@alicloud/aidge20260428 5.12.1 → 5.13.0
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 +211 -152
- package/dist/client.js +274 -152
- package/dist/client.js.map +1 -1
- package/dist/models/AiTryOnRequest.d.ts +43 -5
- package/dist/models/AiTryOnRequest.js +10 -0
- package/dist/models/AiTryOnRequest.js.map +1 -1
- package/dist/models/AiTryOnResponseBody.d.ts +4 -2
- package/dist/models/AiTryOnResponseBody.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/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/VirtualTryOnRequest.d.ts +2 -2
- package/dist/models/VirtualTryOnResponseBody.d.ts +8 -7
- package/dist/models/VirtualTryOnResponseBody.js.map +1 -1
- package/dist/models/VisionFlowRequest.d.ts +17 -17
- package/dist/models/VisionFlowResponseBody.d.ts +6 -6
- package/dist/models/VisionFlowShrinkRequest.d.ts +17 -17
- package/dist/models/model.d.ts +5 -0
- package/dist/models/model.js +15 -5
- package/dist/models/model.js.map +1 -1
- package/package.json +2 -1
- package/src/client.ts +290 -154
- package/src/models/AiTryOnRequest.ts +53 -5
- package/src/models/AiTryOnResponseBody.ts +4 -2
- package/src/models/DocumentTranslateRequest.ts +10 -7
- package/src/models/DocumentTranslateResponseBody.ts +3 -3
- 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/VirtualTryOnRequest.ts +2 -2
- package/src/models/VirtualTryOnResponseBody.ts +8 -7
- package/src/models/VisionFlowRequest.ts +17 -17
- package/src/models/VisionFlowResponseBody.ts +6 -6
- package/src/models/VisionFlowShrinkRequest.ts +17 -17
- package/src/models/model.ts +5 -0
package/src/client.ts
CHANGED
|
@@ -1,5 +1,6 @@
|
|
|
1
1
|
// This file is auto-generated, don't edit it
|
|
2
2
|
import * as $dara from '@darabonba/typescript';
|
|
3
|
+
import GatewayClient from '@alicloud/gateway-pop';
|
|
3
4
|
import OpenApi from '@alicloud/openapi-core';
|
|
4
5
|
import { OpenApiUtil, $OpenApiUtil }from '@alicloud/openapi-core';
|
|
5
6
|
|
|
@@ -11,6 +12,9 @@ export default class Client extends OpenApi {
|
|
|
11
12
|
|
|
12
13
|
constructor(config: $OpenApiUtil.Config) {
|
|
13
14
|
super(config);
|
|
15
|
+
this._productId = "Aidge";
|
|
16
|
+
let gatewayClient = new GatewayClient();
|
|
17
|
+
this._spi = gatewayClient;
|
|
14
18
|
this._endpointRule = "regional";
|
|
15
19
|
this.checkConfig(config);
|
|
16
20
|
this._endpoint = this.getEndpoint("aidge", this._regionId, this._endpointRule, this._network, this._suffix, this._endpointMap, this._endpoint);
|
|
@@ -82,38 +86,38 @@ export default class Client extends OpenApi {
|
|
|
82
86
|
}
|
|
83
87
|
|
|
84
88
|
/**
|
|
85
|
-
* Generates
|
|
89
|
+
* Generates virtual try-on images by applying specified garments to a model image based on AI algorithms. It preserves the model\\"s pose, facial features, and background details while ensuring a realistic fit. Users can obtain the processed images by providing the URLs of the original product and model images.
|
|
86
90
|
*
|
|
87
91
|
* @remarks
|
|
88
92
|
* ## Scenarios
|
|
89
93
|
* - **Virtual try-on for clothing:**
|
|
90
|
-
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After
|
|
94
|
+
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After users upload a model image and a product image, the system generates natural and realistic try-on effects to intuitively display how the clothing looks on the model.
|
|
91
95
|
* - **Virtual try-on for shoes and hats:**
|
|
92
|
-
* Supports virtual try-on for products such as shoes and hats.
|
|
96
|
+
* Supports virtual try-on for products such as shoes and hats. It intelligently matches the position and proportion of the product based on the model\\"s pose and body parts, presenting a coordinated and realistic wearing effect.
|
|
93
97
|
* - **E-commerce product display and marketing:**
|
|
94
|
-
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional photography, outfit changes, and post-production, and improving the production efficiency of product images.
|
|
98
|
+
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional photography, outfit changes, and post-production, and improving the production efficiency of product images.
|
|
95
99
|
* - **Online shopping experience optimization:**
|
|
96
|
-
*
|
|
100
|
+
* Consumers can preview the wearing effect of products through virtual try-on, more intuitively understand the style, matching, and overall effect of the products, assist in purchase decisions, and enhance the shopping experience.
|
|
97
101
|
* ## Features
|
|
98
|
-
* - **First,
|
|
99
|
-
* - a. Model image:
|
|
100
|
-
* - b. Product image:
|
|
101
|
-
* - **Second,
|
|
102
|
-
* - a. Specify product type:
|
|
103
|
-
* - b. Automatic type recognition:
|
|
104
|
-
* - **Finally, the system
|
|
105
|
-
* - a. Preserve model details:
|
|
106
|
-
* - b. Maintain image consistency:
|
|
107
|
-
* - c. Generate try-on effect:
|
|
102
|
+
* - **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:**
|
|
103
|
+
* - a. Model image: the image of the person who needs to perform the virtual try-on.
|
|
104
|
+
* - b. Product image: the image of the clothing, shoes, or hat to be worn by the model.
|
|
105
|
+
* - **Second, users can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
106
|
+
* - a. Specify product type: users can directly input the type of the current product, and the system will process it according to the specified type.
|
|
107
|
+
* - b. Automatic type recognition: if the user does 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.
|
|
108
|
+
* - **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:**
|
|
109
|
+
* - a. Preserve model details: the generation process does not adjust the appearance, hairstyle, pose, body shape, and other details of the person in the original model image.
|
|
110
|
+
* - b. Maintain image consistency: the background, composition, lighting, and overall visual effect of the original model image remain unchanged, and only the wearing area corresponding to the product is processed.
|
|
111
|
+
* - c. Generate try-on effect: naturally apply the product to the model, making it fit the person\\"s pose and body structure, and generate a coordinated and realistic virtual try-on image.
|
|
108
112
|
* ## Examples
|
|
109
|
-
* | **Type** | **Model image** | **
|
|
113
|
+
* | **Type** | **Model image** | **Garment image** | **Try-on result image** |
|
|
110
114
|
* | --- | --- | --- | --- |
|
|
111
|
-
* |
|
|
112
|
-
* |
|
|
115
|
+
* | Top |  |  |  |
|
|
116
|
+
* | Bottom |  |  |  |
|
|
113
117
|
* | Shoes |  |  |  |
|
|
114
|
-
* |
|
|
115
|
-
* |
|
|
116
|
-
* |
|
|
118
|
+
* | Jumpsuit |  |  |  |
|
|
119
|
+
* | Dress |  |  |  |
|
|
120
|
+
* | Hat |  |  |  |
|
|
117
121
|
*
|
|
118
122
|
* @param request - AiTryOnRequest
|
|
119
123
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -130,14 +134,34 @@ export default class Client extends OpenApi {
|
|
|
130
134
|
query["ClothType"] = request.clothType;
|
|
131
135
|
}
|
|
132
136
|
|
|
137
|
+
if (!$dara.isNull(request.mode)) {
|
|
138
|
+
query["Mode"] = request.mode;
|
|
139
|
+
}
|
|
140
|
+
|
|
133
141
|
if (!$dara.isNull(request.modelImageUrl)) {
|
|
134
142
|
query["ModelImageUrl"] = request.modelImageUrl;
|
|
135
143
|
}
|
|
136
144
|
|
|
145
|
+
if (!$dara.isNull(request.modelTemplateUrl)) {
|
|
146
|
+
query["ModelTemplateUrl"] = request.modelTemplateUrl;
|
|
147
|
+
}
|
|
148
|
+
|
|
149
|
+
if (!$dara.isNull(request.poseTemplateUrl)) {
|
|
150
|
+
query["PoseTemplateUrl"] = request.poseTemplateUrl;
|
|
151
|
+
}
|
|
152
|
+
|
|
153
|
+
if (!$dara.isNull(request.ratio)) {
|
|
154
|
+
query["Ratio"] = request.ratio;
|
|
155
|
+
}
|
|
156
|
+
|
|
137
157
|
if (!$dara.isNull(request.resolution)) {
|
|
138
158
|
query["Resolution"] = request.resolution;
|
|
139
159
|
}
|
|
140
160
|
|
|
161
|
+
if (!$dara.isNull(request.tryonType)) {
|
|
162
|
+
query["TryonType"] = request.tryonType;
|
|
163
|
+
}
|
|
164
|
+
|
|
141
165
|
let req = new $OpenApiUtil.OpenApiRequest({
|
|
142
166
|
query: OpenApiUtil.query(query),
|
|
143
167
|
});
|
|
@@ -156,38 +180,38 @@ export default class Client extends OpenApi {
|
|
|
156
180
|
}
|
|
157
181
|
|
|
158
182
|
/**
|
|
159
|
-
* Generates
|
|
183
|
+
* Generates virtual try-on images by applying specified garments to a model image based on AI algorithms. It preserves the model\\"s pose, facial features, and background details while ensuring a realistic fit. Users can obtain the processed images by providing the URLs of the original product and model images.
|
|
160
184
|
*
|
|
161
185
|
* @remarks
|
|
162
186
|
* ## Scenarios
|
|
163
187
|
* - **Virtual try-on for clothing:**
|
|
164
|
-
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After
|
|
188
|
+
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After users upload a model image and a product image, the system generates natural and realistic try-on effects to intuitively display how the clothing looks on the model.
|
|
165
189
|
* - **Virtual try-on for shoes and hats:**
|
|
166
|
-
* Supports virtual try-on for products such as shoes and hats.
|
|
190
|
+
* Supports virtual try-on for products such as shoes and hats. It intelligently matches the position and proportion of the product based on the model\\"s pose and body parts, presenting a coordinated and realistic wearing effect.
|
|
167
191
|
* - **E-commerce product display and marketing:**
|
|
168
|
-
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional photography, outfit changes, and post-production, and improving the production efficiency of product images.
|
|
192
|
+
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional photography, outfit changes, and post-production, and improving the production efficiency of product images.
|
|
169
193
|
* - **Online shopping experience optimization:**
|
|
170
|
-
*
|
|
194
|
+
* Consumers can preview the wearing effect of products through virtual try-on, more intuitively understand the style, matching, and overall effect of the products, assist in purchase decisions, and enhance the shopping experience.
|
|
171
195
|
* ## Features
|
|
172
|
-
* - **First,
|
|
173
|
-
* - a. Model image:
|
|
174
|
-
* - b. Product image:
|
|
175
|
-
* - **Second,
|
|
176
|
-
* - a. Specify product type:
|
|
177
|
-
* - b. Automatic type recognition:
|
|
178
|
-
* - **Finally, the system
|
|
179
|
-
* - a. Preserve model details:
|
|
180
|
-
* - b. Maintain image consistency:
|
|
181
|
-
* - c. Generate try-on effect:
|
|
196
|
+
* - **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:**
|
|
197
|
+
* - a. Model image: the image of the person who needs to perform the virtual try-on.
|
|
198
|
+
* - b. Product image: the image of the clothing, shoes, or hat to be worn by the model.
|
|
199
|
+
* - **Second, users can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
200
|
+
* - a. Specify product type: users can directly input the type of the current product, and the system will process it according to the specified type.
|
|
201
|
+
* - b. Automatic type recognition: if the user does 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.
|
|
202
|
+
* - **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:**
|
|
203
|
+
* - a. Preserve model details: the generation process does not adjust the appearance, hairstyle, pose, body shape, and other details of the person in the original model image.
|
|
204
|
+
* - b. Maintain image consistency: the background, composition, lighting, and overall visual effect of the original model image remain unchanged, and only the wearing area corresponding to the product is processed.
|
|
205
|
+
* - c. Generate try-on effect: naturally apply the product to the model, making it fit the person\\"s pose and body structure, and generate a coordinated and realistic virtual try-on image.
|
|
182
206
|
* ## Examples
|
|
183
|
-
* | **Type** | **Model image** | **
|
|
207
|
+
* | **Type** | **Model image** | **Garment image** | **Try-on result image** |
|
|
184
208
|
* | --- | --- | --- | --- |
|
|
185
|
-
* |
|
|
186
|
-
* |
|
|
209
|
+
* | Top |  |  |  |
|
|
210
|
+
* | Bottom |  |  |  |
|
|
187
211
|
* | Shoes |  |  |  |
|
|
188
|
-
* |
|
|
189
|
-
* |
|
|
190
|
-
* |
|
|
212
|
+
* | Jumpsuit |  |  |  |
|
|
213
|
+
* | Dress |  |  |  |
|
|
214
|
+
* | Hat |  |  |  |
|
|
191
215
|
*
|
|
192
216
|
* @param request - AiTryOnRequest
|
|
193
217
|
* @returns AiTryOnResponse
|
|
@@ -882,22 +906,29 @@ export default class Client extends OpenApi {
|
|
|
882
906
|
}
|
|
883
907
|
|
|
884
908
|
/**
|
|
885
|
-
* Translates documents
|
|
909
|
+
* 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:
|
|
910
|
+
* - Content accuracy: translation accuracy, and accuracy of parameters and units.
|
|
911
|
+
* - Structural integrity: overall layout continuity, and restoration of page margins and layouts.
|
|
886
912
|
*
|
|
887
913
|
* @remarks
|
|
888
|
-
*
|
|
889
|
-
* Designed specifically for document translation, this
|
|
914
|
+
* # Product introduction
|
|
915
|
+
* 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.
|
|
890
916
|
* It excels in the following aspects:
|
|
891
|
-
*
|
|
892
|
-
*
|
|
893
|
-
*
|
|
894
|
-
*
|
|
895
|
-
*
|
|
896
|
-
*
|
|
897
|
-
*
|
|
898
|
-
*
|
|
899
|
-
*
|
|
900
|
-
*
|
|
917
|
+
* * Content accuracy: translation accuracy, and accuracy of parameters and units.
|
|
918
|
+
*
|
|
919
|
+
* * Structural integrity: overall layout continuity, and restoration of page margins and layouts.
|
|
920
|
+
* # Scenarios
|
|
921
|
+
* Cross-border e-commerce product manuals, contracts, agreements, business proposals, qualification documents, teaching materials, courseware, and various other scenarios.
|
|
922
|
+
* # Features
|
|
923
|
+
* * Supports PDF, Word, and Excel formats. Supports source documents that contain multiple languages. For the detailed language list, see Section 4.4.
|
|
924
|
+
*
|
|
925
|
+
* * Supports the translation of text within images in documents, as well as complex translation scenarios involving other charts and special symbols.
|
|
926
|
+
*
|
|
927
|
+
* * Supports highly accurate layout restoration after translation.
|
|
928
|
+
*
|
|
929
|
+
* * Supports the translation of a single PDF or Word document with up to **800 pages**.
|
|
930
|
+
*
|
|
931
|
+
* * 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)
|
|
901
932
|
*
|
|
902
933
|
* @param request - DocumentTranslateRequest
|
|
903
934
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -940,22 +971,29 @@ export default class Client extends OpenApi {
|
|
|
940
971
|
}
|
|
941
972
|
|
|
942
973
|
/**
|
|
943
|
-
* Translates documents
|
|
974
|
+
* 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:
|
|
975
|
+
* - Content accuracy: translation accuracy, and accuracy of parameters and units.
|
|
976
|
+
* - Structural integrity: overall layout continuity, and restoration of page margins and layouts.
|
|
944
977
|
*
|
|
945
978
|
* @remarks
|
|
946
|
-
*
|
|
947
|
-
* Designed specifically for document translation, this
|
|
979
|
+
* # Product introduction
|
|
980
|
+
* 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.
|
|
948
981
|
* It excels in the following aspects:
|
|
949
|
-
*
|
|
950
|
-
*
|
|
951
|
-
*
|
|
952
|
-
*
|
|
953
|
-
*
|
|
954
|
-
*
|
|
955
|
-
*
|
|
956
|
-
*
|
|
957
|
-
*
|
|
958
|
-
*
|
|
982
|
+
* * Content accuracy: translation accuracy, and accuracy of parameters and units.
|
|
983
|
+
*
|
|
984
|
+
* * Structural integrity: overall layout continuity, and restoration of page margins and layouts.
|
|
985
|
+
* # Scenarios
|
|
986
|
+
* Cross-border e-commerce product manuals, contracts, agreements, business proposals, qualification documents, teaching materials, courseware, and various other scenarios.
|
|
987
|
+
* # Features
|
|
988
|
+
* * Supports PDF, Word, and Excel formats. Supports source documents that contain multiple languages. For the detailed language list, see Section 4.4.
|
|
989
|
+
*
|
|
990
|
+
* * Supports the translation of text within images in documents, as well as complex translation scenarios involving other charts and special symbols.
|
|
991
|
+
*
|
|
992
|
+
* * Supports highly accurate layout restoration after translation.
|
|
993
|
+
*
|
|
994
|
+
* * Supports the translation of a single PDF or Word document with up to **800 pages**.
|
|
995
|
+
*
|
|
996
|
+
* * 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)
|
|
959
997
|
*
|
|
960
998
|
* @param request - DocumentTranslateRequest
|
|
961
999
|
* @returns DocumentTranslateResponse
|
|
@@ -4429,6 +4467,104 @@ export default class Client extends OpenApi {
|
|
|
4429
4467
|
return await this.productHotspotDetectionWithOptions(request, runtime);
|
|
4430
4468
|
}
|
|
4431
4469
|
|
|
4470
|
+
/**
|
|
4471
|
+
* Generates a single-product showcase video for e-commerce merchants and platforms based on a 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 applies to product content production for non-apparel categories. For apparel categories, use the e-commerce enhanced edition.
|
|
4472
|
+
*
|
|
4473
|
+
* @remarks
|
|
4474
|
+
* # Product introduction
|
|
4475
|
+
* The basic e-commerce video edition is designed for e-commerce merchants and platforms. It generates a single-product showcase video based on a 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. This API uses asynchronous tasks, supports 720P and 1080P resolutions and four aspect ratios, and applies to product content production for non-apparel categories. For apparel categories, use the e-commerce enhanced edition.
|
|
4476
|
+
* # Scenarios
|
|
4477
|
+
* - New product material generation: Provide a product title and images to automatically plan storyboard content such as product debut, details, or usage demonstrations.
|
|
4478
|
+
* - 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.
|
|
4479
|
+
* - 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.
|
|
4480
|
+
* # Features
|
|
4481
|
+
* - 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.
|
|
4482
|
+
* - Product appearance consistency constraint: The system uses the selected complete product image as the appearance baseline. It checks the color scheme, structure, proportion, texture, version, and specifications of other images, and selects only reference images that can be confirmed to belong to the same SKU.
|
|
4483
|
+
* - 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).
|
|
4484
|
+
* - Asynchronous generation and task query: After a task is created, a task ID is returned. Callers use the query API to obtain the result. The final video includes background music, no voiceover, and no additional subtitles or marketing text.
|
|
4485
|
+
* # Examples
|
|
4486
|
+
* [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)
|
|
4487
|
+
*
|
|
4488
|
+
* @param tmpReq - ProductVideoGenerationRequest
|
|
4489
|
+
* @param runtime - runtime options for this request RuntimeOptions
|
|
4490
|
+
* @returns ProductVideoGenerationResponse
|
|
4491
|
+
*/
|
|
4492
|
+
async productVideoGenerationWithOptions(tmpReq: $_model.ProductVideoGenerationRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ProductVideoGenerationResponse> {
|
|
4493
|
+
tmpReq.validate();
|
|
4494
|
+
let request = new $_model.ProductVideoGenerationShrinkRequest({ });
|
|
4495
|
+
OpenApiUtil.convert(tmpReq, request);
|
|
4496
|
+
if (!$dara.isNull(tmpReq.productImages)) {
|
|
4497
|
+
request.productImagesShrink = OpenApiUtil.arrayToStringWithSpecifiedStyle(tmpReq.productImages, "product_images", "json");
|
|
4498
|
+
}
|
|
4499
|
+
|
|
4500
|
+
let query = { };
|
|
4501
|
+
if (!$dara.isNull(request.aspectRatio)) {
|
|
4502
|
+
query["aspect_ratio"] = request.aspectRatio;
|
|
4503
|
+
}
|
|
4504
|
+
|
|
4505
|
+
if (!$dara.isNull(request.duration)) {
|
|
4506
|
+
query["duration"] = request.duration;
|
|
4507
|
+
}
|
|
4508
|
+
|
|
4509
|
+
if (!$dara.isNull(request.productImagesShrink)) {
|
|
4510
|
+
query["product_images"] = request.productImagesShrink;
|
|
4511
|
+
}
|
|
4512
|
+
|
|
4513
|
+
if (!$dara.isNull(request.productTitle)) {
|
|
4514
|
+
query["product_title"] = request.productTitle;
|
|
4515
|
+
}
|
|
4516
|
+
|
|
4517
|
+
if (!$dara.isNull(request.resolution)) {
|
|
4518
|
+
query["resolution"] = request.resolution;
|
|
4519
|
+
}
|
|
4520
|
+
|
|
4521
|
+
if (!$dara.isNull(request.script)) {
|
|
4522
|
+
query["script"] = request.script;
|
|
4523
|
+
}
|
|
4524
|
+
|
|
4525
|
+
let req = new $OpenApiUtil.OpenApiRequest({
|
|
4526
|
+
query: OpenApiUtil.query(query),
|
|
4527
|
+
});
|
|
4528
|
+
let params = new $OpenApiUtil.Params({
|
|
4529
|
+
action: "ProductVideoGeneration",
|
|
4530
|
+
version: "2026-04-28",
|
|
4531
|
+
protocol: "HTTPS",
|
|
4532
|
+
pathname: "/",
|
|
4533
|
+
method: "POST",
|
|
4534
|
+
authType: "AK",
|
|
4535
|
+
style: "RPC",
|
|
4536
|
+
reqBodyType: "formData",
|
|
4537
|
+
bodyType: "json",
|
|
4538
|
+
});
|
|
4539
|
+
return $dara.cast<$_model.ProductVideoGenerationResponse>(await this.callApi(params, req, runtime), new $_model.ProductVideoGenerationResponse({}));
|
|
4540
|
+
}
|
|
4541
|
+
|
|
4542
|
+
/**
|
|
4543
|
+
* Generates a single-product showcase video for e-commerce merchants and platforms based on a 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 applies to product content production for non-apparel categories. For apparel categories, use the e-commerce enhanced edition.
|
|
4544
|
+
*
|
|
4545
|
+
* @remarks
|
|
4546
|
+
* # Product introduction
|
|
4547
|
+
* The basic e-commerce video edition is designed for e-commerce merchants and platforms. It generates a single-product showcase video based on a 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. This API uses asynchronous tasks, supports 720P and 1080P resolutions and four aspect ratios, and applies to product content production for non-apparel categories. For apparel categories, use the e-commerce enhanced edition.
|
|
4548
|
+
* # Scenarios
|
|
4549
|
+
* - New product material generation: Provide a product title and images to automatically plan storyboard content such as product debut, details, or usage demonstrations.
|
|
4550
|
+
* - 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.
|
|
4551
|
+
* - 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.
|
|
4552
|
+
* # Features
|
|
4553
|
+
* - 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.
|
|
4554
|
+
* - Product appearance consistency constraint: The system uses the selected complete product image as the appearance baseline. It checks the color scheme, structure, proportion, texture, version, and specifications of other images, and selects only reference images that can be confirmed to belong to the same SKU.
|
|
4555
|
+
* - 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).
|
|
4556
|
+
* - Asynchronous generation and task query: After a task is created, a task ID is returned. Callers use the query API to obtain the result. The final video includes background music, no voiceover, and no additional subtitles or marketing text.
|
|
4557
|
+
* # Examples
|
|
4558
|
+
* [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)
|
|
4559
|
+
*
|
|
4560
|
+
* @param request - ProductVideoGenerationRequest
|
|
4561
|
+
* @returns ProductVideoGenerationResponse
|
|
4562
|
+
*/
|
|
4563
|
+
async productVideoGeneration(request: $_model.ProductVideoGenerationRequest): Promise<$_model.ProductVideoGenerationResponse> {
|
|
4564
|
+
let runtime = new $dara.RuntimeOptions({ });
|
|
4565
|
+
return await this.productVideoGenerationWithOptions(request, runtime);
|
|
4566
|
+
}
|
|
4567
|
+
|
|
4432
4568
|
/**
|
|
4433
4569
|
* Queries the result of an asynchronous task. The API name in the POP gateway is QueryAsyncTaskResult.
|
|
4434
4570
|
*
|
|
@@ -5958,26 +6094,26 @@ export default class Client extends OpenApi {
|
|
|
5958
6094
|
}
|
|
5959
6095
|
|
|
5960
6096
|
/**
|
|
5961
|
-
* Generates virtual try-on images by
|
|
6097
|
+
* Generates virtual try-on images by applying a specified garment to a model image based on AI algorithms. It preserves the model\\"s pose, facial features, and background details while ensuring a realistic fit. Users only need to provide the URLs of the original model and garment images to obtain the processed image.
|
|
5962
6098
|
*
|
|
5963
6099
|
* @remarks
|
|
5964
6100
|
* ## Scenarios
|
|
5965
6101
|
* - **Virtual try-on for clothing:**
|
|
5966
|
-
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After
|
|
6102
|
+
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After users upload a model image and a garment image, the system generates natural and realistic try-on effects to intuitively display how the garment looks on the model.
|
|
5967
6103
|
* - **Virtual try-on for shoes and hats:**
|
|
5968
|
-
* Supports virtual try-on for accessories such as shoes and hats. The system intelligently matches the position and proportion of the
|
|
6104
|
+
* Supports virtual try-on for accessories such as shoes and hats. The system intelligently matches the position and proportion of the product based on the model\\"s pose and body parts, presenting a coordinated and realistic wearing effect.
|
|
5969
6105
|
* - **E-commerce product display and marketing:**
|
|
5970
|
-
*
|
|
6106
|
+
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional photography, outfit changes, and post-production, and improving the production efficiency of product images.
|
|
5971
6107
|
* - **Online shopping experience optimization:**
|
|
5972
|
-
* Allows consumers to preview the wearing effect of products through virtual try-on, providing a more intuitive understanding of the style, matching, and overall effect of the
|
|
6108
|
+
* Allows consumers to preview the wearing effect of products through virtual try-on, providing a more intuitive understanding of the style, matching, and overall effect of the product, which assists in purchase decisions and enhances the shopping experience.
|
|
5973
6109
|
* ## Features
|
|
5974
|
-
* - **First,
|
|
5975
|
-
* - a. Model image: the image of the person
|
|
5976
|
-
* - b.
|
|
5977
|
-
* - **Second,
|
|
5978
|
-
* - a. Specify product type:
|
|
5979
|
-
* - b. Automatic type recognition: if
|
|
5980
|
-
* - **Finally, the system combines the model image,
|
|
6110
|
+
* - **First, users need to input a model image and a garment image. The system uses the model image as the try-on subject and applies the garment from the garment image to the model:**
|
|
6111
|
+
* - a. Model image: the image of the person for the virtual try-on.
|
|
6112
|
+
* - b. Garment image: the image of the clothing, shoes, or hat to be worn by the model.
|
|
6113
|
+
* - **Second, users can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
6114
|
+
* - a. Specify product type: users can directly input the type of the current product, and the system will process it according to the specified type.
|
|
6115
|
+
* - b. Automatic type recognition: if the user does not input the product type, the system will automatically recognize the product category in the garment image and perform the virtual try-on based on the recognition result.
|
|
6116
|
+
* - **Finally, the system combines the model image, garment image, and product type to generate a virtual try-on image, displaying the wearing effect of the product on the model:**
|
|
5981
6117
|
* - a. Preserve model details: the generation process does not adjust the appearance, hairstyle, pose, body shape, or other details of the person in the original model image.
|
|
5982
6118
|
* - 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.
|
|
5983
6119
|
* - c. Generate try-on effect: the product is naturally applied to the model, fitting the person\\"s pose and body structure to generate a coordinated and realistic virtual try-on image.
|
|
@@ -5985,8 +6121,8 @@ export default class Client extends OpenApi {
|
|
|
5985
6121
|
* | **Type** | **Model image** | **Garment image** | **Try-on result** |
|
|
5986
6122
|
* | --- | --- | --- | --- |
|
|
5987
6123
|
* | Tops |  |  |  |
|
|
5988
|
-
* | Bottoms |  |  |  |  |  |
|
|
6125
|
+
* | Shoes |  |  |  |
|
|
5990
6126
|
* | Jumpsuits |  |  |  |
|
|
5991
6127
|
* | Dresses |  |  |  |
|
|
5992
6128
|
* | Hats |  |  |  |
|
|
@@ -6032,26 +6168,26 @@ export default class Client extends OpenApi {
|
|
|
6032
6168
|
}
|
|
6033
6169
|
|
|
6034
6170
|
/**
|
|
6035
|
-
* Generates virtual try-on images by
|
|
6171
|
+
* Generates virtual try-on images by applying a specified garment to a model image based on AI algorithms. It preserves the model\\"s pose, facial features, and background details while ensuring a realistic fit. Users only need to provide the URLs of the original model and garment images to obtain the processed image.
|
|
6036
6172
|
*
|
|
6037
6173
|
* @remarks
|
|
6038
6174
|
* ## Scenarios
|
|
6039
6175
|
* - **Virtual try-on for clothing:**
|
|
6040
|
-
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After
|
|
6176
|
+
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After users upload a model image and a garment image, the system generates natural and realistic try-on effects to intuitively display how the garment looks on the model.
|
|
6041
6177
|
* - **Virtual try-on for shoes and hats:**
|
|
6042
|
-
* Supports virtual try-on for accessories such as shoes and hats. The system intelligently matches the position and proportion of the
|
|
6178
|
+
* Supports virtual try-on for accessories such as shoes and hats. The system intelligently matches the position and proportion of the product based on the model\\"s pose and body parts, presenting a coordinated and realistic wearing effect.
|
|
6043
6179
|
* - **E-commerce product display and marketing:**
|
|
6044
|
-
*
|
|
6180
|
+
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional photography, outfit changes, and post-production, and improving the production efficiency of product images.
|
|
6045
6181
|
* - **Online shopping experience optimization:**
|
|
6046
|
-
* Allows consumers to preview the wearing effect of products through virtual try-on, providing a more intuitive understanding of the style, matching, and overall effect of the
|
|
6182
|
+
* Allows consumers to preview the wearing effect of products through virtual try-on, providing a more intuitive understanding of the style, matching, and overall effect of the product, which assists in purchase decisions and enhances the shopping experience.
|
|
6047
6183
|
* ## Features
|
|
6048
|
-
* - **First,
|
|
6049
|
-
* - a. Model image: the image of the person
|
|
6050
|
-
* - b.
|
|
6051
|
-
* - **Second,
|
|
6052
|
-
* - a. Specify product type:
|
|
6053
|
-
* - b. Automatic type recognition: if
|
|
6054
|
-
* - **Finally, the system combines the model image,
|
|
6184
|
+
* - **First, users need to input a model image and a garment image. The system uses the model image as the try-on subject and applies the garment from the garment image to the model:**
|
|
6185
|
+
* - a. Model image: the image of the person for the virtual try-on.
|
|
6186
|
+
* - b. Garment image: the image of the clothing, shoes, or hat to be worn by the model.
|
|
6187
|
+
* - **Second, users can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
6188
|
+
* - a. Specify product type: users can directly input the type of the current product, and the system will process it according to the specified type.
|
|
6189
|
+
* - b. Automatic type recognition: if the user does not input the product type, the system will automatically recognize the product category in the garment image and perform the virtual try-on based on the recognition result.
|
|
6190
|
+
* - **Finally, the system combines the model image, garment image, and product type to generate a virtual try-on image, displaying the wearing effect of the product on the model:**
|
|
6055
6191
|
* - a. Preserve model details: the generation process does not adjust the appearance, hairstyle, pose, body shape, or other details of the person in the original model image.
|
|
6056
6192
|
* - 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.
|
|
6057
6193
|
* - c. Generate try-on effect: the product is naturally applied to the model, fitting the person\\"s pose and body structure to generate a coordinated and realistic virtual try-on image.
|
|
@@ -6059,8 +6195,8 @@ export default class Client extends OpenApi {
|
|
|
6059
6195
|
* | **Type** | **Model image** | **Garment image** | **Try-on result** |
|
|
6060
6196
|
* | --- | --- | --- | --- |
|
|
6061
6197
|
* | Tops |  |  |  |
|
|
6062
|
-
* | Bottoms |  |  |  |  |  |
|
|
6199
|
+
* | Shoes |  |  |  |
|
|
6064
6200
|
* | Jumpsuits |  |  |  |
|
|
6065
6201
|
* | Dresses |  |  |  |
|
|
6066
6202
|
* | Hats |  |  |  |
|
|
@@ -6074,61 +6210,61 @@ export default class Client extends OpenApi {
|
|
|
6074
6210
|
}
|
|
6075
6211
|
|
|
6076
6212
|
/**
|
|
6077
|
-
* Provides a one-stop AI
|
|
6213
|
+
* Provides a one-stop AI image processing service for e-commerce sellers. Orchestrates six atomic capabilities—element recognition, intelligent cutout, intelligent erasure, image translation Pro, intelligent cropping, and high-definition upscaling—into an image processing workflow. Users can upload an image once, select the required capabilities, and complete multiple image optimizations in sequence to output product images that meet the requirements of e-commerce platforms. (Asynchronous)
|
|
6078
6214
|
*
|
|
6079
6215
|
* @remarks
|
|
6080
|
-
* # 1. Product
|
|
6081
|
-
*
|
|
6082
|
-
* # 2.
|
|
6083
|
-
* Applicable to batch optimization of product images in cross-platform listing scenarios. Adapts source product images into main images, SKU images, and detail images required by listing platforms.
|
|
6084
|
-
* *
|
|
6216
|
+
* # 1. Product introduction
|
|
6217
|
+
* Provides a one-stop AI image processing service for e-commerce sellers. Orchestrates six atomic capabilities—element recognition, intelligent cutout, intelligent erasure, image translation Pro, intelligent cropping, and high-definition upscaling—into an image processing workflow. Users can upload an image once, select the required capabilities, and complete multiple image optimizations in sequence to output product images that meet the requirements of e-commerce platforms. (Asynchronous)
|
|
6218
|
+
* # 2. Scenarios
|
|
6219
|
+
* Applicable to batch optimization of product images in cross-platform listing scenarios. Adapts source product images into main images, SKU images, and detail images required by listing platforms. Supports the following operations:
|
|
6220
|
+
* * Identifies low-quality images with text, watermarks, logos, or cluttered text, and allows users to filter the images to be processed.
|
|
6085
6221
|
*
|
|
6086
|
-
* *
|
|
6222
|
+
* * Removes non-compliant elements such as watermarks, logos, cluttered text, and Chinese text from the original image.
|
|
6087
6223
|
*
|
|
6088
|
-
* *
|
|
6224
|
+
* * Removes the background around the main product subject.
|
|
6089
6225
|
*
|
|
6090
|
-
* *
|
|
6226
|
+
* * Translates text in the image into other languages.
|
|
6091
6227
|
*
|
|
6092
|
-
* *
|
|
6228
|
+
* * Expands the image to other sizes (by ratio or dimensions) and automatically fills the background.
|
|
6093
6229
|
*
|
|
6094
|
-
* *
|
|
6230
|
+
* * Crops the image to a specified size.
|
|
6095
6231
|
*
|
|
6096
|
-
* *
|
|
6232
|
+
* * Upscales the image pixels by a specified factor.
|
|
6097
6233
|
* # 3. Features
|
|
6098
|
-
*
|
|
6234
|
+
* Users input the URL of a product image and select the required AI capabilities through the Ability parameter (1=Intelligent element recognition, 2=Intelligent cutout, 3=Intelligent erasure, 4=Image translation Pro, 5=Image expansion, 6=Intelligent cropping, 7=High-definition upscaling). The system executes the selected capabilities in a preset sequence. Because intelligent element recognition helps users determine whether an image contains specific elements, and the presence of these elements affects the selection of subsequent AI capabilities, an additional input option is provided. This option allows users to choose whether to filter out images from subsequent AI processing or retain them without further processing.
|
|
6099
6235
|
* 
|
|
6100
|
-
*
|
|
6101
|
-
* 1.
|
|
6236
|
+
* The following section describes each AI capability:
|
|
6237
|
+
* **1. Intelligent element recognition**: An element detection capability designed specifically for e-commerce images. It identifies elements such as text, logos, watermarks, and text blocks in the subject and background of an image, and returns Boolean detection results. Users can filter images based on the recognition results (for example, processing only images with watermarks) and link this capability with subsequent ones—first identifying the types of elements to be optimized, and then precisely executing operations such as erasure.
|
|
6102
6238
|
*
|
|
6103
|
-
* 2.
|
|
6239
|
+
* **2. Intelligent cutout**: Automatically identifies the main product subject in an image and precisely separates it from the background. Based on deep learning models, it supports precise segmentation of complex edges such as hair and transparent objects. It can output images with transparent or white backgrounds, supports custom background colors and target size cropping, and directly generates product display images that comply with e-commerce platform specifications.
|
|
6104
6240
|
*
|
|
6105
|
-
* 3.
|
|
6241
|
+
* **3. Intelligent erasure**: Automatically identifies and removes non-compliant elements in e-commerce images, such as text, specific names (brand or store names), transparent text blocks, and cluttered text. It supports specifying the removal of elements in the subject area or non-subject area separately. It also supports precisely specifying the removal area through the Mask parameter to achieve efficient and compliant cleanup of large batches of images.
|
|
6106
6242
|
*
|
|
6107
|
-
* 4.
|
|
6243
|
+
* **4. Image translation Pro**: Integrates multimodal large model technology to translate text in an image into a target language and directly renders it in the corresponding position of the original image. It supports over 100 language pairs. It provides features such as product subject text protection, brand name protection, and translation intervention glossaries to avoid mistranslating embedded product information. After translation, it can return layout information such as text position, font, and color to support secondary editing.
|
|
6108
6244
|
*
|
|
6109
|
-
* 5.
|
|
6245
|
+
* **5. Intelligent image expansion**: Expands the image canvas based on AI generation technology to broaden the image field of view without cropping the subject. It supports multiple expansion methods: expanding by aspect ratio (1:1, 3:4, 4:3, 9:16, 16:9), scaling by horizontal or vertical proportion (1.0 to 3.0 times), and shifting pixels in the up, down, left, or right directions. The AI automatically fills and generates naturally transitioning background content.
|
|
6110
6246
|
*
|
|
6111
|
-
* 6.
|
|
6247
|
+
* **6. Intelligent cropping**: Intelligently crops images to specified sizes, automatically identifies the main subject area of the image, and precisely retains the core content. It supports custom output width and height (100 to 5000 pixels) and adapts to the image size requirements of different e-commerce platforms and ad slots, ensuring that the subject stands out and the picture is balanced after cropping.
|
|
6112
6248
|
*
|
|
6113
|
-
* 7.
|
|
6114
|
-
* # 4.
|
|
6249
|
+
* **7. High-definition upscaling**: Enhances details and reduces noise while upscaling the image. It supports 2x to 4x upscaling. It is applicable to improving the clarity of low-resolution product images and optimizing visual presentation. It supports output in formats such as PNG, JPG, and BMP.
|
|
6250
|
+
* # 4. Effect comparison
|
|
6115
6251
|
* | **Original image** | **Capabilities used** | **Output image** |
|
|
6116
6252
|
* | --- | --- | --- |
|
|
6117
|
-
* |  | * Intelligent
|
|
6253
|
+
* |  | * Intelligent recognition
|
|
6118
6254
|
*
|
|
6119
|
-
* * Image
|
|
6255
|
+
* * Image translation Pro
|
|
6120
6256
|
*
|
|
6121
6257
|
* * Intelligent cropping |  |
|
|
6122
|
-
* |  | * Intelligent
|
|
6258
|
+
* |  | * Intelligent cutout
|
|
6123
6259
|
*
|
|
6124
|
-
* * Intelligent
|
|
6260
|
+
* * Intelligent erasure
|
|
6125
6261
|
*
|
|
6126
6262
|
* * Intelligent cropping |  |
|
|
6127
|
-
* |  | * Intelligent
|
|
6263
|
+
* |  | * Intelligent recognition
|
|
6128
6264
|
*
|
|
6129
|
-
* * Intelligent
|
|
6265
|
+
* * Intelligent erasure
|
|
6130
6266
|
*
|
|
6131
|
-
* *
|
|
6267
|
+
* * High-definition upscaling |  |
|
|
6132
6268
|
*
|
|
6133
6269
|
* @param tmpReq - VisionFlowRequest
|
|
6134
6270
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -6245,61 +6381,61 @@ export default class Client extends OpenApi {
|
|
|
6245
6381
|
}
|
|
6246
6382
|
|
|
6247
6383
|
/**
|
|
6248
|
-
* Provides a one-stop AI
|
|
6384
|
+
* Provides a one-stop AI image processing service for e-commerce sellers. Orchestrates six atomic capabilities—element recognition, intelligent cutout, intelligent erasure, image translation Pro, intelligent cropping, and high-definition upscaling—into an image processing workflow. Users can upload an image once, select the required capabilities, and complete multiple image optimizations in sequence to output product images that meet the requirements of e-commerce platforms. (Asynchronous)
|
|
6249
6385
|
*
|
|
6250
6386
|
* @remarks
|
|
6251
|
-
* # 1. Product
|
|
6252
|
-
*
|
|
6253
|
-
* # 2.
|
|
6254
|
-
* Applicable to batch optimization of product images in cross-platform listing scenarios. Adapts source product images into main images, SKU images, and detail images required by listing platforms.
|
|
6255
|
-
* *
|
|
6387
|
+
* # 1. Product introduction
|
|
6388
|
+
* Provides a one-stop AI image processing service for e-commerce sellers. Orchestrates six atomic capabilities—element recognition, intelligent cutout, intelligent erasure, image translation Pro, intelligent cropping, and high-definition upscaling—into an image processing workflow. Users can upload an image once, select the required capabilities, and complete multiple image optimizations in sequence to output product images that meet the requirements of e-commerce platforms. (Asynchronous)
|
|
6389
|
+
* # 2. Scenarios
|
|
6390
|
+
* Applicable to batch optimization of product images in cross-platform listing scenarios. Adapts source product images into main images, SKU images, and detail images required by listing platforms. Supports the following operations:
|
|
6391
|
+
* * Identifies low-quality images with text, watermarks, logos, or cluttered text, and allows users to filter the images to be processed.
|
|
6256
6392
|
*
|
|
6257
|
-
* *
|
|
6393
|
+
* * Removes non-compliant elements such as watermarks, logos, cluttered text, and Chinese text from the original image.
|
|
6258
6394
|
*
|
|
6259
|
-
* *
|
|
6395
|
+
* * Removes the background around the main product subject.
|
|
6260
6396
|
*
|
|
6261
|
-
* *
|
|
6397
|
+
* * Translates text in the image into other languages.
|
|
6262
6398
|
*
|
|
6263
|
-
* *
|
|
6399
|
+
* * Expands the image to other sizes (by ratio or dimensions) and automatically fills the background.
|
|
6264
6400
|
*
|
|
6265
|
-
* *
|
|
6401
|
+
* * Crops the image to a specified size.
|
|
6266
6402
|
*
|
|
6267
|
-
* *
|
|
6403
|
+
* * Upscales the image pixels by a specified factor.
|
|
6268
6404
|
* # 3. Features
|
|
6269
|
-
*
|
|
6405
|
+
* Users input the URL of a product image and select the required AI capabilities through the Ability parameter (1=Intelligent element recognition, 2=Intelligent cutout, 3=Intelligent erasure, 4=Image translation Pro, 5=Image expansion, 6=Intelligent cropping, 7=High-definition upscaling). The system executes the selected capabilities in a preset sequence. Because intelligent element recognition helps users determine whether an image contains specific elements, and the presence of these elements affects the selection of subsequent AI capabilities, an additional input option is provided. This option allows users to choose whether to filter out images from subsequent AI processing or retain them without further processing.
|
|
6270
6406
|
* 
|
|
6271
|
-
*
|
|
6272
|
-
* 1.
|
|
6407
|
+
* The following section describes each AI capability:
|
|
6408
|
+
* **1. Intelligent element recognition**: An element detection capability designed specifically for e-commerce images. It identifies elements such as text, logos, watermarks, and text blocks in the subject and background of an image, and returns Boolean detection results. Users can filter images based on the recognition results (for example, processing only images with watermarks) and link this capability with subsequent ones—first identifying the types of elements to be optimized, and then precisely executing operations such as erasure.
|
|
6273
6409
|
*
|
|
6274
|
-
* 2.
|
|
6410
|
+
* **2. Intelligent cutout**: Automatically identifies the main product subject in an image and precisely separates it from the background. Based on deep learning models, it supports precise segmentation of complex edges such as hair and transparent objects. It can output images with transparent or white backgrounds, supports custom background colors and target size cropping, and directly generates product display images that comply with e-commerce platform specifications.
|
|
6275
6411
|
*
|
|
6276
|
-
* 3.
|
|
6412
|
+
* **3. Intelligent erasure**: Automatically identifies and removes non-compliant elements in e-commerce images, such as text, specific names (brand or store names), transparent text blocks, and cluttered text. It supports specifying the removal of elements in the subject area or non-subject area separately. It also supports precisely specifying the removal area through the Mask parameter to achieve efficient and compliant cleanup of large batches of images.
|
|
6277
6413
|
*
|
|
6278
|
-
* 4.
|
|
6414
|
+
* **4. Image translation Pro**: Integrates multimodal large model technology to translate text in an image into a target language and directly renders it in the corresponding position of the original image. It supports over 100 language pairs. It provides features such as product subject text protection, brand name protection, and translation intervention glossaries to avoid mistranslating embedded product information. After translation, it can return layout information such as text position, font, and color to support secondary editing.
|
|
6279
6415
|
*
|
|
6280
|
-
* 5.
|
|
6416
|
+
* **5. Intelligent image expansion**: Expands the image canvas based on AI generation technology to broaden the image field of view without cropping the subject. It supports multiple expansion methods: expanding by aspect ratio (1:1, 3:4, 4:3, 9:16, 16:9), scaling by horizontal or vertical proportion (1.0 to 3.0 times), and shifting pixels in the up, down, left, or right directions. The AI automatically fills and generates naturally transitioning background content.
|
|
6281
6417
|
*
|
|
6282
|
-
* 6.
|
|
6418
|
+
* **6. Intelligent cropping**: Intelligently crops images to specified sizes, automatically identifies the main subject area of the image, and precisely retains the core content. It supports custom output width and height (100 to 5000 pixels) and adapts to the image size requirements of different e-commerce platforms and ad slots, ensuring that the subject stands out and the picture is balanced after cropping.
|
|
6283
6419
|
*
|
|
6284
|
-
* 7.
|
|
6285
|
-
* # 4.
|
|
6420
|
+
* **7. High-definition upscaling**: Enhances details and reduces noise while upscaling the image. It supports 2x to 4x upscaling. It is applicable to improving the clarity of low-resolution product images and optimizing visual presentation. It supports output in formats such as PNG, JPG, and BMP.
|
|
6421
|
+
* # 4. Effect comparison
|
|
6286
6422
|
* | **Original image** | **Capabilities used** | **Output image** |
|
|
6287
6423
|
* | --- | --- | --- |
|
|
6288
|
-
* |  | * Intelligent
|
|
6424
|
+
* |  | * Intelligent recognition
|
|
6289
6425
|
*
|
|
6290
|
-
* * Image
|
|
6426
|
+
* * Image translation Pro
|
|
6291
6427
|
*
|
|
6292
6428
|
* * Intelligent cropping |  |
|
|
6293
|
-
* |  | * Intelligent
|
|
6429
|
+
* |  | * Intelligent cutout
|
|
6294
6430
|
*
|
|
6295
|
-
* * Intelligent
|
|
6431
|
+
* * Intelligent erasure
|
|
6296
6432
|
*
|
|
6297
6433
|
* * Intelligent cropping |  |
|
|
6298
|
-
* |  | * Intelligent
|
|
6434
|
+
* |  | * Intelligent recognition
|
|
6299
6435
|
*
|
|
6300
|
-
* * Intelligent
|
|
6436
|
+
* * Intelligent erasure
|
|
6301
6437
|
*
|
|
6302
|
-
* *
|
|
6438
|
+
* * High-definition upscaling |  |
|
|
6303
6439
|
*
|
|
6304
6440
|
* @param request - VisionFlowRequest
|
|
6305
6441
|
* @returns VisionFlowResponse
|