@alicloud/aidge20260428 5.6.0 → 5.7.1
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 +199 -122
- package/dist/client.js +235 -122
- package/dist/client.js.map +1 -1
- package/dist/models/AiTryOnRequest.d.ts +51 -0
- package/dist/models/AiTryOnRequest.js +64 -0
- package/dist/models/AiTryOnRequest.js.map +1 -0
- package/dist/models/AiTryOnResponse.d.ts +19 -0
- package/dist/models/AiTryOnResponse.js +69 -0
- package/dist/models/AiTryOnResponse.js.map +1 -0
- package/dist/models/AiTryOnResponseBody.d.ts +124 -0
- package/dist/models/AiTryOnResponseBody.js +120 -0
- package/dist/models/AiTryOnResponseBody.js.map +1 -0
- package/dist/models/AssetOptimizeLiteResponseBody.d.ts +0 -2
- package/dist/models/AssetOptimizeLiteResponseBody.js +0 -2
- package/dist/models/AssetOptimizeLiteResponseBody.js.map +1 -1
- package/dist/models/DocumentTranslateRequest.d.ts +1 -1
- package/dist/models/DocumentTranslateResponseBody.d.ts +2 -2
- package/dist/models/ImageRecognitionRequest.d.ts +4 -4
- package/dist/models/ImageRecognitionResponseBody.d.ts +2 -2
- package/dist/models/ImageRecognitionShrinkRequest.d.ts +4 -4
- package/dist/models/ImageTranslationProRequest.d.ts +8 -8
- package/dist/models/MerchandisePlacementDetectionRequest.d.ts +1 -0
- package/dist/models/MerchandisePlacementDetectionRequest.js +2 -0
- package/dist/models/MerchandisePlacementDetectionRequest.js.map +1 -1
- package/dist/models/PrepaidTextTranslateRequest.d.ts +1 -1
- package/dist/models/PrepaidTextTranslateResponseBody.d.ts +2 -2
- package/dist/models/PrepaidTextTranslateShrinkRequest.d.ts +1 -1
- package/dist/models/SizeChartExtractRequest.d.ts +2 -2
- package/dist/models/SizeChartExtractResponseBody.d.ts +1 -1
- package/dist/models/SizeChartExtractShrinkRequest.d.ts +2 -2
- package/dist/models/TextCorrectResponseBody.d.ts +1 -1
- package/dist/models/TextTranslateRequest.d.ts +11 -5
- package/dist/models/TextTranslateRequest.js.map +1 -1
- package/dist/models/TextTranslateResponseBody.d.ts +1 -1
- package/dist/models/TextTranslateShrinkRequest.d.ts +11 -5
- package/dist/models/TextTranslateShrinkRequest.js.map +1 -1
- package/dist/models/VideoTranslationRequest.d.ts +1 -1
- package/dist/models/VideoTranslationResponseBody.d.ts +1 -1
- package/dist/models/VideoTranslationShrinkRequest.d.ts +1 -1
- package/dist/models/VirtualTryOnResponseBody.d.ts +3 -3
- package/dist/models/model.d.ts +5 -0
- package/dist/models/model.js +14 -4
- package/dist/models/model.js.map +1 -1
- package/package.json +1 -1
- package/src/client.ts +242 -122
- package/src/models/AiTryOnRequest.ts +70 -0
- package/src/models/AiTryOnResponse.ts +40 -0
- package/src/models/AiTryOnResponseBody.ts +179 -0
- package/src/models/AssetOptimizeLiteResponseBody.ts +0 -2
- package/src/models/DocumentTranslateRequest.ts +1 -1
- package/src/models/DocumentTranslateResponseBody.ts +2 -2
- package/src/models/ImageRecognitionRequest.ts +4 -4
- package/src/models/ImageRecognitionResponseBody.ts +2 -2
- package/src/models/ImageRecognitionShrinkRequest.ts +4 -4
- package/src/models/ImageTranslationProRequest.ts +8 -8
- package/src/models/MerchandisePlacementDetectionRequest.ts +3 -0
- package/src/models/PrepaidTextTranslateRequest.ts +1 -1
- package/src/models/PrepaidTextTranslateResponseBody.ts +2 -2
- package/src/models/PrepaidTextTranslateShrinkRequest.ts +1 -1
- package/src/models/SizeChartExtractRequest.ts +2 -2
- package/src/models/SizeChartExtractResponseBody.ts +1 -1
- package/src/models/SizeChartExtractShrinkRequest.ts +2 -2
- package/src/models/TextCorrectResponseBody.ts +1 -1
- package/src/models/TextTranslateRequest.ts +11 -5
- package/src/models/TextTranslateResponseBody.ts +1 -1
- package/src/models/TextTranslateShrinkRequest.ts +11 -5
- package/src/models/VideoTranslationRequest.ts +1 -1
- package/src/models/VideoTranslationResponseBody.ts +1 -1
- package/src/models/VideoTranslationShrinkRequest.ts +1 -1
- package/src/models/VirtualTryOnResponseBody.ts +3 -3
- package/src/models/model.ts +5 -0
package/dist/client.d.ts
CHANGED
|
@@ -8,6 +8,83 @@ export default class Client extends OpenApi {
|
|
|
8
8
|
getEndpoint(productId: string, regionId: string, endpointRule: string, network: string, suffix: string, endpointMap: {
|
|
9
9
|
[key: string]: string;
|
|
10
10
|
}, endpoint: string): string;
|
|
11
|
+
/**
|
|
12
|
+
* Virtual Try-On is an AI algorithm-based image generation API service that replaces the clothing on a model with the garment provided by the user based on the input garment image and model image, while preserving the model\\"s other details and scene details without altering the model\\"s pose, facial features, or other attributes, and achieving realistic and well-fitted clothing placement. Users only need to provide the URL of the original product image to obtain a processed clean image.
|
|
13
|
+
*
|
|
14
|
+
* @remarks
|
|
15
|
+
* ## Scenarios
|
|
16
|
+
* - **Virtual try-on for clothing products:**
|
|
17
|
+
* Supports multiple clothing categories including tops, bottoms, jumpsuits, and dresses. After uploading a person image and a product image, the service generates natural and realistic try-on results that intuitively showcase how the clothing looks when worn.
|
|
18
|
+
* - **Virtual try-on for shoes and hats:**
|
|
19
|
+
* Supports virtual try-on for shoes, hats, and similar products. The service intelligently matches the product position and proportion based on the person\\"s pose and body parts, producing coordinated and lifelike wearing effects.
|
|
20
|
+
* - **E-commerce product display and marketing:**
|
|
21
|
+
* 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.
|
|
22
|
+
* - **Online shopping experience optimization:**
|
|
23
|
+
* Consumers can preview how products look when worn through virtual try-on, gaining a more intuitive understanding of the product\\"s style, coordination, and overall appearance, which assists purchase decisions and enhances the shopping experience.
|
|
24
|
+
* ## Features
|
|
25
|
+
* - **First, the user needs to provide a model image and a product image. The system uses the model image as the try-on subject and applies the clothing from the product image onto the model:**
|
|
26
|
+
* - a. Model image: The person image on which the virtual try-on is performed.
|
|
27
|
+
* - b. Product image: The clothing, shoes, or hat image to be applied onto the model.
|
|
28
|
+
* - **Second, the user can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
29
|
+
* - a. Specify product type: The user can directly specify the product type, and the system processes accordingly.
|
|
30
|
+
* - b. Automatic type recognition: If the user does not specify a product type, the system automatically identifies the product category from the product image and performs the virtual try-on based on the recognition result.
|
|
31
|
+
* - **Finally, the system combines the model image, product image, and product type to generate a virtual try-on image that showcases how the product looks on the model:**
|
|
32
|
+
* - a. Preserve model details: The generation process does not alter the person\\"s appearance, hairstyle, pose, body shape, or other details in the original model image.
|
|
33
|
+
* - b. Maintain scene 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.
|
|
34
|
+
* - c. Generate try-on results: The product is naturally applied onto the model, conforming to the person\\"s pose and body structure, producing a coordinated and realistic virtual try-on image.
|
|
35
|
+
* ## Sample results
|
|
36
|
+
* | **Type** | **Model image** | **Clothing image** | **Try-on result** |
|
|
37
|
+
* | --- | --- | --- | --- |
|
|
38
|
+
* | Tops |  |  |  |
|
|
39
|
+
* | Bottoms |  |  |  |
|
|
40
|
+
* | Shoes |  |  |  |
|
|
41
|
+
* | Jumpsuits |  |  |  |
|
|
42
|
+
* | Dresses |  |  |  |
|
|
43
|
+
* | Hats |  |  |  |
|
|
44
|
+
*
|
|
45
|
+
* @param request - AiTryOnRequest
|
|
46
|
+
* @param runtime - runtime options for this request RuntimeOptions
|
|
47
|
+
* @returns AiTryOnResponse
|
|
48
|
+
*/
|
|
49
|
+
aiTryOnWithOptions(request: $_model.AiTryOnRequest, runtime: $dara.RuntimeOptions): Promise<$_model.AiTryOnResponse>;
|
|
50
|
+
/**
|
|
51
|
+
* Virtual Try-On is an AI algorithm-based image generation API service that replaces the clothing on a model with the garment provided by the user based on the input garment image and model image, while preserving the model\\"s other details and scene details without altering the model\\"s pose, facial features, or other attributes, and achieving realistic and well-fitted clothing placement. Users only need to provide the URL of the original product image to obtain a processed clean image.
|
|
52
|
+
*
|
|
53
|
+
* @remarks
|
|
54
|
+
* ## Scenarios
|
|
55
|
+
* - **Virtual try-on for clothing products:**
|
|
56
|
+
* Supports multiple clothing categories including tops, bottoms, jumpsuits, and dresses. After uploading a person image and a product image, the service generates natural and realistic try-on results that intuitively showcase how the clothing looks when worn.
|
|
57
|
+
* - **Virtual try-on for shoes and hats:**
|
|
58
|
+
* Supports virtual try-on for shoes, hats, and similar products. The service intelligently matches the product position and proportion based on the person\\"s pose and body parts, producing coordinated and lifelike wearing effects.
|
|
59
|
+
* - **E-commerce product display and marketing:**
|
|
60
|
+
* 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.
|
|
61
|
+
* - **Online shopping experience optimization:**
|
|
62
|
+
* Consumers can preview how products look when worn through virtual try-on, gaining a more intuitive understanding of the product\\"s style, coordination, and overall appearance, which assists purchase decisions and enhances the shopping experience.
|
|
63
|
+
* ## Features
|
|
64
|
+
* - **First, the user needs to provide a model image and a product image. The system uses the model image as the try-on subject and applies the clothing from the product image onto the model:**
|
|
65
|
+
* - a. Model image: The person image on which the virtual try-on is performed.
|
|
66
|
+
* - b. Product image: The clothing, shoes, or hat image to be applied onto the model.
|
|
67
|
+
* - **Second, the user can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
68
|
+
* - a. Specify product type: The user can directly specify the product type, and the system processes accordingly.
|
|
69
|
+
* - b. Automatic type recognition: If the user does not specify a product type, the system automatically identifies the product category from the product image and performs the virtual try-on based on the recognition result.
|
|
70
|
+
* - **Finally, the system combines the model image, product image, and product type to generate a virtual try-on image that showcases how the product looks on the model:**
|
|
71
|
+
* - a. Preserve model details: The generation process does not alter the person\\"s appearance, hairstyle, pose, body shape, or other details in the original model image.
|
|
72
|
+
* - b. Maintain scene 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.
|
|
73
|
+
* - c. Generate try-on results: The product is naturally applied onto the model, conforming to the person\\"s pose and body structure, producing a coordinated and realistic virtual try-on image.
|
|
74
|
+
* ## Sample results
|
|
75
|
+
* | **Type** | **Model image** | **Clothing image** | **Try-on result** |
|
|
76
|
+
* | --- | --- | --- | --- |
|
|
77
|
+
* | Tops |  |  |  |
|
|
78
|
+
* | Bottoms |  |  |  |
|
|
79
|
+
* | Shoes |  |  |  |
|
|
80
|
+
* | Jumpsuits |  |  |  |
|
|
81
|
+
* | Dresses |  |  |  |
|
|
82
|
+
* | Hats |  |  |  |
|
|
83
|
+
*
|
|
84
|
+
* @param request - AiTryOnRequest
|
|
85
|
+
* @returns AiTryOnResponse
|
|
86
|
+
*/
|
|
87
|
+
aiTryOn(request: $_model.AiTryOnRequest): Promise<$_model.AiTryOnResponse>;
|
|
11
88
|
/**
|
|
12
89
|
* Provides a one-click cross-platform product listing optimization service for cross-border e-commerce sellers (minimum cost edition). Accepts a product link from a source platform and outputs all listing assets adapted to the target platform requirements, including titles, attributes, main images, SKU images, detail images, and copywriting. Uses an officially preset minimum-cost workflow that focuses on filtering and lightweight processing without calling expensive image translation capabilities, maximizing cost control while ensuring listing compliance. (Asynchronous)
|
|
13
90
|
*
|
|
@@ -278,25 +355,25 @@ export default class Client extends OpenApi {
|
|
|
278
355
|
*/
|
|
279
356
|
diduiAreaDeduction(request: $_model.DiduiAreaDeductionRequest): Promise<$_model.DiduiAreaDeductionResponse>;
|
|
280
357
|
/**
|
|
281
|
-
* Designed specifically for document translation. Supports translation between more than
|
|
358
|
+
* Designed specifically for document translation. Supports translation between more than 400 language pairs (including bridged pairs) to handle multi-scenario, multi-page, and highly complex document translation. Scanned documents are not currently supported.
|
|
282
359
|
* Excels in the following areas:
|
|
283
360
|
* - Content accuracy: translation accuracy, parameter and unit accuracy.
|
|
284
361
|
* - Structural integrity: overall layout continuity, page margin and layout restoration.
|
|
285
362
|
*
|
|
286
363
|
* @remarks
|
|
287
364
|
* ## Product Introduction
|
|
288
|
-
* Designed specifically for document translation. Supports translation between more than
|
|
365
|
+
* Designed specifically for document translation. Supports translation between more than 400 language pairs (including bridged pairs) to handle multi-scenario, multi-page, and highly complex document translation. Scanned documents are not currently supported.
|
|
289
366
|
* Excels in the following areas:
|
|
290
367
|
* - Content accuracy: translation accuracy, parameter and unit accuracy
|
|
291
368
|
* - Structural integrity: overall layout continuity, page margin and layout restoration
|
|
292
369
|
* ## Common scenarios
|
|
293
370
|
* Cross-border e-commerce product manuals, contracts, agreements, business proposals, qualification documents, textbooks and courseware, and many other scenarios.
|
|
294
|
-
* ##
|
|
371
|
+
* ## Functions and features
|
|
295
372
|
* - Supports PDF and Word formats. Supports source documents that contain multiple languages. For a detailed language list, see section 4.5.
|
|
296
373
|
* - Supports translation of text within images in documents, as well as complex translation scenarios such as charts and special symbols.
|
|
297
374
|
* - Supports high-fidelity layout restoration after translation.
|
|
298
375
|
* - A single PDF supports up to 100 pages. A single Word document supports up to 100 pages.
|
|
299
|
-
* - Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and skip translation (ABC-empty value). This is commonly used for
|
|
376
|
+
* - Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and skip translation (ABC-empty value). This is commonly used for brand name protection and similar scenarios. Simply pass the corresponding intervention glossary ID when calling the API to meet your translation needs across different scenarios. You can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance.
|
|
300
377
|
*
|
|
301
378
|
* @param request - DocumentTranslateRequest
|
|
302
379
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -304,25 +381,25 @@ export default class Client extends OpenApi {
|
|
|
304
381
|
*/
|
|
305
382
|
documentTranslateWithOptions(request: $_model.DocumentTranslateRequest, runtime: $dara.RuntimeOptions): Promise<$_model.DocumentTranslateResponse>;
|
|
306
383
|
/**
|
|
307
|
-
* Designed specifically for document translation. Supports translation between more than
|
|
384
|
+
* Designed specifically for document translation. Supports translation between more than 400 language pairs (including bridged pairs) to handle multi-scenario, multi-page, and highly complex document translation. Scanned documents are not currently supported.
|
|
308
385
|
* Excels in the following areas:
|
|
309
386
|
* - Content accuracy: translation accuracy, parameter and unit accuracy.
|
|
310
387
|
* - Structural integrity: overall layout continuity, page margin and layout restoration.
|
|
311
388
|
*
|
|
312
389
|
* @remarks
|
|
313
390
|
* ## Product Introduction
|
|
314
|
-
* Designed specifically for document translation. Supports translation between more than
|
|
391
|
+
* Designed specifically for document translation. Supports translation between more than 400 language pairs (including bridged pairs) to handle multi-scenario, multi-page, and highly complex document translation. Scanned documents are not currently supported.
|
|
315
392
|
* Excels in the following areas:
|
|
316
393
|
* - Content accuracy: translation accuracy, parameter and unit accuracy
|
|
317
394
|
* - Structural integrity: overall layout continuity, page margin and layout restoration
|
|
318
395
|
* ## Common scenarios
|
|
319
396
|
* Cross-border e-commerce product manuals, contracts, agreements, business proposals, qualification documents, textbooks and courseware, and many other scenarios.
|
|
320
|
-
* ##
|
|
397
|
+
* ## Functions and features
|
|
321
398
|
* - Supports PDF and Word formats. Supports source documents that contain multiple languages. For a detailed language list, see section 4.5.
|
|
322
399
|
* - Supports translation of text within images in documents, as well as complex translation scenarios such as charts and special symbols.
|
|
323
400
|
* - Supports high-fidelity layout restoration after translation.
|
|
324
401
|
* - A single PDF supports up to 100 pages. A single Word document supports up to 100 pages.
|
|
325
|
-
* - Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and skip translation (ABC-empty value). This is commonly used for
|
|
402
|
+
* - Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and skip translation (ABC-empty value). This is commonly used for brand name protection and similar scenarios. Simply pass the corresponding intervention glossary ID when calling the API to meet your translation needs across different scenarios. You can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance.
|
|
326
403
|
*
|
|
327
404
|
* @param request - DocumentTranslateRequest
|
|
328
405
|
* @returns DocumentTranslateResponse
|
|
@@ -506,16 +583,16 @@ export default class Client extends OpenApi {
|
|
|
506
583
|
*/
|
|
507
584
|
imageMatting(request: $_model.ImageMattingRequest): Promise<$_model.ImageMattingResponse>;
|
|
508
585
|
/**
|
|
509
|
-
*
|
|
586
|
+
* Intelligent element recognition.
|
|
510
587
|
*
|
|
511
588
|
* @remarks
|
|
512
589
|
* ## Product Introduction
|
|
513
|
-
* The Intelligent Element Recognition API is designed specifically for identifying specific elements in e-commerce images. It
|
|
590
|
+
* The Intelligent Element Recognition API is designed specifically for identifying specific elements in e-commerce images. It analyzes image details in depth, helping users quickly identify elements such as text, logos, watermarks, and text-containing color blocks in both the subject and background of images. This greatly improves the efficiency and accuracy of image screening. (Synchronous)
|
|
514
591
|
* ## Scenarios
|
|
515
592
|
* **1. Intelligent image screening and optimization:**
|
|
516
593
|
* Merchants and platforms can use the Intelligent Element Recognition API for image screening to automatically identify images that contain specific elements such as watermarks and logos. After screening, you can call the Intelligent Removal API to optimize these images, improve image quality, and shorten the product release cycle.
|
|
517
594
|
* **2. Automated image processing and efficiency improvement:**
|
|
518
|
-
*
|
|
595
|
+
* With the Intelligent Element Recognition API, merchants and platforms can automate the image processing workflow by automatically identifying and marking image elements that require optimization. This process reduces manual intervention and improves image processing efficiency.
|
|
519
596
|
* ## Features
|
|
520
597
|
* **1. Definitions of image subject, image background, text, logo, watermark, and text-containing color block: For details, see the related examples in the removal documentation (reserved text link)**
|
|
521
598
|
* * Image subject: The core product area in the image.
|
|
@@ -533,12 +610,12 @@ export default class Client extends OpenApi {
|
|
|
533
610
|
* **2. The main features of the Intelligent Element Recognition API include:**
|
|
534
611
|
* * Element recognition: Identifies whether elements such as text, logos, watermarks, and text-containing color blocks exist in the image subject and background.
|
|
535
612
|
*
|
|
536
|
-
* * Workflow coordination: Used in combination with the Intelligent Removal API. First,
|
|
613
|
+
* * Workflow coordination: Used in combination with the Intelligent Removal API. First, the Intelligent Element Recognition API identifies elements that need to be removed, and then the Intelligent Removal API removes them effectively, ensuring the accuracy and efficiency of image processing.
|
|
537
614
|
* ## Technical advantages
|
|
538
|
-
* * Synchronous batch processing: As a synchronous API, the Intelligent Element Recognition API can process a large number of images while maintaining fast response times, adapting to business
|
|
615
|
+
* * Synchronous batch processing: As a synchronous API, the Intelligent Element Recognition API can process a large number of images while maintaining fast response times, adapting to business needs of different scales.
|
|
539
616
|
*
|
|
540
|
-
* * Flexibility: Users can select the types of elements to identify
|
|
541
|
-
* ##
|
|
617
|
+
* * Flexibility: Users can select the types of elements to identify, including elements in both the subject and non-subject areas, such as watermarks, logos, and text, to meet personalized recognition needs.
|
|
618
|
+
* ## Comparison
|
|
542
619
|
* | **Original image** | **Recognition result** |
|
|
543
620
|
* | --- | --- |
|
|
544
621
|
* |  | [Subject]
|
|
@@ -582,16 +659,16 @@ export default class Client extends OpenApi {
|
|
|
582
659
|
*/
|
|
583
660
|
imageRecognitionWithOptions(tmpReq: $_model.ImageRecognitionRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageRecognitionResponse>;
|
|
584
661
|
/**
|
|
585
|
-
*
|
|
662
|
+
* Intelligent element recognition.
|
|
586
663
|
*
|
|
587
664
|
* @remarks
|
|
588
665
|
* ## Product Introduction
|
|
589
|
-
* The Intelligent Element Recognition API is designed specifically for identifying specific elements in e-commerce images. It
|
|
666
|
+
* The Intelligent Element Recognition API is designed specifically for identifying specific elements in e-commerce images. It analyzes image details in depth, helping users quickly identify elements such as text, logos, watermarks, and text-containing color blocks in both the subject and background of images. This greatly improves the efficiency and accuracy of image screening. (Synchronous)
|
|
590
667
|
* ## Scenarios
|
|
591
668
|
* **1. Intelligent image screening and optimization:**
|
|
592
669
|
* Merchants and platforms can use the Intelligent Element Recognition API for image screening to automatically identify images that contain specific elements such as watermarks and logos. After screening, you can call the Intelligent Removal API to optimize these images, improve image quality, and shorten the product release cycle.
|
|
593
670
|
* **2. Automated image processing and efficiency improvement:**
|
|
594
|
-
*
|
|
671
|
+
* With the Intelligent Element Recognition API, merchants and platforms can automate the image processing workflow by automatically identifying and marking image elements that require optimization. This process reduces manual intervention and improves image processing efficiency.
|
|
595
672
|
* ## Features
|
|
596
673
|
* **1. Definitions of image subject, image background, text, logo, watermark, and text-containing color block: For details, see the related examples in the removal documentation (reserved text link)**
|
|
597
674
|
* * Image subject: The core product area in the image.
|
|
@@ -609,12 +686,12 @@ export default class Client extends OpenApi {
|
|
|
609
686
|
* **2. The main features of the Intelligent Element Recognition API include:**
|
|
610
687
|
* * Element recognition: Identifies whether elements such as text, logos, watermarks, and text-containing color blocks exist in the image subject and background.
|
|
611
688
|
*
|
|
612
|
-
* * Workflow coordination: Used in combination with the Intelligent Removal API. First,
|
|
689
|
+
* * Workflow coordination: Used in combination with the Intelligent Removal API. First, the Intelligent Element Recognition API identifies elements that need to be removed, and then the Intelligent Removal API removes them effectively, ensuring the accuracy and efficiency of image processing.
|
|
613
690
|
* ## Technical advantages
|
|
614
|
-
* * Synchronous batch processing: As a synchronous API, the Intelligent Element Recognition API can process a large number of images while maintaining fast response times, adapting to business
|
|
691
|
+
* * Synchronous batch processing: As a synchronous API, the Intelligent Element Recognition API can process a large number of images while maintaining fast response times, adapting to business needs of different scales.
|
|
615
692
|
*
|
|
616
|
-
* * Flexibility: Users can select the types of elements to identify
|
|
617
|
-
* ##
|
|
693
|
+
* * Flexibility: Users can select the types of elements to identify, including elements in both the subject and non-subject areas, such as watermarks, logos, and text, to meet personalized recognition needs.
|
|
694
|
+
* ## Comparison
|
|
618
695
|
* | **Original image** | **Recognition result** |
|
|
619
696
|
* | --- | --- |
|
|
620
697
|
* |  | [Subject]
|
|
@@ -974,19 +1051,19 @@ export default class Client extends OpenApi {
|
|
|
974
1051
|
*/
|
|
975
1052
|
imageTranslationPlus(request: $_model.ImageTranslationPlusRequest): Promise<$_model.ImageTranslationPlusResponse>;
|
|
976
1053
|
/**
|
|
977
|
-
* Image Translation Pro is designed for e-commerce images. It integrates multimodal
|
|
1054
|
+
* Image Translation Pro is designed for e-commerce images. It integrates multimodal large model technology to achieve more accurate image understanding, significantly improve translation quality, and continuously expand and optimize multilingual translation capabilities. It supports more than 100 language directions (including bridged directions).
|
|
978
1055
|
*
|
|
979
1056
|
* @remarks
|
|
980
1057
|
* ## Product Introduction
|
|
981
|
-
* Image Translation Pro is designed for e-commerce images. It integrates multimodal
|
|
1058
|
+
* Image Translation Pro is designed for e-commerce images. It integrates multimodal large model technology to achieve more accurate image understanding, significantly improve translation quality, and continuously expand and optimize multilingual translation capabilities. It supports more than 400 language directions (including bridged directions).
|
|
982
1059
|
* ## Scenarios
|
|
983
1060
|
* E-commerce product images, marketing images, and images for various other scenarios.
|
|
984
1061
|
* ## Features
|
|
985
|
-
* - **Product subject protection**: Specify whether to translate text on the product subject. This helps protect subject information such as embedded product names
|
|
986
|
-
* - **Post-translation editing**: Specify whether to return layout information such as text position, font, and color. This
|
|
987
|
-
* - **Brand name protection**: Specify whether to translate brand names on images. This helps protect brand name information from being translated.
|
|
988
|
-
* - **Translation intervention**: Customize translation results, including do-not-translate (ABC→ABC), specified translation (ABC→DEF), and remove text (ABC→empty value). This is commonly used for brand name protection and similar scenarios. Pass the corresponding intervention glossary ID when calling the API to meet translation
|
|
989
|
-
* - **Image editor integration**: For more information, see [Image Translation Editor Protocol](https://www.alibabacloud.com/help/en/document_detail/3042647.html).
|
|
1062
|
+
* - **Product subject protection**: Specify whether to translate text on the product subject. This helps you protect subject information from being translated, such as embedded information like product names.
|
|
1063
|
+
* - **Post-translation editing**: Specify whether to return layout information such as text position, font, and color. This can be used for secondary editing when integrated with an image editor. The editor SDK is not yet available. Follow platform notifications for updates.
|
|
1064
|
+
* - **Brand name protection**: Specify whether to translate brand names on images. This helps you protect brand name information from being translated.
|
|
1065
|
+
* - **Translation intervention**: Customize translation results, including do-not-translate (ABC→ABC), specified translation (ABC→DEF), and remove text (ABC→empty value). This is commonly used for brand name protection and similar scenarios. Pass the corresponding intervention glossary ID when calling the API to meet your translation needs in different scenarios. You can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance.
|
|
1066
|
+
* - <props="china"> **Image editor integration**: For more information, see [Image Translation Editor Protocol](https://www.alibabacloud.com/help/en/document_detail/3042647.html).
|
|
990
1067
|
*
|
|
991
1068
|
* @param request - ImageTranslationProRequest
|
|
992
1069
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -994,19 +1071,19 @@ export default class Client extends OpenApi {
|
|
|
994
1071
|
*/
|
|
995
1072
|
imageTranslationProWithOptions(request: $_model.ImageTranslationProRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageTranslationProResponse>;
|
|
996
1073
|
/**
|
|
997
|
-
* Image Translation Pro is designed for e-commerce images. It integrates multimodal
|
|
1074
|
+
* Image Translation Pro is designed for e-commerce images. It integrates multimodal large model technology to achieve more accurate image understanding, significantly improve translation quality, and continuously expand and optimize multilingual translation capabilities. It supports more than 100 language directions (including bridged directions).
|
|
998
1075
|
*
|
|
999
1076
|
* @remarks
|
|
1000
1077
|
* ## Product Introduction
|
|
1001
|
-
* Image Translation Pro is designed for e-commerce images. It integrates multimodal
|
|
1078
|
+
* Image Translation Pro is designed for e-commerce images. It integrates multimodal large model technology to achieve more accurate image understanding, significantly improve translation quality, and continuously expand and optimize multilingual translation capabilities. It supports more than 400 language directions (including bridged directions).
|
|
1002
1079
|
* ## Scenarios
|
|
1003
1080
|
* E-commerce product images, marketing images, and images for various other scenarios.
|
|
1004
1081
|
* ## Features
|
|
1005
|
-
* - **Product subject protection**: Specify whether to translate text on the product subject. This helps protect subject information such as embedded product names
|
|
1006
|
-
* - **Post-translation editing**: Specify whether to return layout information such as text position, font, and color. This
|
|
1007
|
-
* - **Brand name protection**: Specify whether to translate brand names on images. This helps protect brand name information from being translated.
|
|
1008
|
-
* - **Translation intervention**: Customize translation results, including do-not-translate (ABC→ABC), specified translation (ABC→DEF), and remove text (ABC→empty value). This is commonly used for brand name protection and similar scenarios. Pass the corresponding intervention glossary ID when calling the API to meet translation
|
|
1009
|
-
* - **Image editor integration**: For more information, see [Image Translation Editor Protocol](https://www.alibabacloud.com/help/en/document_detail/3042647.html).
|
|
1082
|
+
* - **Product subject protection**: Specify whether to translate text on the product subject. This helps you protect subject information from being translated, such as embedded information like product names.
|
|
1083
|
+
* - **Post-translation editing**: Specify whether to return layout information such as text position, font, and color. This can be used for secondary editing when integrated with an image editor. The editor SDK is not yet available. Follow platform notifications for updates.
|
|
1084
|
+
* - **Brand name protection**: Specify whether to translate brand names on images. This helps you protect brand name information from being translated.
|
|
1085
|
+
* - **Translation intervention**: Customize translation results, including do-not-translate (ABC→ABC), specified translation (ABC→DEF), and remove text (ABC→empty value). This is commonly used for brand name protection and similar scenarios. Pass the corresponding intervention glossary ID when calling the API to meet your translation needs in different scenarios. You can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance.
|
|
1086
|
+
* - <props="china"> **Image editor integration**: For more information, see [Image Translation Editor Protocol](https://www.alibabacloud.com/help/en/document_detail/3042647.html).
|
|
1010
1087
|
*
|
|
1011
1088
|
* @param request - ImageTranslationProRequest
|
|
1012
1089
|
* @returns ImageTranslationProResponse
|
|
@@ -1236,28 +1313,28 @@ export default class Client extends OpenApi {
|
|
|
1236
1313
|
*/
|
|
1237
1314
|
packageWeightSizeCheck(request: $_model.PackageWeightSizeCheckRequest): Promise<$_model.PackageWeightSizeCheckResponse>;
|
|
1238
1315
|
/**
|
|
1239
|
-
*
|
|
1316
|
+
* Maas-MT is an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs, continuously optimized for e-commerce-specific terminology such as brands, models, materials, and attributes. It supports mutual translation among more than 400 language directions (including bridged translations), especially Chinese-English, Chinese-to-multilingual, and English-to-multilingual translations. It supports language detection for 24 language directions. If you do not specify a source language, automatic detection is performed.
|
|
1240
1317
|
*
|
|
1241
1318
|
* @remarks
|
|
1242
1319
|
* ## Product Introduction
|
|
1243
|
-
* Marco MT is an e-commerce translation model trained on over 1 billion\\+ high-quality bilingual sentence pairs, continuously optimized for e-commerce-specific terminology such as brands, models, materials, and attributes. It supports translation
|
|
1320
|
+
* Marco MT is an e-commerce translation model trained on over 1 billion\\+ high-quality bilingual sentence pairs, continuously optimized for e-commerce-specific terminology such as brands, models, materials, and attributes. It supports mutual translation among more than 100 language directions (including bridged translations), especially Chinese-English, Chinese-to-multilingual, and English-to-multilingual translations. It supports language detection for 24 language directions. If you do not specify a source language, automatic detection is performed.
|
|
1244
1321
|
* ## Common scenarios
|
|
1245
1322
|
* - Product titles: Marco MT large model translation accurately translates phrases, keywords, and trending terms in product titles into the target language, improving product visibility on e-commerce platforms.
|
|
1246
|
-
* - Product descriptions: Product descriptions are typically long with diverse and complex formatting. Marco large model translation supports long text translation and HTML
|
|
1247
|
-
* - Product attributes: Product attribute terms are short and may contain e-commerce-specific terms such as model numbers and
|
|
1323
|
+
* - Product descriptions: Product descriptions are typically long with diverse and complex formatting. Marco MT large model translation supports long text translation and HTML formatting, delivering excellent translation quality and format preservation.
|
|
1324
|
+
* - Product attributes: Product attribute terms are typically short and may contain e-commerce-specific terms such as model numbers and specifications.
|
|
1248
1325
|
* - Customer service conversations: In customer service scenarios, the model optimizes issues such as missing context and typos, and supports polite expressions for certain language directions.
|
|
1249
1326
|
* Marco MT large model translation can also be used for general-purpose translation scenarios, such as office work, meetings, and daily conversations.
|
|
1250
1327
|
* ## Features
|
|
1251
|
-
* - **Supported language directions** Marco MT large model translation supports translation
|
|
1252
|
-
* - **Ultra-low hallucination rate and high-speed inference** Marco MT large model translation is a large language model with preference alignment for translation scenarios. Compared with general-purpose large language models, it
|
|
1328
|
+
* - **Supported language directions** Marco MT large model translation supports mutual translation among more than 100 languages and language detection for 23 languages. For specific language directions, refer to the language mapping table in Section 5.6.
|
|
1329
|
+
* - **Ultra-low hallucination rate and high-speed inference** Marco MT large model translation is a large language model with preference alignment for translation scenarios. Compared with general-purpose large language models, it delivers faster translation inference and an extremely low hallucination rate, making it especially suitable for large-scale invocation scenarios.
|
|
1253
1330
|
* - **Supported text format types** Currently supports text and html text types.
|
|
1254
|
-
* - **Translation intervention support** Supports custom translation results, including do-not-translate (ABC
|
|
1331
|
+
* - **Translation intervention support** Supports custom translation results, including do-not-translate (ABC→ABC), specified translation (ABC→DEF), and skip translation (ABC→empty value). This is commonly used for scenarios such as brand name protection. Simply pass the corresponding intervention glossary ID when calling the API to meet your translation needs across different scenarios. You can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance.
|
|
1255
1332
|
* ## Translation quality comparison
|
|
1256
1333
|
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation advantage** |
|
|
1257
1334
|
* |----------|---------------|-----------------------|-----------------------|---------------------|
|
|
1258
1335
|
* | 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 |
|
|
1259
1336
|
* | 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 segmentation |
|
|
1260
|
-
* | 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
|
|
1337
|
+
* | 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 accurate product subject description — correctly identifies "key bag" rather than "keychain." Other translations may cause ambiguity about the product subject |
|
|
1261
1338
|
*
|
|
1262
1339
|
* @param tmpReq - PrepaidTextTranslateRequest
|
|
1263
1340
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -1265,28 +1342,28 @@ export default class Client extends OpenApi {
|
|
|
1265
1342
|
*/
|
|
1266
1343
|
prepaidTextTranslateWithOptions(tmpReq: $_model.PrepaidTextTranslateRequest, runtime: $dara.RuntimeOptions): Promise<$_model.PrepaidTextTranslateResponse>;
|
|
1267
1344
|
/**
|
|
1268
|
-
*
|
|
1345
|
+
* Maas-MT is an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs, continuously optimized for e-commerce-specific terminology such as brands, models, materials, and attributes. It supports mutual translation among more than 400 language directions (including bridged translations), especially Chinese-English, Chinese-to-multilingual, and English-to-multilingual translations. It supports language detection for 24 language directions. If you do not specify a source language, automatic detection is performed.
|
|
1269
1346
|
*
|
|
1270
1347
|
* @remarks
|
|
1271
1348
|
* ## Product Introduction
|
|
1272
|
-
* Marco MT is an e-commerce translation model trained on over 1 billion\\+ high-quality bilingual sentence pairs, continuously optimized for e-commerce-specific terminology such as brands, models, materials, and attributes. It supports translation
|
|
1349
|
+
* Marco MT is an e-commerce translation model trained on over 1 billion\\+ high-quality bilingual sentence pairs, continuously optimized for e-commerce-specific terminology such as brands, models, materials, and attributes. It supports mutual translation among more than 100 language directions (including bridged translations), especially Chinese-English, Chinese-to-multilingual, and English-to-multilingual translations. It supports language detection for 24 language directions. If you do not specify a source language, automatic detection is performed.
|
|
1273
1350
|
* ## Common scenarios
|
|
1274
1351
|
* - Product titles: Marco MT large model translation accurately translates phrases, keywords, and trending terms in product titles into the target language, improving product visibility on e-commerce platforms.
|
|
1275
|
-
* - Product descriptions: Product descriptions are typically long with diverse and complex formatting. Marco large model translation supports long text translation and HTML
|
|
1276
|
-
* - Product attributes: Product attribute terms are short and may contain e-commerce-specific terms such as model numbers and
|
|
1352
|
+
* - Product descriptions: Product descriptions are typically long with diverse and complex formatting. Marco MT large model translation supports long text translation and HTML formatting, delivering excellent translation quality and format preservation.
|
|
1353
|
+
* - Product attributes: Product attribute terms are typically short and may contain e-commerce-specific terms such as model numbers and specifications.
|
|
1277
1354
|
* - Customer service conversations: In customer service scenarios, the model optimizes issues such as missing context and typos, and supports polite expressions for certain language directions.
|
|
1278
1355
|
* Marco MT large model translation can also be used for general-purpose translation scenarios, such as office work, meetings, and daily conversations.
|
|
1279
1356
|
* ## Features
|
|
1280
|
-
* - **Supported language directions** Marco MT large model translation supports translation
|
|
1281
|
-
* - **Ultra-low hallucination rate and high-speed inference** Marco MT large model translation is a large language model with preference alignment for translation scenarios. Compared with general-purpose large language models, it
|
|
1357
|
+
* - **Supported language directions** Marco MT large model translation supports mutual translation among more than 100 languages and language detection for 23 languages. For specific language directions, refer to the language mapping table in Section 5.6.
|
|
1358
|
+
* - **Ultra-low hallucination rate and high-speed inference** Marco MT large model translation is a large language model with preference alignment for translation scenarios. Compared with general-purpose large language models, it delivers faster translation inference and an extremely low hallucination rate, making it especially suitable for large-scale invocation scenarios.
|
|
1282
1359
|
* - **Supported text format types** Currently supports text and html text types.
|
|
1283
|
-
* - **Translation intervention support** Supports custom translation results, including do-not-translate (ABC
|
|
1360
|
+
* - **Translation intervention support** Supports custom translation results, including do-not-translate (ABC→ABC), specified translation (ABC→DEF), and skip translation (ABC→empty value). This is commonly used for scenarios such as brand name protection. Simply pass the corresponding intervention glossary ID when calling the API to meet your translation needs across different scenarios. You can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance.
|
|
1284
1361
|
* ## Translation quality comparison
|
|
1285
1362
|
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation advantage** |
|
|
1286
1363
|
* |----------|---------------|-----------------------|-----------------------|---------------------|
|
|
1287
1364
|
* | 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 |
|
|
1288
1365
|
* | 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 segmentation |
|
|
1289
|
-
* | 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
|
|
1366
|
+
* | 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 accurate product subject description — correctly identifies "key bag" rather than "keychain." Other translations may cause ambiguity about the product subject |
|
|
1290
1367
|
*
|
|
1291
1368
|
* @param request - PrepaidTextTranslateRequest
|
|
1292
1369
|
* @returns PrepaidTextTranslateResponse
|
|
@@ -1394,19 +1471,19 @@ export default class Client extends OpenApi {
|
|
|
1394
1471
|
*/
|
|
1395
1472
|
sizeChartDetect(request: $_model.SizeChartDetectRequest): Promise<$_model.SizeChartDetectResponse>;
|
|
1396
1473
|
/**
|
|
1397
|
-
* Intelligently extracts structured information such as size charts and package weight/
|
|
1474
|
+
* Intelligently extracts structured information such as size charts and package weight/dimension data from images by using a multimodal large language model. (Asynchronous)
|
|
1398
1475
|
*
|
|
1399
1476
|
* @remarks
|
|
1400
1477
|
* ## Product Introduction
|
|
1401
|
-
* Intelligently extracts structured information such as size charts and package weight/
|
|
1478
|
+
* Intelligently extracts structured information such as size charts and package weight/dimension data from images by using a multimodal large language model. (Asynchronous)
|
|
1402
1479
|
* ## Common scenarios
|
|
1403
1480
|
* * Size chart: Extracts size charts from apparel category images into text.
|
|
1404
1481
|
*
|
|
1405
1482
|
* * Package weight/dimensions: Extracts package weight and dimension information from images.
|
|
1406
1483
|
* ## Functions and features
|
|
1407
|
-
* The size chart extraction service is based on a multimodal
|
|
1408
|
-
* Core
|
|
1409
|
-
* ##
|
|
1484
|
+
* The size chart extraction service is based on a multimodal large language model. It automatically recognizes size chart or package weight/dimension information in images and converts it 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 use the ColumnNameList parameter to specify the column names to recognize (such as Size, Bust, and Length) for precise targeted extraction. You can also use the LanguageModel parameter to control the output language. Valid values: cn (Chinese) and en (English). If you leave this parameter empty, the original language is retained. This service is applicable to scenarios such as converting apparel size charts to text and batch structuring of product weight/dimension information.
|
|
1485
|
+
* Core capability: Provide an image URL and optional column name configurations as input, and receive structured data of size charts or package weight/dimensions from the image as output. The API uses an asynchronous task mode (background: true). After submission, a task ID is returned. Poll for the final result. This mode is suitable for processing complex images or high-volume call scenarios.
|
|
1486
|
+
* ## Comparison
|
|
1410
1487
|
* | **Input image** | **Output result** |
|
|
1411
1488
|
* | --- | --- |
|
|
1412
1489
|
* |  | {
|
|
@@ -1522,19 +1599,19 @@ export default class Client extends OpenApi {
|
|
|
1522
1599
|
*/
|
|
1523
1600
|
sizeChartExtractWithOptions(tmpReq: $_model.SizeChartExtractRequest, runtime: $dara.RuntimeOptions): Promise<$_model.SizeChartExtractResponse>;
|
|
1524
1601
|
/**
|
|
1525
|
-
* Intelligently extracts structured information such as size charts and package weight/
|
|
1602
|
+
* Intelligently extracts structured information such as size charts and package weight/dimension data from images by using a multimodal large language model. (Asynchronous)
|
|
1526
1603
|
*
|
|
1527
1604
|
* @remarks
|
|
1528
1605
|
* ## Product Introduction
|
|
1529
|
-
* Intelligently extracts structured information such as size charts and package weight/
|
|
1606
|
+
* Intelligently extracts structured information such as size charts and package weight/dimension data from images by using a multimodal large language model. (Asynchronous)
|
|
1530
1607
|
* ## Common scenarios
|
|
1531
1608
|
* * Size chart: Extracts size charts from apparel category images into text.
|
|
1532
1609
|
*
|
|
1533
1610
|
* * Package weight/dimensions: Extracts package weight and dimension information from images.
|
|
1534
1611
|
* ## Functions and features
|
|
1535
|
-
* The size chart extraction service is based on a multimodal
|
|
1536
|
-
* Core
|
|
1537
|
-
* ##
|
|
1612
|
+
* The size chart extraction service is based on a multimodal large language model. It automatically recognizes size chart or package weight/dimension information in images and converts it 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 use the ColumnNameList parameter to specify the column names to recognize (such as Size, Bust, and Length) for precise targeted extraction. You can also use the LanguageModel parameter to control the output language. Valid values: cn (Chinese) and en (English). If you leave this parameter empty, the original language is retained. This service is applicable to scenarios such as converting apparel size charts to text and batch structuring of product weight/dimension information.
|
|
1613
|
+
* Core capability: Provide an image URL and optional column name configurations as input, and receive structured data of size charts or package weight/dimensions from the image as output. The API uses an asynchronous task mode (background: true). After submission, a task ID is returned. Poll for the final result. This mode is suitable for processing complex images or high-volume call scenarios.
|
|
1614
|
+
* ## Comparison
|
|
1538
1615
|
* | **Input image** | **Output result** |
|
|
1539
1616
|
* | --- | --- |
|
|
1540
1617
|
* |  | {
|
|
@@ -1719,32 +1796,32 @@ export default class Client extends OpenApi {
|
|
|
1719
1796
|
*/
|
|
1720
1797
|
textCorrect(request: $_model.TextCorrectRequest): Promise<$_model.TextCorrectResponse>;
|
|
1721
1798
|
/**
|
|
1722
|
-
*
|
|
1799
|
+
* Maas-MT is an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs, continuously optimized for e-commerce-specific terminology such as brands, models, materials, and attributes. It supports mutual translation among more than 100 language directions (including bridged directions), especially Chinese-English, Chinese-multilingual, and English-multilingual translation. It supports language detection for 24 language directions. If you do not specify a source language, automatic detection is performed.
|
|
1723
1800
|
*
|
|
1724
1801
|
* @remarks
|
|
1725
1802
|
* ## Product Introduction
|
|
1726
|
-
* Marco MT is an e-commerce translation model trained on over 1 billion
|
|
1803
|
+
* Marco MT is an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs, continuously optimized for e-commerce-specific terminology such as brands, models, materials, and attributes. It supports mutual translation among more than 100 language directions (including bridged directions), especially Chinese-English, Chinese-multilingual, and English-multilingual translation. It supports language detection for 24 language directions. If you do not specify a source language, automatic detection is performed.
|
|
1727
1804
|
* ## Common scenarios
|
|
1728
|
-
* - Product titles
|
|
1729
|
-
* - Product descriptions
|
|
1730
|
-
* - Product attributes
|
|
1731
|
-
* - Customer service conversations
|
|
1732
|
-
* Marco MT
|
|
1733
|
-
* ##
|
|
1805
|
+
* - **Product titles**: Marco MT can accurately translate phrases, keywords, and trending terms in product titles into the target language, improving product visibility on e-commerce platforms.
|
|
1806
|
+
* - **Product descriptions**: Product descriptions are typically long with diverse and complex formatting. Marco MT supports long text translation and HTML format, delivering excellent translation quality and format preservation.
|
|
1807
|
+
* - **Product attributes**: Product attribute terms are typically short and may contain e-commerce-specific terms such as model numbers and specifications.
|
|
1808
|
+
* - **Customer service conversations**: In customer service scenarios, Marco MT can handle issues such as missing context and typos, and supports polite expressions for certain language directions.
|
|
1809
|
+
* Marco MT can also be used for general translation scenarios such as office work, meetings, and daily conversations.
|
|
1810
|
+
* ## Functions and features
|
|
1734
1811
|
* - **Supported language directions**
|
|
1735
|
-
* Marco MT
|
|
1812
|
+
* Marco MT supports mutual translation among more than 100 languages and language detection for 24 languages. For supported language directions, see [Language direction mapping table](https://www.alibabacloud.com/help/en/document_detail/3041883.html).
|
|
1736
1813
|
* - **Ultra-low hallucination rate and high-speed inference**
|
|
1737
|
-
* Marco MT
|
|
1814
|
+
* Marco MT is a large language model with preference alignment for translation scenarios. Compared with general-purpose large language models, it delivers faster translation inference and an extremely low hallucination rate, making it especially suitable for large-scale invocation scenarios.
|
|
1738
1815
|
* - **Supported text format types**
|
|
1739
|
-
* Currently
|
|
1740
|
-
* - **Translation intervention
|
|
1741
|
-
*
|
|
1816
|
+
* Currently supports text and html text types.
|
|
1817
|
+
* - **Translation intervention**
|
|
1818
|
+
* Supports custom translation results, including do-not-translate (ABC→ABC), specified translation (ABC→DEF), and skip translation (ABC→empty value). This is commonly used for scenarios such as brand name protection. Simply pass the corresponding intervention glossary ID when calling the API to meet your translation needs across different scenarios. You can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance.
|
|
1742
1819
|
* ## Translation quality comparison
|
|
1743
1820
|
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation advantage** |
|
|
1744
1821
|
* |----------|---------------|-----------------------|-----------------------|---------------------|
|
|
1745
1822
|
* | 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 |
|
|
1746
1823
|
* | 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 segmentation |
|
|
1747
|
-
* | 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 accurate product subject expression
|
|
1824
|
+
* | 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 accurate product subject expression — correctly identifies "key bag" rather than "keychain," avoiding ambiguity about the product |
|
|
1748
1825
|
*
|
|
1749
1826
|
* @param tmpReq - TextTranslateRequest
|
|
1750
1827
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -1752,32 +1829,32 @@ export default class Client extends OpenApi {
|
|
|
1752
1829
|
*/
|
|
1753
1830
|
textTranslateWithOptions(tmpReq: $_model.TextTranslateRequest, runtime: $dara.RuntimeOptions): Promise<$_model.TextTranslateResponse>;
|
|
1754
1831
|
/**
|
|
1755
|
-
*
|
|
1832
|
+
* Maas-MT is an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs, continuously optimized for e-commerce-specific terminology such as brands, models, materials, and attributes. It supports mutual translation among more than 100 language directions (including bridged directions), especially Chinese-English, Chinese-multilingual, and English-multilingual translation. It supports language detection for 24 language directions. If you do not specify a source language, automatic detection is performed.
|
|
1756
1833
|
*
|
|
1757
1834
|
* @remarks
|
|
1758
1835
|
* ## Product Introduction
|
|
1759
|
-
* Marco MT is an e-commerce translation model trained on over 1 billion
|
|
1836
|
+
* Marco MT is an e-commerce translation model trained on over 1 billion high-quality bilingual sentence pairs, continuously optimized for e-commerce-specific terminology such as brands, models, materials, and attributes. It supports mutual translation among more than 100 language directions (including bridged directions), especially Chinese-English, Chinese-multilingual, and English-multilingual translation. It supports language detection for 24 language directions. If you do not specify a source language, automatic detection is performed.
|
|
1760
1837
|
* ## Common scenarios
|
|
1761
|
-
* - Product titles
|
|
1762
|
-
* - Product descriptions
|
|
1763
|
-
* - Product attributes
|
|
1764
|
-
* - Customer service conversations
|
|
1765
|
-
* Marco MT
|
|
1766
|
-
* ##
|
|
1838
|
+
* - **Product titles**: Marco MT can accurately translate phrases, keywords, and trending terms in product titles into the target language, improving product visibility on e-commerce platforms.
|
|
1839
|
+
* - **Product descriptions**: Product descriptions are typically long with diverse and complex formatting. Marco MT supports long text translation and HTML format, delivering excellent translation quality and format preservation.
|
|
1840
|
+
* - **Product attributes**: Product attribute terms are typically short and may contain e-commerce-specific terms such as model numbers and specifications.
|
|
1841
|
+
* - **Customer service conversations**: In customer service scenarios, Marco MT can handle issues such as missing context and typos, and supports polite expressions for certain language directions.
|
|
1842
|
+
* Marco MT can also be used for general translation scenarios such as office work, meetings, and daily conversations.
|
|
1843
|
+
* ## Functions and features
|
|
1767
1844
|
* - **Supported language directions**
|
|
1768
|
-
* Marco MT
|
|
1845
|
+
* Marco MT supports mutual translation among more than 100 languages and language detection for 24 languages. For supported language directions, see [Language direction mapping table](https://www.alibabacloud.com/help/en/document_detail/3041883.html).
|
|
1769
1846
|
* - **Ultra-low hallucination rate and high-speed inference**
|
|
1770
|
-
* Marco MT
|
|
1847
|
+
* Marco MT is a large language model with preference alignment for translation scenarios. Compared with general-purpose large language models, it delivers faster translation inference and an extremely low hallucination rate, making it especially suitable for large-scale invocation scenarios.
|
|
1771
1848
|
* - **Supported text format types**
|
|
1772
|
-
* Currently
|
|
1773
|
-
* - **Translation intervention
|
|
1774
|
-
*
|
|
1849
|
+
* Currently supports text and html text types.
|
|
1850
|
+
* - **Translation intervention**
|
|
1851
|
+
* Supports custom translation results, including do-not-translate (ABC→ABC), specified translation (ABC→DEF), and skip translation (ABC→empty value). This is commonly used for scenarios such as brand name protection. Simply pass the corresponding intervention glossary ID when calling the API to meet your translation needs across different scenarios. You can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance.
|
|
1775
1852
|
* ## Translation quality comparison
|
|
1776
1853
|
* | **Source text** | **Aidge translation** | **Other translation product 1** | **Other translation product 2** | **Aidge translation advantage** |
|
|
1777
1854
|
* |----------|---------------|-----------------------|-----------------------|---------------------|
|
|
1778
1855
|
* | 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 |
|
|
1779
1856
|
* | 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 segmentation |
|
|
1780
|
-
* | 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 accurate product subject expression
|
|
1857
|
+
* | 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 accurate product subject expression — correctly identifies "key bag" rather than "keychain," avoiding ambiguity about the product |
|
|
1781
1858
|
*
|
|
1782
1859
|
* @param request - TextTranslateRequest
|
|
1783
1860
|
* @returns TextTranslateResponse
|
|
@@ -1848,9 +1925,9 @@ export default class Client extends OpenApi {
|
|
|
1848
1925
|
*
|
|
1849
1926
|
* * **Global brand advertising**: Automatically generates video versions in the language of the target region to reduce manual production costs.
|
|
1850
1927
|
*
|
|
1851
|
-
* * **Training and product
|
|
1928
|
+
* * **Training and product instructions**: Translates on-screen text in training courses or product demonstration videos into multiple languages for use by global teams.
|
|
1852
1929
|
* ## 3. Features
|
|
1853
|
-
* |
|
|
1930
|
+
* | Feature | Identifier | Description |
|
|
1854
1931
|
* | --- | --- | --- |
|
|
1855
1932
|
* | Visual translation | `visual` | Translates embedded text (subtitles, promotional text, etc.) in video frames into the target language and erases the original text. |
|
|
1856
1933
|
* ## 4. Developer guide.
|
|
@@ -1877,9 +1954,9 @@ export default class Client extends OpenApi {
|
|
|
1877
1954
|
*
|
|
1878
1955
|
* * **Global brand advertising**: Automatically generates video versions in the language of the target region to reduce manual production costs.
|
|
1879
1956
|
*
|
|
1880
|
-
* * **Training and product
|
|
1957
|
+
* * **Training and product instructions**: Translates on-screen text in training courses or product demonstration videos into multiple languages for use by global teams.
|
|
1881
1958
|
* ## 3. Features
|
|
1882
|
-
* |
|
|
1959
|
+
* | Feature | Identifier | Description |
|
|
1883
1960
|
* | --- | --- | --- |
|
|
1884
1961
|
* | Visual translation | `visual` | Translates embedded text (subtitles, promotional text, etc.) in video frames into the target language and erases the original text. |
|
|
1885
1962
|
* ## 4. Developer guide.
|
|
@@ -1892,29 +1969,29 @@ export default class Client extends OpenApi {
|
|
|
1892
1969
|
*/
|
|
1893
1970
|
videoTranslation(request: $_model.VideoTranslationRequest): Promise<$_model.VideoTranslationResponse>;
|
|
1894
1971
|
/**
|
|
1895
|
-
* Generates virtual try-on images based on AI algorithms. This API service replaces the clothing on a model with the specified garment based on the input garment image and model image, while preserving the model\\"s appearance details, pose, facial features, and scene details to
|
|
1972
|
+
* Generates virtual try-on images based on AI algorithms. This API service replaces the clothing on a model with the specified garment based on the input garment image and model image, while preserving the model\\"s appearance details, pose, facial features, and scene details to produce realistic and well-fitted try-on results. You only need to provide the URL of the original product image to obtain a processed clean image.
|
|
1896
1973
|
*
|
|
1897
1974
|
* @remarks
|
|
1898
1975
|
* ## Scenarios
|
|
1899
1976
|
* - **Virtual try-on for clothing products:**
|
|
1900
|
-
* Supports multiple clothing categories such as tops, bottoms, jumpsuits, and
|
|
1977
|
+
* Supports multiple clothing categories such as tops, bottoms, jumpsuits, and dresses. After uploading a model image and a product image, the system generates a natural and realistic try-on effect that visually demonstrates how the garment looks when worn.
|
|
1901
1978
|
* - **Virtual try-on for shoes and hats:**
|
|
1902
|
-
* Supports virtual try-on for shoes, hats, and similar products. The system intelligently matches the product position and proportion based on the model\\"s pose and body parts
|
|
1979
|
+
* Supports virtual try-on for shoes, hats, and similar products. The system intelligently matches the product position and proportion based on the model\\"s pose and body parts to produce a coordinated and realistic wearing effect.
|
|
1903
1980
|
* - **E-commerce product display and marketing:**
|
|
1904
|
-
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional photography, outfit changes, and post-production
|
|
1981
|
+
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional photography, outfit changes, and post-production while improving the production efficiency of product images.
|
|
1905
1982
|
* - **Online shopping experience optimization:**
|
|
1906
|
-
* Consumers can preview how products look when worn through virtual try-on, gaining a more intuitive understanding of the style, coordination, and overall effect of products
|
|
1983
|
+
* Consumers can preview how products look when worn through virtual try-on, gaining a more intuitive understanding of the style, coordination, and overall effect of products to support purchasing decisions and enhance the shopping experience.
|
|
1907
1984
|
* ## Features
|
|
1908
|
-
* - **First,
|
|
1909
|
-
* - a. Model image: the image of the person for
|
|
1985
|
+
* - **First, provide 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 onto the model:**
|
|
1986
|
+
* - a. Model image: the image of the person for virtual try-on.
|
|
1910
1987
|
* - b. Product image: the image of the clothing, shoes, or hat to be applied onto the model.
|
|
1911
|
-
* - **Second,
|
|
1912
|
-
* - a.
|
|
1913
|
-
* - b. Automatic type recognition: if
|
|
1988
|
+
* - **Second, select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
1989
|
+
* - a. Specify product type: directly specify the product type, and the system processes accordingly.
|
|
1990
|
+
* - b. Automatic type recognition: if no product type is specified, the system automatically identifies the product category from the product image and performs the virtual try-on based on the recognition result.
|
|
1914
1991
|
* - **Finally, the system combines the model image, product image, and product type to generate a virtual try-on image that shows how the product looks on the model:**
|
|
1915
|
-
* - a.
|
|
1916
|
-
* - b.
|
|
1917
|
-
* - c.
|
|
1992
|
+
* - a. Preserve model details: the generation process does not alter the model\\"s appearance, hairstyle, pose, body shape, or other details from the original model image.
|
|
1993
|
+
* - b. Maintain scene 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.
|
|
1994
|
+
* - c. Generate try-on effect: the product is naturally applied onto the model, conforming to the model\\"s pose and body structure, to produce a coordinated and realistic virtual try-on image.
|
|
1918
1995
|
* ## Sample results
|
|
1919
1996
|
* | **Type** | **Model image** | **Garment image** | **Try-on result** |
|
|
1920
1997
|
* | --- | --- | --- | --- |
|
|
@@ -1922,7 +1999,7 @@ export default class Client extends OpenApi {
|
|
|
1922
1999
|
* | Bottoms |  |  |  |
|
|
1923
2000
|
* | Shoes |  |  |  |
|
|
1924
2001
|
* | Jumpsuits |  |  |  |
|
|
1925
|
-
* |
|
|
2002
|
+
* | Dresses |  |  |  |
|
|
1926
2003
|
* | Hats |  |  |  |
|
|
1927
2004
|
*
|
|
1928
2005
|
* @param request - VirtualTryOnRequest
|
|
@@ -1931,29 +2008,29 @@ export default class Client extends OpenApi {
|
|
|
1931
2008
|
*/
|
|
1932
2009
|
virtualTryOnWithOptions(request: $_model.VirtualTryOnRequest, runtime: $dara.RuntimeOptions): Promise<$_model.VirtualTryOnResponse>;
|
|
1933
2010
|
/**
|
|
1934
|
-
* Generates virtual try-on images based on AI algorithms. This API service replaces the clothing on a model with the specified garment based on the input garment image and model image, while preserving the model\\"s appearance details, pose, facial features, and scene details to
|
|
2011
|
+
* Generates virtual try-on images based on AI algorithms. This API service replaces the clothing on a model with the specified garment based on the input garment image and model image, while preserving the model\\"s appearance details, pose, facial features, and scene details to produce realistic and well-fitted try-on results. You only need to provide the URL of the original product image to obtain a processed clean image.
|
|
1935
2012
|
*
|
|
1936
2013
|
* @remarks
|
|
1937
2014
|
* ## Scenarios
|
|
1938
2015
|
* - **Virtual try-on for clothing products:**
|
|
1939
|
-
* Supports multiple clothing categories such as tops, bottoms, jumpsuits, and
|
|
2016
|
+
* Supports multiple clothing categories such as tops, bottoms, jumpsuits, and dresses. After uploading a model image and a product image, the system generates a natural and realistic try-on effect that visually demonstrates how the garment looks when worn.
|
|
1940
2017
|
* - **Virtual try-on for shoes and hats:**
|
|
1941
|
-
* Supports virtual try-on for shoes, hats, and similar products. The system intelligently matches the product position and proportion based on the model\\"s pose and body parts
|
|
2018
|
+
* Supports virtual try-on for shoes, hats, and similar products. The system intelligently matches the product position and proportion based on the model\\"s pose and body parts to produce a coordinated and realistic wearing effect.
|
|
1942
2019
|
* - **E-commerce product display and marketing:**
|
|
1943
|
-
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional photography, outfit changes, and post-production
|
|
2020
|
+
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional photography, outfit changes, and post-production while improving the production efficiency of product images.
|
|
1944
2021
|
* - **Online shopping experience optimization:**
|
|
1945
|
-
* Consumers can preview how products look when worn through virtual try-on, gaining a more intuitive understanding of the style, coordination, and overall effect of products
|
|
2022
|
+
* Consumers can preview how products look when worn through virtual try-on, gaining a more intuitive understanding of the style, coordination, and overall effect of products to support purchasing decisions and enhance the shopping experience.
|
|
1946
2023
|
* ## Features
|
|
1947
|
-
* - **First,
|
|
1948
|
-
* - a. Model image: the image of the person for
|
|
2024
|
+
* - **First, provide 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 onto the model:**
|
|
2025
|
+
* - a. Model image: the image of the person for virtual try-on.
|
|
1949
2026
|
* - b. Product image: the image of the clothing, shoes, or hat to be applied onto the model.
|
|
1950
|
-
* - **Second,
|
|
1951
|
-
* - a.
|
|
1952
|
-
* - b. Automatic type recognition: if
|
|
2027
|
+
* - **Second, select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
2028
|
+
* - a. Specify product type: directly specify the product type, and the system processes accordingly.
|
|
2029
|
+
* - b. Automatic type recognition: if no product type is specified, the system automatically identifies the product category from the product image and performs the virtual try-on based on the recognition result.
|
|
1953
2030
|
* - **Finally, the system combines the model image, product image, and product type to generate a virtual try-on image that shows how the product looks on the model:**
|
|
1954
|
-
* - a.
|
|
1955
|
-
* - b.
|
|
1956
|
-
* - c.
|
|
2031
|
+
* - a. Preserve model details: the generation process does not alter the model\\"s appearance, hairstyle, pose, body shape, or other details from the original model image.
|
|
2032
|
+
* - b. Maintain scene 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.
|
|
2033
|
+
* - c. Generate try-on effect: the product is naturally applied onto the model, conforming to the model\\"s pose and body structure, to produce a coordinated and realistic virtual try-on image.
|
|
1957
2034
|
* ## Sample results
|
|
1958
2035
|
* | **Type** | **Model image** | **Garment image** | **Try-on result** |
|
|
1959
2036
|
* | --- | --- | --- | --- |
|
|
@@ -1961,7 +2038,7 @@ export default class Client extends OpenApi {
|
|
|
1961
2038
|
* | Bottoms |  |  |  |
|
|
1962
2039
|
* | Shoes |  |  |  |
|
|
1963
2040
|
* | Jumpsuits |  |  |  |
|
|
1964
|
-
* |
|
|
2041
|
+
* | Dresses |  |  |  |
|
|
1965
2042
|
* | Hats |  |  |  |
|
|
1966
2043
|
*
|
|
1967
2044
|
* @param request - VirtualTryOnRequest
|