
|
+
* | 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. |
|
|
6198
|
+
* Speech subtitle translation (speech) generates target language dubbing based on the spoken content in the video, processes the subtitles based on the original subtitle processing option, and synthesizes the final video. Original subtitles refer to the existing subtitles in the video frames that correspond to the spoken content. Replacing with translated subtitles erases the original subtitles first and then adds subtitles synchronized with the translated speech.
|
|
6199
|
+
* On-screen text translation (visual) targets the recognizable original video language text in the video frames, such as titles, product selling points, and descriptive text. It can be used independently without selecting speech subtitle translation first, and does not require the text to appear in the speech. Original subtitles within the processing scope may also be processed.
|
|
6200
|
+
* When both speech and visual are selected, the speech subtitle translation is completed and the video is synthesized first, and then the on-screen text processing is performed on this video. The translated dubbing is retained, and a final video is output. The order of capabilities in the array does not affect the execution order. Therefore, not processing original subtitles only means that no subtitles are erased or added during the speech subtitle phase, and subsequent on-screen text processing may still change the original subtitles. Subtitles that have been replaced with translated subtitles are retained during subsequent on-screen text processing.
|
|
5955
6201
|
*
|
|
5956
6202
|
* @param request - VideoTranslationRequest
|
|
5957
6203
|
* @returns VideoTranslationResponse
|
|
@@ -5962,35 +6208,38 @@ export default class Client extends OpenApi {
|
|
|
5962
6208
|
}
|
|
5963
6209
|
|
|
5964
6210
|
/**
|
|
5965
|
-
* Generates virtual try-on images by using AI algorithms
|
|
6211
|
+
* Generates virtual try-on images by using AI algorithms to replace a model\\"s clothing with a specified garment. The service preserves the model\\"s pose, facial features, and background details while ensuring a realistic and well-fitted appearance. Users only need to provide the URLs of the original model and garment images to obtain the processed images.
|
|
5966
6212
|
*
|
|
5967
6213
|
* @remarks
|
|
6214
|
+
* *Note:**
|
|
6215
|
+
* VirtualTryOn is an early version that supports only single-item try-on and is scheduled to be deprecated soon.
|
|
6216
|
+
* New features such as multi-item outfit matching, model replacement, and pose replacement are now available in [Virtual try-on (AiTryOn)](https://api.aliyun.com/document/Aidge/2026-04-28/AiTryOn). Refer to the new API for integration.
|
|
5968
6217
|
* ## Scenarios
|
|
5969
|
-
* - **Virtual try-on for
|
|
5970
|
-
* Supports various
|
|
5971
|
-
* - **Virtual try-on for
|
|
5972
|
-
* Supports virtual try-on for
|
|
6218
|
+
* - **Virtual try-on for apparel:**
|
|
6219
|
+
* Supports various apparel categories such as tops, bottoms, jumpsuits, and dresses. After users upload a model image and a product image, the service generates natural and realistic try-on effects to intuitively display how the garment looks on the model.
|
|
6220
|
+
* - **Virtual try-on for footwear and headwear:**
|
|
6221
|
+
* Supports virtual try-on for products such as shoes and hats. The service intelligently matches the product position and proportion based on the model\\"s pose and body parts to present a coordinated and realistic wearing effect.
|
|
5973
6222
|
* - **E-commerce product display and marketing:**
|
|
5974
|
-
*
|
|
6223
|
+
* Helps merchants quickly generate model try-on images for different products. This reduces the costs of traditional photography, outfit changes, and post-production, and improves the production efficiency of product images.
|
|
5975
6224
|
* - **Online shopping experience optimization:**
|
|
5976
|
-
* Allows consumers to preview the wearing effect of products through virtual try-on
|
|
6225
|
+
* Allows consumers to preview the wearing effect of products through virtual try-on. This provides a more intuitive understanding of the product style, matching, and overall effect to assist in purchase decisions and enhance the shopping experience.
|
|
5977
6226
|
* ## Features
|
|
5978
|
-
* - **First,
|
|
5979
|
-
* - a. Model image:
|
|
5980
|
-
* - b. Product image:
|
|
5981
|
-
* - **Second,
|
|
5982
|
-
* - a. Specify product type:
|
|
5983
|
-
* - b. Automatic type recognition:
|
|
5984
|
-
* - **Finally, the system combines the model image, product image, and product type to generate a virtual try-on image,
|
|
5985
|
-
* - a. Preserve model details:
|
|
5986
|
-
* - b. Maintain image consistency:
|
|
5987
|
-
* - c. Generate try-on effect:
|
|
6227
|
+
* - **First, users need to input a model image and a product image. The system uses the model image as the try-on subject and applies the garment from the product image to the model:**
|
|
6228
|
+
* - a. Model image: The image of the person for the virtual try-on.
|
|
6229
|
+
* - b. Product image: The image of the garment, shoes, or hat to be worn by the model.
|
|
6230
|
+
* - **Second, users can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
6231
|
+
* - a. Specify product type: Users can directly input the type of the current product. The system will process it according to the specified type.
|
|
6232
|
+
* - b. Automatic type recognition: If users do not input the product type, the system will automatically recognize the product category in the product image and perform the virtual try-on based on the recognition result.
|
|
6233
|
+
* - **Finally, the system combines the model image, product image, and product type to generate a virtual try-on image, displaying the wearing effect of the product on the model:**
|
|
6234
|
+
* - 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.
|
|
6235
|
+
* - 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.
|
|
6236
|
+
* - c. Generate try-on effect: The product is naturally applied to the model, fitting the pose and body structure of the person to generate a coordinated and realistic virtual try-on image.
|
|
5988
6237
|
* ## Examples
|
|
5989
6238
|
* | **Type** | **Model image** | **Garment image** | **Try-on result** |
|
|
5990
6239
|
* | --- | --- | --- | --- |
|
|
5991
|
-
* | Tops |  |  |  |  |
|
|
5992
6241
|
* | Bottoms |  |  |  |
|
|
5993
|
-
* | Shoes |  |  |  |  |
|
|
5994
6243
|
* | Jumpsuits |  |  |  |
|
|
5995
6244
|
* | Dresses |  |  |  |
|
|
5996
6245
|
* | Hats |  |  |  |
|
|
@@ -6036,35 +6285,38 @@ export default class Client extends OpenApi {
|
|
|
6036
6285
|
}
|
|
6037
6286
|
|
|
6038
6287
|
/**
|
|
6039
|
-
* Generates virtual try-on images by using AI algorithms
|
|
6288
|
+
* Generates virtual try-on images by using AI algorithms to replace a model\\"s clothing with a specified garment. The service preserves the model\\"s pose, facial features, and background details while ensuring a realistic and well-fitted appearance. Users only need to provide the URLs of the original model and garment images to obtain the processed images.
|
|
6040
6289
|
*
|
|
6041
6290
|
* @remarks
|
|
6291
|
+
* *Note:**
|
|
6292
|
+
* VirtualTryOn is an early version that supports only single-item try-on and is scheduled to be deprecated soon.
|
|
6293
|
+
* New features such as multi-item outfit matching, model replacement, and pose replacement are now available in [Virtual try-on (AiTryOn)](https://api.aliyun.com/document/Aidge/2026-04-28/AiTryOn). Refer to the new API for integration.
|
|
6042
6294
|
* ## Scenarios
|
|
6043
|
-
* - **Virtual try-on for
|
|
6044
|
-
* Supports various
|
|
6045
|
-
* - **Virtual try-on for
|
|
6046
|
-
* Supports virtual try-on for
|
|
6295
|
+
* - **Virtual try-on for apparel:**
|
|
6296
|
+
* Supports various apparel categories such as tops, bottoms, jumpsuits, and dresses. After users upload a model image and a product image, the service generates natural and realistic try-on effects to intuitively display how the garment looks on the model.
|
|
6297
|
+
* - **Virtual try-on for footwear and headwear:**
|
|
6298
|
+
* Supports virtual try-on for products such as shoes and hats. The service intelligently matches the product position and proportion based on the model\\"s pose and body parts to present a coordinated and realistic wearing effect.
|
|
6047
6299
|
* - **E-commerce product display and marketing:**
|
|
6048
|
-
*
|
|
6300
|
+
* Helps merchants quickly generate model try-on images for different products. This reduces the costs of traditional photography, outfit changes, and post-production, and improves the production efficiency of product images.
|
|
6049
6301
|
* - **Online shopping experience optimization:**
|
|
6050
|
-
* Allows consumers to preview the wearing effect of products through virtual try-on
|
|
6302
|
+
* Allows consumers to preview the wearing effect of products through virtual try-on. This provides a more intuitive understanding of the product style, matching, and overall effect to assist in purchase decisions and enhance the shopping experience.
|
|
6051
6303
|
* ## Features
|
|
6052
|
-
* - **First,
|
|
6053
|
-
* - a. Model image:
|
|
6054
|
-
* - b. Product image:
|
|
6055
|
-
* - **Second,
|
|
6056
|
-
* - a. Specify product type:
|
|
6057
|
-
* - b. Automatic type recognition:
|
|
6058
|
-
* - **Finally, the system combines the model image, product image, and product type to generate a virtual try-on image,
|
|
6059
|
-
* - a. Preserve model details:
|
|
6060
|
-
* - b. Maintain image consistency:
|
|
6061
|
-
* - c. Generate try-on effect:
|
|
6304
|
+
* - **First, users need to input a model image and a product image. The system uses the model image as the try-on subject and applies the garment from the product image to the model:**
|
|
6305
|
+
* - a. Model image: The image of the person for the virtual try-on.
|
|
6306
|
+
* - b. Product image: The image of the garment, shoes, or hat to be worn by the model.
|
|
6307
|
+
* - **Second, users can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
6308
|
+
* - a. Specify product type: Users can directly input the type of the current product. The system will process it according to the specified type.
|
|
6309
|
+
* - b. Automatic type recognition: If users do not input the product type, the system will automatically recognize the product category in the product image and perform the virtual try-on based on the recognition result.
|
|
6310
|
+
* - **Finally, the system combines the model image, product image, and product type to generate a virtual try-on image, displaying the wearing effect of the product on the model:**
|
|
6311
|
+
* - 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.
|
|
6312
|
+
* - 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.
|
|
6313
|
+
* - c. Generate try-on effect: The product is naturally applied to the model, fitting the pose and body structure of the person to generate a coordinated and realistic virtual try-on image.
|
|
6062
6314
|
* ## Examples
|
|
6063
6315
|
* | **Type** | **Model image** | **Garment image** | **Try-on result** |
|
|
6064
6316
|
* | --- | --- | --- | --- |
|
|
6065
|
-
* | Tops |  |  |  |  |
|
|
6066
6318
|
* | Bottoms |  |  |  |
|
|
6067
|
-
* | Shoes |  |  |  |  |
|
|
6068
6320
|
* | Jumpsuits |  |  |  |
|
|
6069
6321
|
* | Dresses |  |  |  |
|
|
6070
6322
|
* | Hats |  |  |  |
|