@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/dist/client.d.ts
CHANGED
|
@@ -24,38 +24,38 @@ export default class Client extends OpenApi {
|
|
|
24
24
|
*/
|
|
25
25
|
addDisplayKnowledge(request: $_model.AddDisplayKnowledgeRequest): Promise<$_model.AddDisplayKnowledgeResponse>;
|
|
26
26
|
/**
|
|
27
|
-
* Generates
|
|
27
|
+
* 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.
|
|
28
28
|
*
|
|
29
29
|
* @remarks
|
|
30
30
|
* ## Scenarios
|
|
31
31
|
* - **Virtual try-on for clothing:**
|
|
32
|
-
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After
|
|
32
|
+
* 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.
|
|
33
33
|
* - **Virtual try-on for shoes and hats:**
|
|
34
|
-
* Supports virtual try-on for products such as shoes and hats.
|
|
34
|
+
* 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.
|
|
35
35
|
* - **E-commerce product display and marketing:**
|
|
36
36
|
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional photography, outfit changes, and post-production, and improving the production efficiency of product images.
|
|
37
37
|
* - **Online shopping experience optimization:**
|
|
38
|
-
*
|
|
38
|
+
* 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.
|
|
39
39
|
* ## Features
|
|
40
|
-
* - **First,
|
|
41
|
-
* - a. Model image:
|
|
42
|
-
* - b. Product image:
|
|
43
|
-
* - **Second,
|
|
44
|
-
* - a. Specify product type:
|
|
45
|
-
* - b. Automatic type recognition:
|
|
46
|
-
* - **Finally, the system
|
|
47
|
-
* - a. Preserve model details:
|
|
48
|
-
* - b. Maintain image consistency:
|
|
49
|
-
* - c. Generate try-on effect:
|
|
40
|
+
* - **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:**
|
|
41
|
+
* - a. Model image: the image of the person who needs to perform the virtual try-on.
|
|
42
|
+
* - b. Product image: the image of the clothing, shoes, or hat to be worn by the model.
|
|
43
|
+
* - **Second, users can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
44
|
+
* - a. Specify product type: users can directly input the type of the current product, and the system will process it according to the specified type.
|
|
45
|
+
* - 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.
|
|
46
|
+
* - **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:**
|
|
47
|
+
* - 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.
|
|
48
|
+
* - 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.
|
|
49
|
+
* - 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.
|
|
50
50
|
* ## Examples
|
|
51
|
-
* | **Type** | **Model image** | **
|
|
51
|
+
* | **Type** | **Model image** | **Garment image** | **Try-on result image** |
|
|
52
52
|
* | --- | --- | --- | --- |
|
|
53
|
-
* |
|
|
54
|
-
* |
|
|
53
|
+
* | Top |  |  |  |
|
|
54
|
+
* | Bottom |  |  |  |
|
|
55
55
|
* | Shoes |  |  |  |
|
|
56
|
-
* |
|
|
57
|
-
* |
|
|
58
|
-
* |
|
|
56
|
+
* | Jumpsuit |  |  |  |
|
|
57
|
+
* | Dress |  |  |  |
|
|
58
|
+
* | Hat |  |  |  |
|
|
59
59
|
*
|
|
60
60
|
* @param request - AiTryOnRequest
|
|
61
61
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -63,38 +63,38 @@ export default class Client extends OpenApi {
|
|
|
63
63
|
*/
|
|
64
64
|
aiTryOnWithOptions(request: $_model.AiTryOnRequest, runtime: $dara.RuntimeOptions): Promise<$_model.AiTryOnResponse>;
|
|
65
65
|
/**
|
|
66
|
-
* Generates
|
|
66
|
+
* 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.
|
|
67
67
|
*
|
|
68
68
|
* @remarks
|
|
69
69
|
* ## Scenarios
|
|
70
70
|
* - **Virtual try-on for clothing:**
|
|
71
|
-
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After
|
|
71
|
+
* 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.
|
|
72
72
|
* - **Virtual try-on for shoes and hats:**
|
|
73
|
-
* Supports virtual try-on for products such as shoes and hats.
|
|
73
|
+
* 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.
|
|
74
74
|
* - **E-commerce product display and marketing:**
|
|
75
75
|
* Helps merchants quickly generate model try-on images for different products, reducing the costs of traditional photography, outfit changes, and post-production, and improving the production efficiency of product images.
|
|
76
76
|
* - **Online shopping experience optimization:**
|
|
77
|
-
*
|
|
77
|
+
* 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.
|
|
78
78
|
* ## Features
|
|
79
|
-
* - **First,
|
|
80
|
-
* - a. Model image:
|
|
81
|
-
* - b. Product image:
|
|
82
|
-
* - **Second,
|
|
83
|
-
* - a. Specify product type:
|
|
84
|
-
* - b. Automatic type recognition:
|
|
85
|
-
* - **Finally, the system
|
|
86
|
-
* - a. Preserve model details:
|
|
87
|
-
* - b. Maintain image consistency:
|
|
88
|
-
* - c. Generate try-on effect:
|
|
79
|
+
* - **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:**
|
|
80
|
+
* - a. Model image: the image of the person who needs to perform the virtual try-on.
|
|
81
|
+
* - b. Product image: the image of the clothing, shoes, or hat to be worn by the model.
|
|
82
|
+
* - **Second, users can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
83
|
+
* - a. Specify product type: users can directly input the type of the current product, and the system will process it according to the specified type.
|
|
84
|
+
* - 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.
|
|
85
|
+
* - **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:**
|
|
86
|
+
* - 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.
|
|
87
|
+
* - 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.
|
|
88
|
+
* - 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.
|
|
89
89
|
* ## Examples
|
|
90
|
-
* | **Type** | **Model image** | **
|
|
90
|
+
* | **Type** | **Model image** | **Garment image** | **Try-on result image** |
|
|
91
91
|
* | --- | --- | --- | --- |
|
|
92
|
-
* |
|
|
93
|
-
* |
|
|
92
|
+
* | Top |  |  |  |
|
|
93
|
+
* | Bottom |  |  |  |
|
|
94
94
|
* | Shoes |  |  |  |
|
|
95
|
-
* |
|
|
96
|
-
* |
|
|
97
|
-
* |
|
|
95
|
+
* | Jumpsuit |  |  |  |
|
|
96
|
+
* | Dress |  |  |  |
|
|
97
|
+
* | Hat |  |  |  |
|
|
98
98
|
*
|
|
99
99
|
* @param request - AiTryOnRequest
|
|
100
100
|
* @returns AiTryOnResponse
|
|
@@ -424,22 +424,29 @@ export default class Client extends OpenApi {
|
|
|
424
424
|
*/
|
|
425
425
|
diduiAreaDeductionPro(request: $_model.DiduiAreaDeductionProRequest): Promise<$_model.DiduiAreaDeductionProResponse>;
|
|
426
426
|
/**
|
|
427
|
-
* Translates documents
|
|
427
|
+
* 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:
|
|
428
|
+
* - Content accuracy: translation accuracy, and accuracy of parameters and units.
|
|
429
|
+
* - Structural integrity: overall layout continuity, and restoration of page margins and layouts.
|
|
428
430
|
*
|
|
429
431
|
* @remarks
|
|
430
|
-
*
|
|
431
|
-
* Designed specifically for document translation, this
|
|
432
|
+
* # Product introduction
|
|
433
|
+
* Designed specifically for document translation, this service supports more than 150 languages and provides bridging translation capabilities with thousands of language combinations. It handles multi-scenario, multi-page, and highly complex document translations, but does not currently support scanned documents.
|
|
432
434
|
* It excels in the following aspects:
|
|
433
|
-
*
|
|
434
|
-
*
|
|
435
|
-
*
|
|
436
|
-
*
|
|
437
|
-
*
|
|
438
|
-
*
|
|
439
|
-
*
|
|
440
|
-
*
|
|
441
|
-
*
|
|
442
|
-
*
|
|
435
|
+
* * Content accuracy: translation accuracy, and accuracy of parameters and units.
|
|
436
|
+
*
|
|
437
|
+
* * Structural integrity: overall layout continuity, and restoration of page margins and layouts.
|
|
438
|
+
* # Scenarios
|
|
439
|
+
* Cross-border e-commerce product manuals, contracts, agreements, business proposals, qualification documents, teaching materials, courseware, and various other scenarios.
|
|
440
|
+
* # Features
|
|
441
|
+
* * Supports PDF, Word, and Excel formats. Supports source documents that contain multiple languages. For the detailed language list, see Section 4.4.
|
|
442
|
+
*
|
|
443
|
+
* * Supports the translation of text within images in documents, as well as complex translation scenarios involving other charts and special symbols.
|
|
444
|
+
*
|
|
445
|
+
* * Supports highly accurate layout restoration after translation.
|
|
446
|
+
*
|
|
447
|
+
* * Supports the translation of a single PDF or Word document with up to **800 pages**.
|
|
448
|
+
*
|
|
449
|
+
* * Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and translation omission (ABC-null value). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API to meet your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance. For detailed instructions on translation intervention, see [Full-modal translation - Translation intervention instruction manual](https://www.alibabacloud.com/help/en/aidge/full-modal-translation-translation-intervention-instruction-manual)
|
|
443
450
|
*
|
|
444
451
|
* @param request - DocumentTranslateRequest
|
|
445
452
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -447,22 +454,29 @@ export default class Client extends OpenApi {
|
|
|
447
454
|
*/
|
|
448
455
|
documentTranslateWithOptions(request: $_model.DocumentTranslateRequest, runtime: $dara.RuntimeOptions): Promise<$_model.DocumentTranslateResponse>;
|
|
449
456
|
/**
|
|
450
|
-
* Translates documents
|
|
457
|
+
* 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:
|
|
458
|
+
* - Content accuracy: translation accuracy, and accuracy of parameters and units.
|
|
459
|
+
* - Structural integrity: overall layout continuity, and restoration of page margins and layouts.
|
|
451
460
|
*
|
|
452
461
|
* @remarks
|
|
453
|
-
*
|
|
454
|
-
* Designed specifically for document translation, this
|
|
462
|
+
* # Product introduction
|
|
463
|
+
* Designed specifically for document translation, this service supports more than 150 languages and provides bridging translation capabilities with thousands of language combinations. It handles multi-scenario, multi-page, and highly complex document translations, but does not currently support scanned documents.
|
|
455
464
|
* It excels in the following aspects:
|
|
456
|
-
*
|
|
457
|
-
*
|
|
458
|
-
*
|
|
459
|
-
*
|
|
460
|
-
*
|
|
461
|
-
*
|
|
462
|
-
*
|
|
463
|
-
*
|
|
464
|
-
*
|
|
465
|
-
*
|
|
465
|
+
* * Content accuracy: translation accuracy, and accuracy of parameters and units.
|
|
466
|
+
*
|
|
467
|
+
* * Structural integrity: overall layout continuity, and restoration of page margins and layouts.
|
|
468
|
+
* # Scenarios
|
|
469
|
+
* Cross-border e-commerce product manuals, contracts, agreements, business proposals, qualification documents, teaching materials, courseware, and various other scenarios.
|
|
470
|
+
* # Features
|
|
471
|
+
* * Supports PDF, Word, and Excel formats. Supports source documents that contain multiple languages. For the detailed language list, see Section 4.4.
|
|
472
|
+
*
|
|
473
|
+
* * Supports the translation of text within images in documents, as well as complex translation scenarios involving other charts and special symbols.
|
|
474
|
+
*
|
|
475
|
+
* * Supports highly accurate layout restoration after translation.
|
|
476
|
+
*
|
|
477
|
+
* * Supports the translation of a single PDF or Word document with up to **800 pages**.
|
|
478
|
+
*
|
|
479
|
+
* * Supports custom translation results, including do-not-translate (ABC-ABC), specified translation (ABC-DEF), and translation omission (ABC-null value). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API to meet your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention terms. If you need more, contact the platform for assistance. For detailed instructions on translation intervention, see [Full-modal translation - Translation intervention instruction manual](https://www.alibabacloud.com/help/en/aidge/full-modal-translation-translation-intervention-instruction-manual)
|
|
466
480
|
*
|
|
467
481
|
* @param request - DocumentTranslateRequest
|
|
468
482
|
* @returns DocumentTranslateResponse
|
|
@@ -2520,6 +2534,51 @@ export default class Client extends OpenApi {
|
|
|
2520
2534
|
* @returns ProductHotspotDetectionResponse
|
|
2521
2535
|
*/
|
|
2522
2536
|
productHotspotDetection(request: $_model.ProductHotspotDetectionRequest): Promise<$_model.ProductHotspotDetectionResponse>;
|
|
2537
|
+
/**
|
|
2538
|
+
* 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.
|
|
2539
|
+
*
|
|
2540
|
+
* @remarks
|
|
2541
|
+
* # Product introduction
|
|
2542
|
+
* 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.
|
|
2543
|
+
* # Scenarios
|
|
2544
|
+
* - New product material generation: Provide a product title and images to automatically plan storyboard content such as product debut, details, or usage demonstrations.
|
|
2545
|
+
* - 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.
|
|
2546
|
+
* - 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.
|
|
2547
|
+
* # Features
|
|
2548
|
+
* - 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.
|
|
2549
|
+
* - 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.
|
|
2550
|
+
* - 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).
|
|
2551
|
+
* - 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.
|
|
2552
|
+
* # Examples
|
|
2553
|
+
* [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)
|
|
2554
|
+
*
|
|
2555
|
+
* @param tmpReq - ProductVideoGenerationRequest
|
|
2556
|
+
* @param runtime - runtime options for this request RuntimeOptions
|
|
2557
|
+
* @returns ProductVideoGenerationResponse
|
|
2558
|
+
*/
|
|
2559
|
+
productVideoGenerationWithOptions(tmpReq: $_model.ProductVideoGenerationRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ProductVideoGenerationResponse>;
|
|
2560
|
+
/**
|
|
2561
|
+
* 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.
|
|
2562
|
+
*
|
|
2563
|
+
* @remarks
|
|
2564
|
+
* # Product introduction
|
|
2565
|
+
* 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.
|
|
2566
|
+
* # Scenarios
|
|
2567
|
+
* - New product material generation: Provide a product title and images to automatically plan storyboard content such as product debut, details, or usage demonstrations.
|
|
2568
|
+
* - 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.
|
|
2569
|
+
* - 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.
|
|
2570
|
+
* # Features
|
|
2571
|
+
* - 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.
|
|
2572
|
+
* - 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.
|
|
2573
|
+
* - 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).
|
|
2574
|
+
* - 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.
|
|
2575
|
+
* # Examples
|
|
2576
|
+
* [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)
|
|
2577
|
+
*
|
|
2578
|
+
* @param request - ProductVideoGenerationRequest
|
|
2579
|
+
* @returns ProductVideoGenerationResponse
|
|
2580
|
+
*/
|
|
2581
|
+
productVideoGeneration(request: $_model.ProductVideoGenerationRequest): Promise<$_model.ProductVideoGenerationResponse>;
|
|
2523
2582
|
/**
|
|
2524
2583
|
* Queries the result of an asynchronous task. The API name in the POP gateway is QueryAsyncTaskResult.
|
|
2525
2584
|
*
|
|
@@ -3476,26 +3535,26 @@ export default class Client extends OpenApi {
|
|
|
3476
3535
|
*/
|
|
3477
3536
|
videoTranslation(request: $_model.VideoTranslationRequest): Promise<$_model.VideoTranslationResponse>;
|
|
3478
3537
|
/**
|
|
3479
|
-
* Generates virtual try-on images by
|
|
3538
|
+
* 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.
|
|
3480
3539
|
*
|
|
3481
3540
|
* @remarks
|
|
3482
3541
|
* ## Scenarios
|
|
3483
3542
|
* - **Virtual try-on for clothing:**
|
|
3484
|
-
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After
|
|
3543
|
+
* 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.
|
|
3485
3544
|
* - **Virtual try-on for shoes and hats:**
|
|
3486
|
-
* Supports virtual try-on for accessories such as shoes and hats. The system intelligently matches the position and proportion of the
|
|
3545
|
+
* 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.
|
|
3487
3546
|
* - **E-commerce product display and marketing:**
|
|
3488
|
-
*
|
|
3547
|
+
* 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.
|
|
3489
3548
|
* - **Online shopping experience optimization:**
|
|
3490
|
-
* 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
|
|
3549
|
+
* 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.
|
|
3491
3550
|
* ## Features
|
|
3492
|
-
* - **First,
|
|
3493
|
-
* - a. Model image: the image of the person
|
|
3494
|
-
* - b.
|
|
3495
|
-
* - **Second,
|
|
3496
|
-
* - a. Specify product type:
|
|
3497
|
-
* - b. Automatic type recognition: if
|
|
3498
|
-
* - **Finally, the system combines the model image,
|
|
3551
|
+
* - **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:**
|
|
3552
|
+
* - a. Model image: the image of the person for the virtual try-on.
|
|
3553
|
+
* - b. Garment image: the image of the clothing, shoes, or hat to be worn by the model.
|
|
3554
|
+
* - **Second, users can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
3555
|
+
* - 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.
|
|
3556
|
+
* - 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.
|
|
3557
|
+
* - **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:**
|
|
3499
3558
|
* - 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.
|
|
3500
3559
|
* - 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.
|
|
3501
3560
|
* - 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.
|
|
@@ -3503,8 +3562,8 @@ export default class Client extends OpenApi {
|
|
|
3503
3562
|
* | **Type** | **Model image** | **Garment image** | **Try-on result** |
|
|
3504
3563
|
* | --- | --- | --- | --- |
|
|
3505
3564
|
* | Tops |  |  |  |
|
|
3506
|
-
* | Bottoms |  |  |  |  |  |
|
|
3566
|
+
* | Shoes |  |  |  |
|
|
3508
3567
|
* | Jumpsuits |  |  |  |
|
|
3509
3568
|
* | Dresses |  |  |  |
|
|
3510
3569
|
* | Hats |  |  |  |
|
|
@@ -3515,26 +3574,26 @@ export default class Client extends OpenApi {
|
|
|
3515
3574
|
*/
|
|
3516
3575
|
virtualTryOnWithOptions(request: $_model.VirtualTryOnRequest, runtime: $dara.RuntimeOptions): Promise<$_model.VirtualTryOnResponse>;
|
|
3517
3576
|
/**
|
|
3518
|
-
* Generates virtual try-on images by
|
|
3577
|
+
* 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.
|
|
3519
3578
|
*
|
|
3520
3579
|
* @remarks
|
|
3521
3580
|
* ## Scenarios
|
|
3522
3581
|
* - **Virtual try-on for clothing:**
|
|
3523
|
-
* Supports various clothing categories such as tops, bottoms, jumpsuits, and dresses. After
|
|
3582
|
+
* 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.
|
|
3524
3583
|
* - **Virtual try-on for shoes and hats:**
|
|
3525
|
-
* Supports virtual try-on for accessories such as shoes and hats. The system intelligently matches the position and proportion of the
|
|
3584
|
+
* 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.
|
|
3526
3585
|
* - **E-commerce product display and marketing:**
|
|
3527
|
-
*
|
|
3586
|
+
* 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.
|
|
3528
3587
|
* - **Online shopping experience optimization:**
|
|
3529
|
-
* 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
|
|
3588
|
+
* 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.
|
|
3530
3589
|
* ## Features
|
|
3531
|
-
* - **First,
|
|
3532
|
-
* - a. Model image: the image of the person
|
|
3533
|
-
* - b.
|
|
3534
|
-
* - **Second,
|
|
3535
|
-
* - a. Specify product type:
|
|
3536
|
-
* - b. Automatic type recognition: if
|
|
3537
|
-
* - **Finally, the system combines the model image,
|
|
3590
|
+
* - **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:**
|
|
3591
|
+
* - a. Model image: the image of the person for the virtual try-on.
|
|
3592
|
+
* - b. Garment image: the image of the clothing, shoes, or hat to be worn by the model.
|
|
3593
|
+
* - **Second, users can select the corresponding product type based on the actual product. Supported types include tops, bottoms, jumpsuits, dresses, shoes, and hats:**
|
|
3594
|
+
* - 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.
|
|
3595
|
+
* - 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.
|
|
3596
|
+
* - **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:**
|
|
3538
3597
|
* - 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.
|
|
3539
3598
|
* - 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.
|
|
3540
3599
|
* - 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.
|
|
@@ -3542,8 +3601,8 @@ export default class Client extends OpenApi {
|
|
|
3542
3601
|
* | **Type** | **Model image** | **Garment image** | **Try-on result** |
|
|
3543
3602
|
* | --- | --- | --- | --- |
|
|
3544
3603
|
* | Tops |  |  |  |
|
|
3545
|
-
* | Bottoms |  |  |  |  |  |
|
|
3605
|
+
* | Shoes |  |  |  |
|
|
3547
3606
|
* | Jumpsuits |  |  |  |
|
|
3548
3607
|
* | Dresses |  |  |  |
|
|
3549
3608
|
* | Hats |  |  |  |
|
|
@@ -3553,61 +3612,61 @@ export default class Client extends OpenApi {
|
|
|
3553
3612
|
*/
|
|
3554
3613
|
virtualTryOn(request: $_model.VirtualTryOnRequest): Promise<$_model.VirtualTryOnResponse>;
|
|
3555
3614
|
/**
|
|
3556
|
-
* Provides a one-stop AI
|
|
3615
|
+
* 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)
|
|
3557
3616
|
*
|
|
3558
3617
|
* @remarks
|
|
3559
|
-
* # 1. Product
|
|
3560
|
-
*
|
|
3561
|
-
* # 2.
|
|
3562
|
-
* 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.
|
|
3563
|
-
* *
|
|
3618
|
+
* # 1. Product introduction
|
|
3619
|
+
* 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)
|
|
3620
|
+
* # 2. Scenarios
|
|
3621
|
+
* 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:
|
|
3622
|
+
* * Identifies low-quality images with text, watermarks, logos, or cluttered text, and allows users to filter the images to be processed.
|
|
3564
3623
|
*
|
|
3565
|
-
* *
|
|
3624
|
+
* * Removes non-compliant elements such as watermarks, logos, cluttered text, and Chinese text from the original image.
|
|
3566
3625
|
*
|
|
3567
|
-
* *
|
|
3626
|
+
* * Removes the background around the main product subject.
|
|
3568
3627
|
*
|
|
3569
|
-
* *
|
|
3628
|
+
* * Translates text in the image into other languages.
|
|
3570
3629
|
*
|
|
3571
|
-
* *
|
|
3630
|
+
* * Expands the image to other sizes (by ratio or dimensions) and automatically fills the background.
|
|
3572
3631
|
*
|
|
3573
|
-
* *
|
|
3632
|
+
* * Crops the image to a specified size.
|
|
3574
3633
|
*
|
|
3575
|
-
* *
|
|
3634
|
+
* * Upscales the image pixels by a specified factor.
|
|
3576
3635
|
* # 3. Features
|
|
3577
|
-
*
|
|
3636
|
+
* 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.
|
|
3578
3637
|
* 
|
|
3579
|
-
*
|
|
3580
|
-
* 1.
|
|
3638
|
+
* The following section describes each AI capability:
|
|
3639
|
+
* **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.
|
|
3581
3640
|
*
|
|
3582
|
-
* 2.
|
|
3641
|
+
* **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.
|
|
3583
3642
|
*
|
|
3584
|
-
* 3.
|
|
3643
|
+
* **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.
|
|
3585
3644
|
*
|
|
3586
|
-
* 4.
|
|
3645
|
+
* **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.
|
|
3587
3646
|
*
|
|
3588
|
-
* 5.
|
|
3647
|
+
* **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.
|
|
3589
3648
|
*
|
|
3590
|
-
* 6.
|
|
3649
|
+
* **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.
|
|
3591
3650
|
*
|
|
3592
|
-
* 7.
|
|
3593
|
-
* # 4.
|
|
3651
|
+
* **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.
|
|
3652
|
+
* # 4. Effect comparison
|
|
3594
3653
|
* | **Original image** | **Capabilities used** | **Output image** |
|
|
3595
3654
|
* | --- | --- | --- |
|
|
3596
|
-
* |  | * Intelligent
|
|
3655
|
+
* |  | * Intelligent recognition
|
|
3597
3656
|
*
|
|
3598
|
-
* * Image
|
|
3657
|
+
* * Image translation Pro
|
|
3599
3658
|
*
|
|
3600
3659
|
* * Intelligent cropping |  |
|
|
3601
|
-
* |  | * Intelligent
|
|
3660
|
+
* |  | * Intelligent cutout
|
|
3602
3661
|
*
|
|
3603
|
-
* * Intelligent
|
|
3662
|
+
* * Intelligent erasure
|
|
3604
3663
|
*
|
|
3605
3664
|
* * Intelligent cropping |  |
|
|
3606
|
-
* |  | * Intelligent
|
|
3665
|
+
* |  | * Intelligent recognition
|
|
3607
3666
|
*
|
|
3608
|
-
* * Intelligent
|
|
3667
|
+
* * Intelligent erasure
|
|
3609
3668
|
*
|
|
3610
|
-
* *
|
|
3669
|
+
* * High-definition upscaling |  |
|
|
3611
3670
|
*
|
|
3612
3671
|
* @param tmpReq - VisionFlowRequest
|
|
3613
3672
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3615,61 +3674,61 @@ export default class Client extends OpenApi {
|
|
|
3615
3674
|
*/
|
|
3616
3675
|
visionFlowWithOptions(tmpReq: $_model.VisionFlowRequest, runtime: $dara.RuntimeOptions): Promise<$_model.VisionFlowResponse>;
|
|
3617
3676
|
/**
|
|
3618
|
-
* Provides a one-stop AI
|
|
3677
|
+
* 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)
|
|
3619
3678
|
*
|
|
3620
3679
|
* @remarks
|
|
3621
|
-
* # 1. Product
|
|
3622
|
-
*
|
|
3623
|
-
* # 2.
|
|
3624
|
-
* 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.
|
|
3625
|
-
* *
|
|
3680
|
+
* # 1. Product introduction
|
|
3681
|
+
* 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)
|
|
3682
|
+
* # 2. Scenarios
|
|
3683
|
+
* 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:
|
|
3684
|
+
* * Identifies low-quality images with text, watermarks, logos, or cluttered text, and allows users to filter the images to be processed.
|
|
3626
3685
|
*
|
|
3627
|
-
* *
|
|
3686
|
+
* * Removes non-compliant elements such as watermarks, logos, cluttered text, and Chinese text from the original image.
|
|
3628
3687
|
*
|
|
3629
|
-
* *
|
|
3688
|
+
* * Removes the background around the main product subject.
|
|
3630
3689
|
*
|
|
3631
|
-
* *
|
|
3690
|
+
* * Translates text in the image into other languages.
|
|
3632
3691
|
*
|
|
3633
|
-
* *
|
|
3692
|
+
* * Expands the image to other sizes (by ratio or dimensions) and automatically fills the background.
|
|
3634
3693
|
*
|
|
3635
|
-
* *
|
|
3694
|
+
* * Crops the image to a specified size.
|
|
3636
3695
|
*
|
|
3637
|
-
* *
|
|
3696
|
+
* * Upscales the image pixels by a specified factor.
|
|
3638
3697
|
* # 3. Features
|
|
3639
|
-
*
|
|
3698
|
+
* 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.
|
|
3640
3699
|
* 
|
|
3641
|
-
*
|
|
3642
|
-
* 1.
|
|
3700
|
+
* The following section describes each AI capability:
|
|
3701
|
+
* **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.
|
|
3643
3702
|
*
|
|
3644
|
-
* 2.
|
|
3703
|
+
* **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.
|
|
3645
3704
|
*
|
|
3646
|
-
* 3.
|
|
3705
|
+
* **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.
|
|
3647
3706
|
*
|
|
3648
|
-
* 4.
|
|
3707
|
+
* **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.
|
|
3649
3708
|
*
|
|
3650
|
-
* 5.
|
|
3709
|
+
* **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.
|
|
3651
3710
|
*
|
|
3652
|
-
* 6.
|
|
3711
|
+
* **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.
|
|
3653
3712
|
*
|
|
3654
|
-
* 7.
|
|
3655
|
-
* # 4.
|
|
3713
|
+
* **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.
|
|
3714
|
+
* # 4. Effect comparison
|
|
3656
3715
|
* | **Original image** | **Capabilities used** | **Output image** |
|
|
3657
3716
|
* | --- | --- | --- |
|
|
3658
|
-
* |  | * Intelligent
|
|
3717
|
+
* |  | * Intelligent recognition
|
|
3659
3718
|
*
|
|
3660
|
-
* * Image
|
|
3719
|
+
* * Image translation Pro
|
|
3661
3720
|
*
|
|
3662
3721
|
* * Intelligent cropping |  |
|
|
3663
|
-
* |  | * Intelligent
|
|
3722
|
+
* |  | * Intelligent cutout
|
|
3664
3723
|
*
|
|
3665
|
-
* * Intelligent
|
|
3724
|
+
* * Intelligent erasure
|
|
3666
3725
|
*
|
|
3667
3726
|
* * Intelligent cropping |  |
|
|
3668
|
-
* |  | * Intelligent
|
|
3727
|
+
* |  | * Intelligent recognition
|
|
3669
3728
|
*
|
|
3670
|
-
* * Intelligent
|
|
3729
|
+
* * Intelligent erasure
|
|
3671
3730
|
*
|
|
3672
|
-
* *
|
|
3731
|
+
* * High-definition upscaling |  |
|
|
3673
3732
|
*
|
|
3674
3733
|
* @param request - VisionFlowRequest
|
|
3675
3734
|
* @returns VisionFlowResponse
|