@alicloud/aidge20260428 5.10.0 → 5.10.1
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 +186 -186
- package/dist/client.js +210 -186
- package/dist/client.js.map +1 -1
- package/dist/models/ImageMattingAsyncRequest.d.ts +9 -1
- package/dist/models/ImageMattingAsyncRequest.js +2 -0
- package/dist/models/ImageMattingAsyncRequest.js.map +1 -1
- package/dist/models/ImageMattingAsyncResponseBody.d.ts +5 -5
- package/dist/models/ImageRecognitionAsyncRequest.d.ts +33 -25
- package/dist/models/ImageRecognitionAsyncRequest.js +2 -0
- package/dist/models/ImageRecognitionAsyncRequest.js.map +1 -1
- package/dist/models/ImageRecognitionAsyncResponseBody.d.ts +6 -6
- package/dist/models/ImageRecognitionAsyncShrinkRequest.d.ts +33 -25
- package/dist/models/ImageRecognitionAsyncShrinkRequest.js +2 -0
- package/dist/models/ImageRecognitionAsyncShrinkRequest.js.map +1 -1
- package/dist/models/ImageRemovalProAsyncRequest.d.ts +10 -1
- package/dist/models/ImageRemovalProAsyncRequest.js +2 -0
- package/dist/models/ImageRemovalProAsyncRequest.js.map +1 -1
- package/dist/models/ImageRemovalProAsyncResponseBody.d.ts +7 -5
- package/dist/models/ImageRemovalProAsyncResponseBody.js.map +1 -1
- package/dist/models/ImageRemoveAsyncRequest.d.ts +25 -6
- package/dist/models/ImageRemoveAsyncRequest.js +2 -0
- package/dist/models/ImageRemoveAsyncRequest.js.map +1 -1
- package/dist/models/ImageRemoveAsyncResponseBody.d.ts +6 -4
- package/dist/models/ImageRemoveAsyncResponseBody.js.map +1 -1
- package/dist/models/ImageRemoveAsyncShrinkRequest.d.ts +25 -6
- package/dist/models/ImageRemoveAsyncShrinkRequest.js +2 -0
- package/dist/models/ImageRemoveAsyncShrinkRequest.js.map +1 -1
- package/dist/models/ImageTranslationPlusAsyncRequest.d.ts +17 -9
- package/dist/models/ImageTranslationPlusAsyncRequest.js +2 -0
- package/dist/models/ImageTranslationPlusAsyncRequest.js.map +1 -1
- package/dist/models/ImageTranslationPlusAsyncResponseBody.d.ts +5 -5
- package/dist/models/ImageTranslationProAsyncRequest.d.ts +15 -7
- package/dist/models/ImageTranslationProAsyncRequest.js +2 -0
- package/dist/models/ImageTranslationProAsyncRequest.js.map +1 -1
- package/dist/models/ImageTranslationProAsyncResponseBody.d.ts +4 -4
- package/dist/models/ImageTranslationStandardAsyncRequest.d.ts +10 -2
- package/dist/models/ImageTranslationStandardAsyncRequest.js +2 -0
- package/dist/models/ImageTranslationStandardAsyncRequest.js.map +1 -1
- package/dist/models/ImageTranslationStandardAsyncResponseBody.d.ts +4 -4
- package/dist/models/QueryAsyncTaskResultResponseBody.d.ts +13 -7
- package/dist/models/QueryAsyncTaskResultResponseBody.js +2 -0
- package/dist/models/QueryAsyncTaskResultResponseBody.js.map +1 -1
- package/dist/models/SizeChartExtractAsyncRequest.d.ts +9 -1
- package/dist/models/SizeChartExtractAsyncRequest.js +2 -0
- package/dist/models/SizeChartExtractAsyncRequest.js.map +1 -1
- package/dist/models/SizeChartExtractAsyncResponseBody.d.ts +5 -5
- package/dist/models/SizeChartExtractAsyncShrinkRequest.d.ts +9 -1
- package/dist/models/SizeChartExtractAsyncShrinkRequest.js +2 -0
- package/dist/models/SizeChartExtractAsyncShrinkRequest.js.map +1 -1
- package/dist/models/VideoTranslationRequest.d.ts +12 -12
- package/dist/models/VideoTranslationResponseBody.d.ts +4 -4
- package/dist/models/VideoTranslationShrinkRequest.d.ts +12 -12
- package/package.json +1 -1
- package/src/client.ts +222 -190
- package/src/models/ImageMattingAsyncRequest.ts +11 -1
- package/src/models/ImageMattingAsyncResponseBody.ts +5 -5
- package/src/models/ImageRecognitionAsyncRequest.ts +35 -25
- package/src/models/ImageRecognitionAsyncResponseBody.ts +6 -6
- package/src/models/ImageRecognitionAsyncShrinkRequest.ts +35 -25
- package/src/models/ImageRemovalProAsyncRequest.ts +12 -1
- package/src/models/ImageRemovalProAsyncResponseBody.ts +7 -5
- package/src/models/ImageRemoveAsyncRequest.ts +27 -6
- package/src/models/ImageRemoveAsyncResponseBody.ts +6 -4
- package/src/models/ImageRemoveAsyncShrinkRequest.ts +27 -6
- package/src/models/ImageTranslationPlusAsyncRequest.ts +19 -9
- package/src/models/ImageTranslationPlusAsyncResponseBody.ts +5 -5
- package/src/models/ImageTranslationProAsyncRequest.ts +17 -7
- package/src/models/ImageTranslationProAsyncResponseBody.ts +4 -4
- package/src/models/ImageTranslationStandardAsyncRequest.ts +12 -2
- package/src/models/ImageTranslationStandardAsyncResponseBody.ts +4 -4
- package/src/models/QueryAsyncTaskResultResponseBody.ts +15 -7
- package/src/models/SizeChartExtractAsyncRequest.ts +11 -1
- package/src/models/SizeChartExtractAsyncResponseBody.ts +5 -5
- package/src/models/SizeChartExtractAsyncShrinkRequest.ts +11 -1
- package/src/models/VideoTranslationRequest.ts +12 -12
- package/src/models/VideoTranslationResponseBody.ts +4 -4
- package/src/models/VideoTranslationShrinkRequest.ts +12 -12
package/src/client.ts
CHANGED
|
@@ -1358,13 +1358,13 @@ export default class Client extends OpenApi {
|
|
|
1358
1358
|
}
|
|
1359
1359
|
|
|
1360
1360
|
/**
|
|
1361
|
-
* Extracts the salient subject from an image
|
|
1361
|
+
* Extracts the salient subject from an image by separating it from the background and returns the subject image with the background removed. It also provides multiple background options and custom size options to optimize product display.
|
|
1362
1362
|
*
|
|
1363
1363
|
* @remarks
|
|
1364
1364
|
* # Scenarios
|
|
1365
|
-
* * Supports secondary editing of materials: After the image subject
|
|
1365
|
+
* * Supports secondary editing of materials: After separating the image subject from the background, you can further edit the image.
|
|
1366
1366
|
*
|
|
1367
|
-
* * Improves material processing efficiency: Quickly extracts the subjects from various material images for background replacement,
|
|
1367
|
+
* * Improves material processing efficiency: Quickly extracts the subjects from various material images for background replacement, thereby improving the production efficiency of advertising images and marketing posters.
|
|
1368
1368
|
* # Features.
|
|
1369
1369
|
* #### 1. One-click precise subject recognition
|
|
1370
1370
|
* * **AI-based automatic recognition**: Based on deep learning models, it intelligently distinguishes foreground subjects (portraits, products, objects, etc.) from the background without manual outlining.
|
|
@@ -1373,9 +1373,9 @@ export default class Client extends OpenApi {
|
|
|
1373
1373
|
* #### 2. Intelligent edge optimization
|
|
1374
1374
|
* * **Detail-level processing**: Performs automatic optimization on edge jaggies and semi-transparent areas (such as smoke and glass) to retain natural transition effects.
|
|
1375
1375
|
* #### 3. Multi-format output and background operations
|
|
1376
|
-
* * **Transparent background export**: Directly generates PNG images with transparent
|
|
1376
|
+
* * **Transparent background export**: Directly generates PNG images with transparent backgrounds and white backgrounds, adapting to e-commerce and design scenarios.
|
|
1377
1377
|
*
|
|
1378
|
-
* * **
|
|
1378
|
+
* * **Custom background color support**
|
|
1379
1379
|
* # Effect comparison
|
|
1380
1380
|
* | **Original image (input)** | **Result image (output)** |
|
|
1381
1381
|
* | --- | --- |
|
|
@@ -1398,6 +1398,10 @@ export default class Client extends OpenApi {
|
|
|
1398
1398
|
query["BgColor"] = request.bgColor;
|
|
1399
1399
|
}
|
|
1400
1400
|
|
|
1401
|
+
if (!$dara.isNull(request.bizId)) {
|
|
1402
|
+
query["BizId"] = request.bizId;
|
|
1403
|
+
}
|
|
1404
|
+
|
|
1401
1405
|
if (!$dara.isNull(request.imageUrl)) {
|
|
1402
1406
|
query["ImageUrl"] = request.imageUrl;
|
|
1403
1407
|
}
|
|
@@ -1428,13 +1432,13 @@ export default class Client extends OpenApi {
|
|
|
1428
1432
|
}
|
|
1429
1433
|
|
|
1430
1434
|
/**
|
|
1431
|
-
* Extracts the salient subject from an image
|
|
1435
|
+
* Extracts the salient subject from an image by separating it from the background and returns the subject image with the background removed. It also provides multiple background options and custom size options to optimize product display.
|
|
1432
1436
|
*
|
|
1433
1437
|
* @remarks
|
|
1434
1438
|
* # Scenarios
|
|
1435
|
-
* * Supports secondary editing of materials: After the image subject
|
|
1439
|
+
* * Supports secondary editing of materials: After separating the image subject from the background, you can further edit the image.
|
|
1436
1440
|
*
|
|
1437
|
-
* * Improves material processing efficiency: Quickly extracts the subjects from various material images for background replacement,
|
|
1441
|
+
* * Improves material processing efficiency: Quickly extracts the subjects from various material images for background replacement, thereby improving the production efficiency of advertising images and marketing posters.
|
|
1438
1442
|
* # Features.
|
|
1439
1443
|
* #### 1. One-click precise subject recognition
|
|
1440
1444
|
* * **AI-based automatic recognition**: Based on deep learning models, it intelligently distinguishes foreground subjects (portraits, products, objects, etc.) from the background without manual outlining.
|
|
@@ -1443,9 +1447,9 @@ export default class Client extends OpenApi {
|
|
|
1443
1447
|
* #### 2. Intelligent edge optimization
|
|
1444
1448
|
* * **Detail-level processing**: Performs automatic optimization on edge jaggies and semi-transparent areas (such as smoke and glass) to retain natural transition effects.
|
|
1445
1449
|
* #### 3. Multi-format output and background operations
|
|
1446
|
-
* * **Transparent background export**: Directly generates PNG images with transparent
|
|
1450
|
+
* * **Transparent background export**: Directly generates PNG images with transparent backgrounds and white backgrounds, adapting to e-commerce and design scenarios.
|
|
1447
1451
|
*
|
|
1448
|
-
* * **
|
|
1452
|
+
* * **Custom background color support**
|
|
1449
1453
|
* # Effect comparison
|
|
1450
1454
|
* | **Original image (input)** | **Result image (output)** |
|
|
1451
1455
|
* | --- | --- |
|
|
@@ -1678,12 +1682,12 @@ export default class Client extends OpenApi {
|
|
|
1678
1682
|
}
|
|
1679
1683
|
|
|
1680
1684
|
/**
|
|
1681
|
-
* Identifies specific elements in e-commerce images. It
|
|
1685
|
+
* Identifies specific elements in e-commerce images. It extracts image details to help users quickly identify text, logos, watermarks, and text-containing color blocks in the main subject and background, significantly improving the efficiency and accuracy of image filtering.
|
|
1682
1686
|
*
|
|
1683
1687
|
* @remarks
|
|
1684
1688
|
* # Scenarios
|
|
1685
1689
|
* 1. Intelligent image filtering and optimization:
|
|
1686
|
-
* Merchants and platforms can use the intelligent element recognition API to filter images and automatically identify images containing specific elements such as watermarks and logos. After filtering, they can
|
|
1690
|
+
* Merchants and platforms can use the intelligent element recognition API to filter images and automatically identify images containing specific elements such as watermarks and logos. After filtering, they can call the intelligent elimination API to optimize these images, improve image quality, and shorten the product release cycle.
|
|
1687
1691
|
* 2. Automated image processing and efficiency improvement:
|
|
1688
1692
|
* Through the intelligent element recognition API, merchants and platforms can automate the image processing workflow and automatically identify and mark image elements that need to be optimized. This workflow reduces manual intervention and improves the efficiency of image processing.
|
|
1689
1693
|
* # Features
|
|
@@ -1696,14 +1700,14 @@ export default class Client extends OpenApi {
|
|
|
1696
1700
|
*
|
|
1697
1701
|
* * Logo: A logo or trademark.
|
|
1698
1702
|
*
|
|
1699
|
-
* * Watermark: Monochrome transparent text, logos, images, URLs,
|
|
1703
|
+
* * Watermark: Monochrome transparent text, logos, images, URLs, store names, etc.
|
|
1700
1704
|
*
|
|
1701
1705
|
* * Text-containing color block: A color block containing text outside the subject.
|
|
1702
1706
|
*
|
|
1703
|
-
* **2. The
|
|
1707
|
+
* **2. The intelligent element recognition API provides the following features:**
|
|
1704
1708
|
* * Element recognition: Identifies whether elements such as text, logos, watermarks, and text-containing color blocks exist in the image subject and background.
|
|
1705
1709
|
*
|
|
1706
|
-
* * Workflow collaboration: Used in combination with the intelligent elimination API.
|
|
1710
|
+
* * Workflow collaboration: Used in combination with the intelligent elimination API. First, the intelligent element recognition API identifies the elements to be removed, and then the intelligent elimination API effectively removes them to ensure the accuracy and efficiency of image processing.
|
|
1707
1711
|
*
|
|
1708
1712
|
* **3. Technical advantages:**
|
|
1709
1713
|
* * Synchronous batch processing: As a synchronous API, the intelligent element recognition API can process a large number of images while maintaining fast response, adapting to business needs of different scales.
|
|
@@ -1764,6 +1768,10 @@ export default class Client extends OpenApi {
|
|
|
1764
1768
|
}
|
|
1765
1769
|
|
|
1766
1770
|
let query = { };
|
|
1771
|
+
if (!$dara.isNull(request.bizId)) {
|
|
1772
|
+
query["BizId"] = request.bizId;
|
|
1773
|
+
}
|
|
1774
|
+
|
|
1767
1775
|
if (!$dara.isNull(request.imageUrl)) {
|
|
1768
1776
|
query["ImageUrl"] = request.imageUrl;
|
|
1769
1777
|
}
|
|
@@ -1814,12 +1822,12 @@ export default class Client extends OpenApi {
|
|
|
1814
1822
|
}
|
|
1815
1823
|
|
|
1816
1824
|
/**
|
|
1817
|
-
* Identifies specific elements in e-commerce images. It
|
|
1825
|
+
* Identifies specific elements in e-commerce images. It extracts image details to help users quickly identify text, logos, watermarks, and text-containing color blocks in the main subject and background, significantly improving the efficiency and accuracy of image filtering.
|
|
1818
1826
|
*
|
|
1819
1827
|
* @remarks
|
|
1820
1828
|
* # Scenarios
|
|
1821
1829
|
* 1. Intelligent image filtering and optimization:
|
|
1822
|
-
* Merchants and platforms can use the intelligent element recognition API to filter images and automatically identify images containing specific elements such as watermarks and logos. After filtering, they can
|
|
1830
|
+
* Merchants and platforms can use the intelligent element recognition API to filter images and automatically identify images containing specific elements such as watermarks and logos. After filtering, they can call the intelligent elimination API to optimize these images, improve image quality, and shorten the product release cycle.
|
|
1823
1831
|
* 2. Automated image processing and efficiency improvement:
|
|
1824
1832
|
* Through the intelligent element recognition API, merchants and platforms can automate the image processing workflow and automatically identify and mark image elements that need to be optimized. This workflow reduces manual intervention and improves the efficiency of image processing.
|
|
1825
1833
|
* # Features
|
|
@@ -1832,14 +1840,14 @@ export default class Client extends OpenApi {
|
|
|
1832
1840
|
*
|
|
1833
1841
|
* * Logo: A logo or trademark.
|
|
1834
1842
|
*
|
|
1835
|
-
* * Watermark: Monochrome transparent text, logos, images, URLs,
|
|
1843
|
+
* * Watermark: Monochrome transparent text, logos, images, URLs, store names, etc.
|
|
1836
1844
|
*
|
|
1837
1845
|
* * Text-containing color block: A color block containing text outside the subject.
|
|
1838
1846
|
*
|
|
1839
|
-
* **2. The
|
|
1847
|
+
* **2. The intelligent element recognition API provides the following features:**
|
|
1840
1848
|
* * Element recognition: Identifies whether elements such as text, logos, watermarks, and text-containing color blocks exist in the image subject and background.
|
|
1841
1849
|
*
|
|
1842
|
-
* * Workflow collaboration: Used in combination with the intelligent elimination API.
|
|
1850
|
+
* * Workflow collaboration: Used in combination with the intelligent elimination API. First, the intelligent element recognition API identifies the elements to be removed, and then the intelligent elimination API effectively removes them to ensure the accuracy and efficiency of image processing.
|
|
1843
1851
|
*
|
|
1844
1852
|
* **3. Technical advantages:**
|
|
1845
1853
|
* * Synchronous batch processing: As a synchronous API, the intelligent element recognition API can process a large number of images while maintaining fast response, adapting to business needs of different scales.
|
|
@@ -1986,27 +1994,27 @@ export default class Client extends OpenApi {
|
|
|
1986
1994
|
}
|
|
1987
1995
|
|
|
1988
1996
|
/**
|
|
1989
|
-
*
|
|
1997
|
+
* Removes objects from e-commerce images by automatically identifying and erasing text, specific names, transparent text blocks, and watermarks. Allows you to specify objects to remove as needed, enabling efficient and accurate processing of large batches of images and simplifying image editing.
|
|
1990
1998
|
*
|
|
1991
1999
|
* @remarks
|
|
1992
2000
|
* ## Scenarios
|
|
1993
|
-
* * **Efficient e-commerce
|
|
2001
|
+
* * **Efficient processing of e-commerce images:**
|
|
1994
2002
|
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
1995
|
-
* * **
|
|
1996
|
-
*
|
|
2003
|
+
* * **Product information synchronization across multiple platforms:**
|
|
2004
|
+
* Quickly removes specific text and watermarks when merchants list products on different e-commerce platforms to comply with the image specifications of each platform.
|
|
1997
2005
|
* ## Features
|
|
1998
|
-
* 1. First,
|
|
2006
|
+
* 1. First, understand the definitions of the image subject and the image background. In actual use, when specifying the objects to remove, you can choose to remove objects from the image subject or the image background. Both API and editor integration methods are supported to meet different requirements.
|
|
1999
2007
|
*
|
|
2000
2008
|
* 1. Image subject: the core product area in the image.
|
|
2001
2009
|
*
|
|
2002
|
-
* 2. Image background: the rest of the image
|
|
2010
|
+
* 2. Image background: the rest of the image except the product subject.
|
|
2003
2011
|
*
|
|
2004
|
-
* 2. Second, the
|
|
2005
|
-
* ##
|
|
2006
|
-
* | **Original image** | **
|
|
2012
|
+
* 2. Second, the following four types of objects can be removed: text, specific names, transparent text blocks, and watermarks. You can refer to the following examples to clarify your requirements and perform targeted operations:
|
|
2013
|
+
* ## Effect comparison
|
|
2014
|
+
* | **Original image** | **Processed image** |
|
|
2007
2015
|
* | --- | --- |
|
|
2008
|
-
* |  |  |
|
|
2009
|
-
* |  |  |
|
|
2017
|
+
* |  |  |
|
|
2010
2018
|
*
|
|
2011
2019
|
* @param request - ImageRemovalProAsyncRequest
|
|
2012
2020
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -2015,6 +2023,10 @@ export default class Client extends OpenApi {
|
|
|
2015
2023
|
async imageRemovalProAsyncWithOptions(request: $_model.ImageRemovalProAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageRemovalProAsyncResponse> {
|
|
2016
2024
|
request.validate();
|
|
2017
2025
|
let query = { };
|
|
2026
|
+
if (!$dara.isNull(request.bizId)) {
|
|
2027
|
+
query["BizId"] = request.bizId;
|
|
2028
|
+
}
|
|
2029
|
+
|
|
2018
2030
|
if (!$dara.isNull(request.imageUrl)) {
|
|
2019
2031
|
query["ImageUrl"] = request.imageUrl;
|
|
2020
2032
|
}
|
|
@@ -2037,27 +2049,27 @@ export default class Client extends OpenApi {
|
|
|
2037
2049
|
}
|
|
2038
2050
|
|
|
2039
2051
|
/**
|
|
2040
|
-
*
|
|
2052
|
+
* Removes objects from e-commerce images by automatically identifying and erasing text, specific names, transparent text blocks, and watermarks. Allows you to specify objects to remove as needed, enabling efficient and accurate processing of large batches of images and simplifying image editing.
|
|
2041
2053
|
*
|
|
2042
2054
|
* @remarks
|
|
2043
2055
|
* ## Scenarios
|
|
2044
|
-
* * **Efficient e-commerce
|
|
2056
|
+
* * **Efficient processing of e-commerce images:**
|
|
2045
2057
|
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
2046
|
-
* * **
|
|
2047
|
-
*
|
|
2058
|
+
* * **Product information synchronization across multiple platforms:**
|
|
2059
|
+
* Quickly removes specific text and watermarks when merchants list products on different e-commerce platforms to comply with the image specifications of each platform.
|
|
2048
2060
|
* ## Features
|
|
2049
|
-
* 1. First,
|
|
2061
|
+
* 1. First, understand the definitions of the image subject and the image background. In actual use, when specifying the objects to remove, you can choose to remove objects from the image subject or the image background. Both API and editor integration methods are supported to meet different requirements.
|
|
2050
2062
|
*
|
|
2051
2063
|
* 1. Image subject: the core product area in the image.
|
|
2052
2064
|
*
|
|
2053
|
-
* 2. Image background: the rest of the image
|
|
2065
|
+
* 2. Image background: the rest of the image except the product subject.
|
|
2054
2066
|
*
|
|
2055
|
-
* 2. Second, the
|
|
2056
|
-
* ##
|
|
2057
|
-
* | **Original image** | **
|
|
2067
|
+
* 2. Second, the following four types of objects can be removed: text, specific names, transparent text blocks, and watermarks. You can refer to the following examples to clarify your requirements and perform targeted operations:
|
|
2068
|
+
* ## Effect comparison
|
|
2069
|
+
* | **Original image** | **Processed image** |
|
|
2058
2070
|
* | --- | --- |
|
|
2059
|
-
* |  |  |
|
|
2060
|
-
* |  |  |
|
|
2072
|
+
* |  |  |
|
|
2061
2073
|
*
|
|
2062
2074
|
* @param request - ImageRemovalProAsyncRequest
|
|
2063
2075
|
* @returns ImageRemovalProAsyncResponse
|
|
@@ -2320,33 +2332,33 @@ export default class Client extends OpenApi {
|
|
|
2320
2332
|
}
|
|
2321
2333
|
|
|
2322
2334
|
/**
|
|
2323
|
-
*
|
|
2335
|
+
* Intelligently removes unwanted elements from e-commerce images by automatically identifying and erasing text, specific names, transparent text blocks, and promotional stickers. Supports specifying target objects for removal to enable efficient and accurate batch processing and simplify image editing.
|
|
2324
2336
|
*
|
|
2325
2337
|
* @remarks
|
|
2326
2338
|
* ## Scenarios
|
|
2327
|
-
* * **Efficient
|
|
2339
|
+
* * **Efficient e-commerce image processing:**
|
|
2328
2340
|
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
2329
|
-
* * **Multi-platform product information synchronization:**
|
|
2330
|
-
* When merchants
|
|
2331
|
-
* * **Marketing material preparation:**
|
|
2341
|
+
* * **Multi-platform product information synchronization:**
|
|
2342
|
+
* When merchants list products on different e-commerce platforms simultaneously, they can quickly remove specific text and promotional stickers to comply with the image specifications of different platforms.
|
|
2343
|
+
* * **Marketing material preparation:**
|
|
2332
2344
|
* Merchants can easily remove original promotional information and quickly update it with the latest campaign information.
|
|
2333
|
-
* > Note: Merchants or platforms can batch remove
|
|
2345
|
+
* > Note: Merchants or platforms can batch remove impurities in images to optimize image quality. We recommend using this feature in combination with the "Intelligent Recognition API" (coming soon) to first filter images containing text, specific names, transparent text blocks, and promotional stickers, and then use the "Intelligent Erasure API" for batch removal. The Intelligent Recognition API focuses on "recognition", while the Intelligent Erasure API focuses on "erasure". By calling them in sequence, you can maximize the erasure effect and reduce "false removals" and "false recognitions".
|
|
2334
2346
|
* ## Features
|
|
2335
|
-
* 1. First, clarify the definitions of the image subject and the image background. In actual use, when specifying the objects to
|
|
2347
|
+
* 1. First, clarify the definitions of the image subject and the image background. In actual use, when specifying the objects to be removed, you can choose whether the removal scope is the image subject or the image background area. Both API and editor integration methods are supported to meet different types of requirements.
|
|
2336
2348
|
*
|
|
2337
2349
|
* 1. Image subject: the core product area in the image.
|
|
2338
2350
|
*
|
|
2339
2351
|
* 2. Image background: the rest of the image other than the product subject.
|
|
2340
2352
|
*
|
|
2341
|
-
* 2. Second, the objects to
|
|
2353
|
+
* 2. Second, the objects to be removed support the following three cases:
|
|
2342
2354
|
*
|
|
2343
|
-
* 1. The user selects
|
|
2355
|
+
* 1. The user only selects the type. Supported types include text, specific names, transparent text blocks, and promotional stickers. You can clarify the usage requirements through the following examples for targeted operations.
|
|
2344
2356
|
*
|
|
2345
2357
|
* 2. (Upgraded) Provides specified image erasure. Users can specify multiple images at a time.
|
|
2346
2358
|
*
|
|
2347
|
-
* 3. (Upgraded) Provides specified text erasure. Users can specify multiple
|
|
2359
|
+
* 3. (Upgraded) Provides specified text erasure. Users can specify multiple text strings at a time.
|
|
2348
2360
|
*
|
|
2349
|
-
* Processing flow: The user
|
|
2361
|
+
* Processing flow: The user passes in the original image URL → OCR and VLM models detect the text or image position → Determine the coordinates of the area to be repaired → AI repairs and generates a clean image → Returns the result image URL.
|
|
2350
2362
|
* ## Effect comparison
|
|
2351
2363
|
* | **Objects that can be removed from the image** | **Original image** | **Image after erasure** |
|
|
2352
2364
|
* | --- | --- | --- |
|
|
@@ -2386,7 +2398,7 @@ export default class Client extends OpenApi {
|
|
|
2386
2398
|
* * Does not involve the image subject area
|
|
2387
2399
|
*
|
|
2388
2400
|
*  |
|
|
2389
|
-
* |
|
|
2401
|
+
* | Promotional stickers | * Involves the image subject area
|
|
2390
2402
|
*
|
|
2391
2403
|
* 
|
|
2392
2404
|
*
|
|
@@ -2399,7 +2411,7 @@ export default class Client extends OpenApi {
|
|
|
2399
2411
|
*
|
|
2400
2412
|
*  |
|
|
2401
2413
|
* | Specified image element erasure (supports multiple image links) |  |  |
|
|
2402
|
-
* | Specified text erasure (supports multiple
|
|
2414
|
+
* | Specified text erasure (supports multiple text strings) |  |  |
|
|
2403
2415
|
*
|
|
2404
2416
|
* @param tmpReq - ImageRemoveAsyncRequest
|
|
2405
2417
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -2426,6 +2438,10 @@ export default class Client extends OpenApi {
|
|
|
2426
2438
|
}
|
|
2427
2439
|
|
|
2428
2440
|
let query = { };
|
|
2441
|
+
if (!$dara.isNull(request.bizId)) {
|
|
2442
|
+
query["BizId"] = request.bizId;
|
|
2443
|
+
}
|
|
2444
|
+
|
|
2429
2445
|
if (!$dara.isNull(request.imageUrl)) {
|
|
2430
2446
|
query["ImageUrl"] = request.imageUrl;
|
|
2431
2447
|
}
|
|
@@ -2472,33 +2488,33 @@ export default class Client extends OpenApi {
|
|
|
2472
2488
|
}
|
|
2473
2489
|
|
|
2474
2490
|
/**
|
|
2475
|
-
*
|
|
2491
|
+
* Intelligently removes unwanted elements from e-commerce images by automatically identifying and erasing text, specific names, transparent text blocks, and promotional stickers. Supports specifying target objects for removal to enable efficient and accurate batch processing and simplify image editing.
|
|
2476
2492
|
*
|
|
2477
2493
|
* @remarks
|
|
2478
2494
|
* ## Scenarios
|
|
2479
|
-
* * **Efficient
|
|
2495
|
+
* * **Efficient e-commerce image processing:**
|
|
2480
2496
|
* Removes irrelevant visual elements to provide clearer and more focused product displays, enhancing the customer shopping experience.
|
|
2481
|
-
* * **Multi-platform product information synchronization:**
|
|
2482
|
-
* When merchants
|
|
2483
|
-
* * **Marketing material preparation:**
|
|
2497
|
+
* * **Multi-platform product information synchronization:**
|
|
2498
|
+
* When merchants list products on different e-commerce platforms simultaneously, they can quickly remove specific text and promotional stickers to comply with the image specifications of different platforms.
|
|
2499
|
+
* * **Marketing material preparation:**
|
|
2484
2500
|
* Merchants can easily remove original promotional information and quickly update it with the latest campaign information.
|
|
2485
|
-
* > Note: Merchants or platforms can batch remove
|
|
2501
|
+
* > Note: Merchants or platforms can batch remove impurities in images to optimize image quality. We recommend using this feature in combination with the "Intelligent Recognition API" (coming soon) to first filter images containing text, specific names, transparent text blocks, and promotional stickers, and then use the "Intelligent Erasure API" for batch removal. The Intelligent Recognition API focuses on "recognition", while the Intelligent Erasure API focuses on "erasure". By calling them in sequence, you can maximize the erasure effect and reduce "false removals" and "false recognitions".
|
|
2486
2502
|
* ## Features
|
|
2487
|
-
* 1. First, clarify the definitions of the image subject and the image background. In actual use, when specifying the objects to
|
|
2503
|
+
* 1. First, clarify the definitions of the image subject and the image background. In actual use, when specifying the objects to be removed, you can choose whether the removal scope is the image subject or the image background area. Both API and editor integration methods are supported to meet different types of requirements.
|
|
2488
2504
|
*
|
|
2489
2505
|
* 1. Image subject: the core product area in the image.
|
|
2490
2506
|
*
|
|
2491
2507
|
* 2. Image background: the rest of the image other than the product subject.
|
|
2492
2508
|
*
|
|
2493
|
-
* 2. Second, the objects to
|
|
2509
|
+
* 2. Second, the objects to be removed support the following three cases:
|
|
2494
2510
|
*
|
|
2495
|
-
* 1. The user selects
|
|
2511
|
+
* 1. The user only selects the type. Supported types include text, specific names, transparent text blocks, and promotional stickers. You can clarify the usage requirements through the following examples for targeted operations.
|
|
2496
2512
|
*
|
|
2497
2513
|
* 2. (Upgraded) Provides specified image erasure. Users can specify multiple images at a time.
|
|
2498
2514
|
*
|
|
2499
|
-
* 3. (Upgraded) Provides specified text erasure. Users can specify multiple
|
|
2515
|
+
* 3. (Upgraded) Provides specified text erasure. Users can specify multiple text strings at a time.
|
|
2500
2516
|
*
|
|
2501
|
-
* Processing flow: The user
|
|
2517
|
+
* Processing flow: The user passes in the original image URL → OCR and VLM models detect the text or image position → Determine the coordinates of the area to be repaired → AI repairs and generates a clean image → Returns the result image URL.
|
|
2502
2518
|
* ## Effect comparison
|
|
2503
2519
|
* | **Objects that can be removed from the image** | **Original image** | **Image after erasure** |
|
|
2504
2520
|
* | --- | --- | --- |
|
|
@@ -2538,7 +2554,7 @@ export default class Client extends OpenApi {
|
|
|
2538
2554
|
* * Does not involve the image subject area
|
|
2539
2555
|
*
|
|
2540
2556
|
*  |
|
|
2541
|
-
* |
|
|
2557
|
+
* | Promotional stickers | * Involves the image subject area
|
|
2542
2558
|
*
|
|
2543
2559
|
* 
|
|
2544
2560
|
*
|
|
@@ -2551,7 +2567,7 @@ export default class Client extends OpenApi {
|
|
|
2551
2567
|
*
|
|
2552
2568
|
*  |
|
|
2553
2569
|
* | Specified image element erasure (supports multiple image links) |  |  |
|
|
2554
|
-
* | Specified text erasure (supports multiple
|
|
2570
|
+
* | Specified text erasure (supports multiple text strings) |  |  |
|
|
2555
2571
|
*
|
|
2556
2572
|
* @param request - ImageRemoveAsyncRequest
|
|
2557
2573
|
* @returns ImageRemoveAsyncResponse
|
|
@@ -2684,17 +2700,17 @@ export default class Client extends OpenApi {
|
|
|
2684
2700
|
}
|
|
2685
2701
|
|
|
2686
2702
|
/**
|
|
2687
|
-
* Translates e-commerce images by using the Mixture of Experts (
|
|
2703
|
+
* Translates e-commerce images by using the Mixture of Experts (MoE) architecture. Compared with the Lite and Pro editions, the Plus edition provides higher translation accuracy for multiple minor languages.
|
|
2688
2704
|
*
|
|
2689
2705
|
* @remarks
|
|
2690
2706
|
* ## Scenarios
|
|
2691
2707
|
* Main images and detail images for cross-border e-commerce.
|
|
2692
2708
|
* ## Features
|
|
2693
|
-
* * **Product subject information protection**: Allows you to specify whether to translate the text on the product subject. This helps you protect subject information, such as embedded product
|
|
2709
|
+
* * **Product subject information protection**: Allows you to specify whether to translate the text on the product subject. This helps you protect the subject information, such as the embedded product name, from being translated.
|
|
2694
2710
|
*
|
|
2695
|
-
* * **Brand name protection**: Allows you to specify whether to translate brand
|
|
2711
|
+
* * **Brand name protection**: Allows you to specify whether to translate the brand name in the image. This helps you protect the brand name from being translated.
|
|
2696
2712
|
*
|
|
2697
|
-
* * **Translation intervention**: Allows you to customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF),
|
|
2713
|
+
* * **Translation intervention**: Allows you to customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), and skipping translation (ABC-null). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API operation 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.
|
|
2698
2714
|
* ## Supported language pairs
|
|
2699
2715
|
* | **No.** | **Source language** | | **Target language** | |
|
|
2700
2716
|
* | --- | --- | --- | --- | --- |
|
|
@@ -2712,8 +2728,8 @@ export default class Client extends OpenApi {
|
|
|
2712
2728
|
* | 11 | en | English | de | German |
|
|
2713
2729
|
* | 12 | en | English | pl | Polish |
|
|
2714
2730
|
* ## Preparations and call process
|
|
2715
|
-
* The asynchronous API for
|
|
2716
|
-
* For the asynchronous
|
|
2731
|
+
* The asynchronous API operations for the Plus edition of image translation and other features share the same result retrieval process, RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
2732
|
+
* For the integration process of asynchronous calls, subscription rules, message formats and encryption protocols, and detailed integration solutions, refer to [Asynchronous API operation call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
2717
2733
|
*
|
|
2718
2734
|
* @param request - ImageTranslationPlusAsyncRequest
|
|
2719
2735
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -2722,6 +2738,10 @@ export default class Client extends OpenApi {
|
|
|
2722
2738
|
async imageTranslationPlusAsyncWithOptions(request: $_model.ImageTranslationPlusAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageTranslationPlusAsyncResponse> {
|
|
2723
2739
|
request.validate();
|
|
2724
2740
|
let query = { };
|
|
2741
|
+
if (!$dara.isNull(request.bizId)) {
|
|
2742
|
+
query["BizId"] = request.bizId;
|
|
2743
|
+
}
|
|
2744
|
+
|
|
2725
2745
|
if (!$dara.isNull(request.glossary)) {
|
|
2726
2746
|
query["Glossary"] = request.glossary;
|
|
2727
2747
|
}
|
|
@@ -2768,17 +2788,17 @@ export default class Client extends OpenApi {
|
|
|
2768
2788
|
}
|
|
2769
2789
|
|
|
2770
2790
|
/**
|
|
2771
|
-
* Translates e-commerce images by using the Mixture of Experts (
|
|
2791
|
+
* Translates e-commerce images by using the Mixture of Experts (MoE) architecture. Compared with the Lite and Pro editions, the Plus edition provides higher translation accuracy for multiple minor languages.
|
|
2772
2792
|
*
|
|
2773
2793
|
* @remarks
|
|
2774
2794
|
* ## Scenarios
|
|
2775
2795
|
* Main images and detail images for cross-border e-commerce.
|
|
2776
2796
|
* ## Features
|
|
2777
|
-
* * **Product subject information protection**: Allows you to specify whether to translate the text on the product subject. This helps you protect subject information, such as embedded product
|
|
2797
|
+
* * **Product subject information protection**: Allows you to specify whether to translate the text on the product subject. This helps you protect the subject information, such as the embedded product name, from being translated.
|
|
2778
2798
|
*
|
|
2779
|
-
* * **Brand name protection**: Allows you to specify whether to translate brand
|
|
2799
|
+
* * **Brand name protection**: Allows you to specify whether to translate the brand name in the image. This helps you protect the brand name from being translated.
|
|
2780
2800
|
*
|
|
2781
|
-
* * **Translation intervention**: Allows you to customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF),
|
|
2801
|
+
* * **Translation intervention**: Allows you to customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), and skipping translation (ABC-null). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API operation 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.
|
|
2782
2802
|
* ## Supported language pairs
|
|
2783
2803
|
* | **No.** | **Source language** | | **Target language** | |
|
|
2784
2804
|
* | --- | --- | --- | --- | --- |
|
|
@@ -2796,8 +2816,8 @@ export default class Client extends OpenApi {
|
|
|
2796
2816
|
* | 11 | en | English | de | German |
|
|
2797
2817
|
* | 12 | en | English | pl | Polish |
|
|
2798
2818
|
* ## Preparations and call process
|
|
2799
|
-
* The asynchronous API for
|
|
2800
|
-
* For the asynchronous
|
|
2819
|
+
* The asynchronous API operations for the Plus edition of image translation and other features share the same result retrieval process, RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
2820
|
+
* For the integration process of asynchronous calls, subscription rules, message formats and encryption protocols, and detailed integration solutions, refer to [Asynchronous API operation call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
2801
2821
|
*
|
|
2802
2822
|
* @param request - ImageTranslationPlusAsyncRequest
|
|
2803
2823
|
* @returns ImageTranslationPlusAsyncResponse
|
|
@@ -2902,23 +2922,23 @@ export default class Client extends OpenApi {
|
|
|
2902
2922
|
}
|
|
2903
2923
|
|
|
2904
2924
|
/**
|
|
2905
|
-
* Translates images by using Image Translation Pro.
|
|
2925
|
+
* Translates images asynchronously by using Image Translation Pro. Designed for e-commerce images, this service integrates multimodal large language models to achieve more accurate image understanding, significantly improve translation quality, and continuously expand and optimize multilingual translation capabilities. It supports more than 400 language pairs, including bridged language pairs.
|
|
2906
2926
|
*
|
|
2907
2927
|
* @remarks
|
|
2908
2928
|
* ## Scenarios
|
|
2909
2929
|
* E-commerce product images, marketing images, and images in various other scenarios.
|
|
2910
2930
|
* ## Features
|
|
2911
|
-
* * Product subject information protection:
|
|
2931
|
+
* * Product subject information protection: You can specify whether to translate the text on the product subject. This helps you protect the subject information, such as the embedded product name, from being translated.
|
|
2912
2932
|
*
|
|
2913
|
-
* *
|
|
2933
|
+
* * Secondary editing after translation: You can specify whether to return layout information such as the position, font, and color of the text. This information can be used for secondary editing when you integrate an image editor. The SDK package for the editor is not yet available. Follow platform notifications for updates.
|
|
2914
2934
|
*
|
|
2915
|
-
* * Brand name protection:
|
|
2935
|
+
* * Brand name protection: You can specify whether to translate brand names in the image. This helps you protect brand name information from being translated.
|
|
2916
2936
|
*
|
|
2917
|
-
* * Translation intervention:
|
|
2937
|
+
* * Translation intervention: You can customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), or omitting the translation (ABC-null). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API, which meets your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention entries. If you need more, contact the platform for assistance.
|
|
2918
2938
|
* ## Preparations and call process
|
|
2919
|
-
* Image Translation Pro supports both synchronous and asynchronous
|
|
2920
|
-
* The asynchronous APIs for text translation and other capabilities share the result retrieval process,
|
|
2921
|
-
* For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls,
|
|
2939
|
+
* Image Translation Pro supports both synchronous and asynchronous calls. This topic describes the asynchronous call API. For synchronous calls, see [Image Translation Pro](https://www.alibabacloud.com/help/en/aidge/image-translation-pro).
|
|
2940
|
+
* The asynchronous APIs for text translation and other capabilities share the same result retrieval process, RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
2941
|
+
* For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls, see [Asynchronous API call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
2922
2942
|
*
|
|
2923
2943
|
* @param request - ImageTranslationProAsyncRequest
|
|
2924
2944
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -2927,6 +2947,10 @@ export default class Client extends OpenApi {
|
|
|
2927
2947
|
async imageTranslationProAsyncWithOptions(request: $_model.ImageTranslationProAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageTranslationProAsyncResponse> {
|
|
2928
2948
|
request.validate();
|
|
2929
2949
|
let query = { };
|
|
2950
|
+
if (!$dara.isNull(request.bizId)) {
|
|
2951
|
+
query["BizId"] = request.bizId;
|
|
2952
|
+
}
|
|
2953
|
+
|
|
2930
2954
|
if (!$dara.isNull(request.glossary)) {
|
|
2931
2955
|
query["Glossary"] = request.glossary;
|
|
2932
2956
|
}
|
|
@@ -2973,23 +2997,23 @@ export default class Client extends OpenApi {
|
|
|
2973
2997
|
}
|
|
2974
2998
|
|
|
2975
2999
|
/**
|
|
2976
|
-
* Translates images by using Image Translation Pro.
|
|
3000
|
+
* Translates images asynchronously by using Image Translation Pro. Designed for e-commerce images, this service integrates multimodal large language models to achieve more accurate image understanding, significantly improve translation quality, and continuously expand and optimize multilingual translation capabilities. It supports more than 400 language pairs, including bridged language pairs.
|
|
2977
3001
|
*
|
|
2978
3002
|
* @remarks
|
|
2979
3003
|
* ## Scenarios
|
|
2980
3004
|
* E-commerce product images, marketing images, and images in various other scenarios.
|
|
2981
3005
|
* ## Features
|
|
2982
|
-
* * Product subject information protection:
|
|
3006
|
+
* * Product subject information protection: You can specify whether to translate the text on the product subject. This helps you protect the subject information, such as the embedded product name, from being translated.
|
|
2983
3007
|
*
|
|
2984
|
-
* *
|
|
3008
|
+
* * Secondary editing after translation: You can specify whether to return layout information such as the position, font, and color of the text. This information can be used for secondary editing when you integrate an image editor. The SDK package for the editor is not yet available. Follow platform notifications for updates.
|
|
2985
3009
|
*
|
|
2986
|
-
* * Brand name protection:
|
|
3010
|
+
* * Brand name protection: You can specify whether to translate brand names in the image. This helps you protect brand name information from being translated.
|
|
2987
3011
|
*
|
|
2988
|
-
* * Translation intervention:
|
|
3012
|
+
* * Translation intervention: You can customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), or omitting the translation (ABC-null). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API, which meets your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention entries. If you need more, contact the platform for assistance.
|
|
2989
3013
|
* ## Preparations and call process
|
|
2990
|
-
* Image Translation Pro supports both synchronous and asynchronous
|
|
2991
|
-
* The asynchronous APIs for text translation and other capabilities share the result retrieval process,
|
|
2992
|
-
* For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls,
|
|
3014
|
+
* Image Translation Pro supports both synchronous and asynchronous calls. This topic describes the asynchronous call API. For synchronous calls, see [Image Translation Pro](https://www.alibabacloud.com/help/en/aidge/image-translation-pro).
|
|
3015
|
+
* The asynchronous APIs for text translation and other capabilities share the same result retrieval process, RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
3016
|
+
* For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls, see [Asynchronous API call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
2993
3017
|
*
|
|
2994
3018
|
* @param request - ImageTranslationProAsyncRequest
|
|
2995
3019
|
* @returns ImageTranslationProAsyncResponse
|
|
@@ -3096,23 +3120,23 @@ export default class Client extends OpenApi {
|
|
|
3096
3120
|
}
|
|
3097
3121
|
|
|
3098
3122
|
/**
|
|
3099
|
-
* Translates e-commerce
|
|
3123
|
+
* Translates images specifically designed for e-commerce, supporting over 400 language pairs, including bridged pairs. It accurately processes complex text layouts within images and ensures that the translated content matches the image context. This helps e-commerce platforms and developers easily achieve multilingual conversion and presentation of image content. Additionally, the service returns layer information such as the position, font, and color of text in the image, which facilitates secondary editing of translation results by using image editors.
|
|
3100
3124
|
*
|
|
3101
3125
|
* @remarks
|
|
3102
3126
|
* ## Scenarios
|
|
3103
3127
|
* E-commerce product images, marketing images, and images for various other scenarios.
|
|
3104
3128
|
* ## Features
|
|
3105
|
-
* * **Product subject information protection**: Allows you to specify whether to translate text on the product subject
|
|
3129
|
+
* * **Product subject information protection**: Allows you to specify whether to translate the text on the product subject. This helps protect the subject information from being translated and prevents the translation of embedded information such as product names.
|
|
3106
3130
|
*
|
|
3107
|
-
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image
|
|
3131
|
+
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image. This helps protect brand name information from being translated.
|
|
3108
3132
|
*
|
|
3109
|
-
* * **Secondary editing after translation (layer information)**: Allows you to specify whether to return layer information such as
|
|
3133
|
+
* * **Secondary editing after translation (layer information)**: Allows you to specify whether to return layer information such as the position, font, and color of the text. This information can be used to integrate with image editors for secondary editing of translation results. For the release progress of the editor SDK package, refer to platform notifications.
|
|
3110
3134
|
*
|
|
3111
|
-
* * **Translation intervention**: Allows you to customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), and skipping translation (ABC-null 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
|
|
3135
|
+
* * **Translation intervention**: Allows you to customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), and skipping translation (ABC-null value). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API operation to meet your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention entries. If you need more, contact the platform for assistance.
|
|
3112
3136
|
* ## Preparations and call process
|
|
3113
|
-
* * Image Translation
|
|
3114
|
-
* * The asynchronous
|
|
3115
|
-
* * For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls, refer to [Asynchronous API call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
3137
|
+
* * The standard edition of Image Translation supports both synchronous and asynchronous call methods. This topic describes the asynchronous call API operation. To use synchronous calls, refer to [Image Translation Standard Edition](https://www.alibabacloud.com/help/en/aidge/image-translation).
|
|
3138
|
+
* * The asynchronous API operations for the standard edition of Image Translation and other features share the result retrieval process, ApsaraMQ for RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
3139
|
+
* * For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls, refer to [Asynchronous API operation call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
3116
3140
|
*
|
|
3117
3141
|
* @param request - ImageTranslationStandardAsyncRequest
|
|
3118
3142
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -3121,6 +3145,10 @@ export default class Client extends OpenApi {
|
|
|
3121
3145
|
async imageTranslationStandardAsyncWithOptions(request: $_model.ImageTranslationStandardAsyncRequest, runtime: $dara.RuntimeOptions): Promise<$_model.ImageTranslationStandardAsyncResponse> {
|
|
3122
3146
|
request.validate();
|
|
3123
3147
|
let query = { };
|
|
3148
|
+
if (!$dara.isNull(request.bizId)) {
|
|
3149
|
+
query["BizId"] = request.bizId;
|
|
3150
|
+
}
|
|
3151
|
+
|
|
3124
3152
|
if (!$dara.isNull(request.glossary)) {
|
|
3125
3153
|
query["Glossary"] = request.glossary;
|
|
3126
3154
|
}
|
|
@@ -3167,23 +3195,23 @@ export default class Client extends OpenApi {
|
|
|
3167
3195
|
}
|
|
3168
3196
|
|
|
3169
3197
|
/**
|
|
3170
|
-
* Translates e-commerce
|
|
3198
|
+
* Translates images specifically designed for e-commerce, supporting over 400 language pairs, including bridged pairs. It accurately processes complex text layouts within images and ensures that the translated content matches the image context. This helps e-commerce platforms and developers easily achieve multilingual conversion and presentation of image content. Additionally, the service returns layer information such as the position, font, and color of text in the image, which facilitates secondary editing of translation results by using image editors.
|
|
3171
3199
|
*
|
|
3172
3200
|
* @remarks
|
|
3173
3201
|
* ## Scenarios
|
|
3174
3202
|
* E-commerce product images, marketing images, and images for various other scenarios.
|
|
3175
3203
|
* ## Features
|
|
3176
|
-
* * **Product subject information protection**: Allows you to specify whether to translate text on the product subject
|
|
3204
|
+
* * **Product subject information protection**: Allows you to specify whether to translate the text on the product subject. This helps protect the subject information from being translated and prevents the translation of embedded information such as product names.
|
|
3177
3205
|
*
|
|
3178
|
-
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image
|
|
3206
|
+
* * **Brand name protection**: Allows you to specify whether to translate brand names in the image. This helps protect brand name information from being translated.
|
|
3179
3207
|
*
|
|
3180
|
-
* * **Secondary editing after translation (layer information)**: Allows you to specify whether to return layer information such as
|
|
3208
|
+
* * **Secondary editing after translation (layer information)**: Allows you to specify whether to return layer information such as the position, font, and color of the text. This information can be used to integrate with image editors for secondary editing of translation results. For the release progress of the editor SDK package, refer to platform notifications.
|
|
3181
3209
|
*
|
|
3182
|
-
* * **Translation intervention**: Allows you to customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), and skipping translation (ABC-null 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
|
|
3210
|
+
* * **Translation intervention**: Allows you to customize translation results, including keeping the original text (ABC-ABC), specifying a translation (ABC-DEF), and skipping translation (ABC-null value). This is commonly used in scenarios such as brand word protection. You can implement this by passing the corresponding intervention glossary ID when calling the API operation to meet your translation needs in different scenarios. Generally, you can upload up to 100,000 intervention entries. If you need more, contact the platform for assistance.
|
|
3183
3211
|
* ## Preparations and call process
|
|
3184
|
-
* * Image Translation
|
|
3185
|
-
* * The asynchronous
|
|
3186
|
-
* * For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls, refer to [Asynchronous API call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
3212
|
+
* * The standard edition of Image Translation supports both synchronous and asynchronous call methods. This topic describes the asynchronous call API operation. To use synchronous calls, refer to [Image Translation Standard Edition](https://www.alibabacloud.com/help/en/aidge/image-translation).
|
|
3213
|
+
* * The asynchronous API operations for the standard edition of Image Translation and other features share the result retrieval process, ApsaraMQ for RocketMQ subscription rules, message encryption protocols, dependency configurations, and Java consumption and decryption code.
|
|
3214
|
+
* * For the integration process, subscription rules, message formats and encryption protocols, and detailed integration solutions for asynchronous calls, refer to [Asynchronous API operation call instructions](https://www.alibabacloud.com/help/en/aidge/asynchronous-interface-call-instructions).
|
|
3187
3215
|
*
|
|
3188
3216
|
* @param request - ImageTranslationStandardAsyncRequest
|
|
3189
3217
|
* @returns ImageTranslationStandardAsyncResponse
|
|
@@ -4160,10 +4188,10 @@ export default class Client extends OpenApi {
|
|
|
4160
4188
|
}
|
|
4161
4189
|
|
|
4162
4190
|
/**
|
|
4163
|
-
* API name
|
|
4191
|
+
* Queries the result of an asynchronous task. The API name in the POP gateway is QueryAsyncTaskResult.
|
|
4164
4192
|
*
|
|
4165
4193
|
* @remarks
|
|
4166
|
-
* API name
|
|
4194
|
+
* The API name in the POP gateway is QueryAsyncTaskResult.
|
|
4167
4195
|
*
|
|
4168
4196
|
* @param request - QueryAsyncTaskResultRequest
|
|
4169
4197
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -4194,10 +4222,10 @@ export default class Client extends OpenApi {
|
|
|
4194
4222
|
}
|
|
4195
4223
|
|
|
4196
4224
|
/**
|
|
4197
|
-
* API name
|
|
4225
|
+
* Queries the result of an asynchronous task. The API name in the POP gateway is QueryAsyncTaskResult.
|
|
4198
4226
|
*
|
|
4199
4227
|
* @remarks
|
|
4200
|
-
* API name
|
|
4228
|
+
* The API name in the POP gateway is QueryAsyncTaskResult.
|
|
4201
4229
|
*
|
|
4202
4230
|
* @param request - QueryAsyncTaskResultRequest
|
|
4203
4231
|
* @returns QueryAsyncTaskResultResponse
|
|
@@ -4646,105 +4674,105 @@ export default class Client extends OpenApi {
|
|
|
4646
4674
|
}
|
|
4647
4675
|
|
|
4648
4676
|
/**
|
|
4649
|
-
* Extracts structured information such as size charts and package weight and dimensions from images by using multimodal large models in asynchronous mode.
|
|
4677
|
+
* Extracts structured information such as size charts and package weight and dimensions from images by using multimodal large language models in asynchronous mode.
|
|
4650
4678
|
*
|
|
4651
4679
|
* @remarks
|
|
4652
4680
|
* ## Scenarios
|
|
4653
|
-
* Size charts:
|
|
4654
|
-
* Package weight and dimensions:
|
|
4681
|
+
* Size charts: extracts size charts of apparel categories into text.
|
|
4682
|
+
* Package weight and dimensions: extracts package weight and dimension information from images.
|
|
4655
4683
|
* ## Feature description
|
|
4656
|
-
* The size chart extraction service is based on multimodal
|
|
4657
|
-
* Core capabilities:
|
|
4658
|
-
* ##
|
|
4684
|
+
* The size chart extraction service is based on multimodal large language models. It automatically recognizes size charts or package weight and dimension information in images and converts the information into structured text. You provide an image URL, and the system processes the request as an asynchronous task and returns the extracted structured data. You can specify the column names to be recognized, such as Size, Bust, and Length, by using ColumnNameList to achieve precise and targeted extraction. You can also control the output language by using the LanguageModel parameter. Valid values: cn for Chinese and en for English. If you do not specify this parameter, the original language is retained. This service is applicable to scenarios such as text conversion of size charts for apparel categories and batch structuring of package weight and dimension information for commodities.
|
|
4685
|
+
* Core capabilities: You can input an image URL and optional column name configurations to output the structured data of the size chart or package weight and dimensions in the image. The API operation uses the asynchronous task mode (background: true). After you submit the task, a task ID is returned. You must poll the task to obtain the final result. This mode is suitable for processing complex images or handling a large number of calls.
|
|
4686
|
+
* ## Comparison
|
|
4659
4687
|
* | Input image | Output result |
|
|
4660
4688
|
* | --- | --- |
|
|
4661
4689
|
* |  | {
|
|
4662
4690
|
* "SizeChart": [
|
|
4663
4691
|
* {
|
|
4664
|
-
* "
|
|
4692
|
+
* "Size": {
|
|
4665
4693
|
* "value": "S"
|
|
4666
4694
|
* },
|
|
4667
|
-
* "
|
|
4695
|
+
* "Waist": {
|
|
4668
4696
|
* "unit": "CM",
|
|
4669
4697
|
* "value": 58
|
|
4670
4698
|
* },
|
|
4671
|
-
* "
|
|
4699
|
+
* "Skirt length": {
|
|
4672
4700
|
* "unit": "CM",
|
|
4673
4701
|
* "value": 81
|
|
4674
4702
|
* },
|
|
4675
|
-
* "
|
|
4703
|
+
* "Weight recommendation": {
|
|
4676
4704
|
* "unit": "kg",
|
|
4677
4705
|
* "lower_value": 40,
|
|
4678
4706
|
* "upper_value": 47.5
|
|
4679
4707
|
* }
|
|
4680
4708
|
* },
|
|
4681
4709
|
* {
|
|
4682
|
-
* "
|
|
4710
|
+
* "Size": {
|
|
4683
4711
|
* "value": "M"
|
|
4684
4712
|
* },
|
|
4685
|
-
* "
|
|
4713
|
+
* "Waist": {
|
|
4686
4714
|
* "unit": "CM",
|
|
4687
4715
|
* "value": 59
|
|
4688
4716
|
* },
|
|
4689
|
-
* "
|
|
4717
|
+
* "Skirt length": {
|
|
4690
4718
|
* "unit": "CM",
|
|
4691
4719
|
* "value": 82
|
|
4692
4720
|
* },
|
|
4693
|
-
* "
|
|
4721
|
+
* "Weight recommendation": {
|
|
4694
4722
|
* "unit": "kg",
|
|
4695
4723
|
* "lower_value": 45,
|
|
4696
4724
|
* "upper_value": 52.5
|
|
4697
4725
|
* }
|
|
4698
4726
|
* },
|
|
4699
4727
|
* {
|
|
4700
|
-
* "
|
|
4728
|
+
* "Size": {
|
|
4701
4729
|
* "value": "L"
|
|
4702
4730
|
* },
|
|
4703
|
-
* "
|
|
4731
|
+
* "Waist": {
|
|
4704
4732
|
* "unit": "CM",
|
|
4705
4733
|
* "value": 60
|
|
4706
4734
|
* },
|
|
4707
|
-
* "
|
|
4735
|
+
* "Skirt length": {
|
|
4708
4736
|
* "unit": "CM",
|
|
4709
4737
|
* "value": 83
|
|
4710
4738
|
* },
|
|
4711
|
-
* "
|
|
4739
|
+
* "Weight recommendation": {
|
|
4712
4740
|
* "unit": "kg",
|
|
4713
4741
|
* "lower_value": 50,
|
|
4714
4742
|
* "upper_value": 57.5
|
|
4715
4743
|
* }
|
|
4716
4744
|
* },
|
|
4717
4745
|
* {
|
|
4718
|
-
* "
|
|
4746
|
+
* "Size": {
|
|
4719
4747
|
* "value": "XL"
|
|
4720
4748
|
* },
|
|
4721
|
-
* "
|
|
4749
|
+
* "Waist": {
|
|
4722
4750
|
* "unit": "CM",
|
|
4723
4751
|
* "value": 61
|
|
4724
4752
|
* },
|
|
4725
|
-
* "
|
|
4753
|
+
* "Skirt length": {
|
|
4726
4754
|
* "unit": "CM",
|
|
4727
4755
|
* "value": 84
|
|
4728
4756
|
* },
|
|
4729
|
-
* "
|
|
4757
|
+
* "Weight recommendation": {
|
|
4730
4758
|
* "unit": "kg",
|
|
4731
4759
|
* "lower_value": 55,
|
|
4732
4760
|
* "upper_value": 62.5
|
|
4733
4761
|
* }
|
|
4734
4762
|
* },
|
|
4735
4763
|
* {
|
|
4736
|
-
* "
|
|
4764
|
+
* "Size": {
|
|
4737
4765
|
* "value": "2XL"
|
|
4738
4766
|
* },
|
|
4739
|
-
* "
|
|
4767
|
+
* "Waist": {
|
|
4740
4768
|
* "unit": "CM",
|
|
4741
4769
|
* "value": 62
|
|
4742
4770
|
* },
|
|
4743
|
-
* "
|
|
4771
|
+
* "Skirt length": {
|
|
4744
4772
|
* "unit": "CM",
|
|
4745
4773
|
* "value": 85
|
|
4746
4774
|
* },
|
|
4747
|
-
* "
|
|
4775
|
+
* "Weight recommendation": {
|
|
4748
4776
|
* "unit": "kg",
|
|
4749
4777
|
* "lower_value": 60,
|
|
4750
4778
|
* "upper_value": 67.5
|
|
@@ -4778,6 +4806,10 @@ export default class Client extends OpenApi {
|
|
|
4778
4806
|
}
|
|
4779
4807
|
|
|
4780
4808
|
let query = { };
|
|
4809
|
+
if (!$dara.isNull(request.bizId)) {
|
|
4810
|
+
query["BizId"] = request.bizId;
|
|
4811
|
+
}
|
|
4812
|
+
|
|
4781
4813
|
if (!$dara.isNull(request.columnNameListShrink)) {
|
|
4782
4814
|
query["ColumnNameList"] = request.columnNameListShrink;
|
|
4783
4815
|
}
|
|
@@ -4808,105 +4840,105 @@ export default class Client extends OpenApi {
|
|
|
4808
4840
|
}
|
|
4809
4841
|
|
|
4810
4842
|
/**
|
|
4811
|
-
* Extracts structured information such as size charts and package weight and dimensions from images by using multimodal large models in asynchronous mode.
|
|
4843
|
+
* Extracts structured information such as size charts and package weight and dimensions from images by using multimodal large language models in asynchronous mode.
|
|
4812
4844
|
*
|
|
4813
4845
|
* @remarks
|
|
4814
4846
|
* ## Scenarios
|
|
4815
|
-
* Size charts:
|
|
4816
|
-
* Package weight and dimensions:
|
|
4847
|
+
* Size charts: extracts size charts of apparel categories into text.
|
|
4848
|
+
* Package weight and dimensions: extracts package weight and dimension information from images.
|
|
4817
4849
|
* ## Feature description
|
|
4818
|
-
* The size chart extraction service is based on multimodal
|
|
4819
|
-
* Core capabilities:
|
|
4820
|
-
* ##
|
|
4850
|
+
* The size chart extraction service is based on multimodal large language models. It automatically recognizes size charts or package weight and dimension information in images and converts the information into structured text. You provide an image URL, and the system processes the request as an asynchronous task and returns the extracted structured data. You can specify the column names to be recognized, such as Size, Bust, and Length, by using ColumnNameList to achieve precise and targeted extraction. You can also control the output language by using the LanguageModel parameter. Valid values: cn for Chinese and en for English. If you do not specify this parameter, the original language is retained. This service is applicable to scenarios such as text conversion of size charts for apparel categories and batch structuring of package weight and dimension information for commodities.
|
|
4851
|
+
* Core capabilities: You can input an image URL and optional column name configurations to output the structured data of the size chart or package weight and dimensions in the image. The API operation uses the asynchronous task mode (background: true). After you submit the task, a task ID is returned. You must poll the task to obtain the final result. This mode is suitable for processing complex images or handling a large number of calls.
|
|
4852
|
+
* ## Comparison
|
|
4821
4853
|
* | Input image | Output result |
|
|
4822
4854
|
* | --- | --- |
|
|
4823
4855
|
* |  | {
|
|
4824
4856
|
* "SizeChart": [
|
|
4825
4857
|
* {
|
|
4826
|
-
* "
|
|
4858
|
+
* "Size": {
|
|
4827
4859
|
* "value": "S"
|
|
4828
4860
|
* },
|
|
4829
|
-
* "
|
|
4861
|
+
* "Waist": {
|
|
4830
4862
|
* "unit": "CM",
|
|
4831
4863
|
* "value": 58
|
|
4832
4864
|
* },
|
|
4833
|
-
* "
|
|
4865
|
+
* "Skirt length": {
|
|
4834
4866
|
* "unit": "CM",
|
|
4835
4867
|
* "value": 81
|
|
4836
4868
|
* },
|
|
4837
|
-
* "
|
|
4869
|
+
* "Weight recommendation": {
|
|
4838
4870
|
* "unit": "kg",
|
|
4839
4871
|
* "lower_value": 40,
|
|
4840
4872
|
* "upper_value": 47.5
|
|
4841
4873
|
* }
|
|
4842
4874
|
* },
|
|
4843
4875
|
* {
|
|
4844
|
-
* "
|
|
4876
|
+
* "Size": {
|
|
4845
4877
|
* "value": "M"
|
|
4846
4878
|
* },
|
|
4847
|
-
* "
|
|
4879
|
+
* "Waist": {
|
|
4848
4880
|
* "unit": "CM",
|
|
4849
4881
|
* "value": 59
|
|
4850
4882
|
* },
|
|
4851
|
-
* "
|
|
4883
|
+
* "Skirt length": {
|
|
4852
4884
|
* "unit": "CM",
|
|
4853
4885
|
* "value": 82
|
|
4854
4886
|
* },
|
|
4855
|
-
* "
|
|
4887
|
+
* "Weight recommendation": {
|
|
4856
4888
|
* "unit": "kg",
|
|
4857
4889
|
* "lower_value": 45,
|
|
4858
4890
|
* "upper_value": 52.5
|
|
4859
4891
|
* }
|
|
4860
4892
|
* },
|
|
4861
4893
|
* {
|
|
4862
|
-
* "
|
|
4894
|
+
* "Size": {
|
|
4863
4895
|
* "value": "L"
|
|
4864
4896
|
* },
|
|
4865
|
-
* "
|
|
4897
|
+
* "Waist": {
|
|
4866
4898
|
* "unit": "CM",
|
|
4867
4899
|
* "value": 60
|
|
4868
4900
|
* },
|
|
4869
|
-
* "
|
|
4901
|
+
* "Skirt length": {
|
|
4870
4902
|
* "unit": "CM",
|
|
4871
4903
|
* "value": 83
|
|
4872
4904
|
* },
|
|
4873
|
-
* "
|
|
4905
|
+
* "Weight recommendation": {
|
|
4874
4906
|
* "unit": "kg",
|
|
4875
4907
|
* "lower_value": 50,
|
|
4876
4908
|
* "upper_value": 57.5
|
|
4877
4909
|
* }
|
|
4878
4910
|
* },
|
|
4879
4911
|
* {
|
|
4880
|
-
* "
|
|
4912
|
+
* "Size": {
|
|
4881
4913
|
* "value": "XL"
|
|
4882
4914
|
* },
|
|
4883
|
-
* "
|
|
4915
|
+
* "Waist": {
|
|
4884
4916
|
* "unit": "CM",
|
|
4885
4917
|
* "value": 61
|
|
4886
4918
|
* },
|
|
4887
|
-
* "
|
|
4919
|
+
* "Skirt length": {
|
|
4888
4920
|
* "unit": "CM",
|
|
4889
4921
|
* "value": 84
|
|
4890
4922
|
* },
|
|
4891
|
-
* "
|
|
4923
|
+
* "Weight recommendation": {
|
|
4892
4924
|
* "unit": "kg",
|
|
4893
4925
|
* "lower_value": 55,
|
|
4894
4926
|
* "upper_value": 62.5
|
|
4895
4927
|
* }
|
|
4896
4928
|
* },
|
|
4897
4929
|
* {
|
|
4898
|
-
* "
|
|
4930
|
+
* "Size": {
|
|
4899
4931
|
* "value": "2XL"
|
|
4900
4932
|
* },
|
|
4901
|
-
* "
|
|
4933
|
+
* "Waist": {
|
|
4902
4934
|
* "unit": "CM",
|
|
4903
4935
|
* "value": 62
|
|
4904
4936
|
* },
|
|
4905
|
-
* "
|
|
4937
|
+
* "Skirt length": {
|
|
4906
4938
|
* "unit": "CM",
|
|
4907
4939
|
* "value": 85
|
|
4908
4940
|
* },
|
|
4909
|
-
* "
|
|
4941
|
+
* "Weight recommendation": {
|
|
4910
4942
|
* "unit": "kg",
|
|
4911
4943
|
* "lower_value": 60,
|
|
4912
4944
|
* "upper_value": 67.5
|
|
@@ -5564,28 +5596,28 @@ export default class Client extends OpenApi {
|
|
|
5564
5596
|
}
|
|
5565
5597
|
|
|
5566
5598
|
/**
|
|
5567
|
-
* Translates the speech and on-screen text in a video into a target language. You can select speech subtitle translation, on-screen text translation, or both. This API applies to scenarios such as multilingual distribution of e-commerce videos, international social media marketing, and global brand advertising. The API uses an asynchronous invocation mode. After you submit a translation task, you can obtain the
|
|
5599
|
+
* Translates the speech and on-screen text in a video into a target language. You can select speech subtitle translation, on-screen text translation, or both. This API applies to scenarios such as multilingual distribution of e-commerce videos, international social media marketing, and global brand advertising. The API uses an asynchronous invocation mode. After you submit a translation task, you can obtain the TaskId and poll the task status by calling the query API until the task is completed and the result is returned.
|
|
5568
5600
|
*
|
|
5569
5601
|
* @remarks
|
|
5570
5602
|
* ## Product introduction
|
|
5571
5603
|
* The video translation API translates the speech and on-screen text in a video into a target language. You can select speech subtitle translation, on-screen text translation, or both. This API applies to scenarios such as multilingual distribution of e-commerce videos, international social media marketing, and global brand advertising.
|
|
5572
|
-
* The API uses an asynchronous invocation mode. After you submit a translation task, you can obtain the
|
|
5604
|
+
* The API uses an asynchronous invocation mode. After you submit a translation task, you can obtain the TaskId and poll the task status by calling the query API until the task is completed and the result is returned.
|
|
5573
5605
|
* ## Scenarios
|
|
5574
|
-
* * **Cross-border e-commerce video localization**: Translates the selling point text in product introduction videos into the language of the target market to
|
|
5606
|
+
* * **Cross-border e-commerce video localization**: Translates the speech subtitles and selling point text in product introduction videos into the language of the target market to promote products on overseas platforms.
|
|
5575
5607
|
*
|
|
5576
|
-
* * **International social media marketing**: Localizes
|
|
5608
|
+
* * **International social media marketing**: Localizes speech subtitles and on-screen text for platforms such as TikTok, Instagram, and YouTube with one click to improve comprehension and conversion rates among overseas users.
|
|
5577
5609
|
*
|
|
5578
|
-
* * **Global brand advertising**: Automatically generates video versions in the languages
|
|
5610
|
+
* * **Global brand advertising**: Automatically generates video versions in the corresponding languages based on the delivery regions to reduce manual production costs.
|
|
5579
5611
|
*
|
|
5580
|
-
* * **Training and product instructions**: Translates the on-screen text in training courses or product demo videos into multiple languages for global teams.
|
|
5612
|
+
* * **Training and product instructions**: Translates the speech subtitles and on-screen text in training courses or product demo videos into multiple languages for global teams.
|
|
5581
5613
|
* ## Features
|
|
5582
5614
|
* | Feature | Identifier | Description |
|
|
5583
5615
|
* | --- | --- | --- |
|
|
5584
|
-
* | Speech subtitle translation |
|
|
5585
|
-
* | On-screen text translation |
|
|
5586
|
-
* Speech subtitle translation (
|
|
5587
|
-
* On-screen text translation (
|
|
5588
|
-
* When both
|
|
5616
|
+
* | Speech subtitle translation | speech | Translates the video speech into target language dubbing. You can choose to erase the original subtitles only or replace them with translated subtitles. By default, the original subtitles are not processed and no new subtitles are added. |
|
|
5617
|
+
* | On-screen text translation | visual | Translates the source language text in the video frames, or erases the on-screen text without translation. You can choose to erase brand logos. |
|
|
5618
|
+
* Speech subtitle translation (speech) generates target language dubbing based on the spoken content in the video, processes the subtitles based on the original subtitle processing option, and synthesizes the final video. Original subtitles refer to the existing subtitles in the video frames that correspond to the spoken content. Replacing with translated subtitles erases the original subtitles first and then adds subtitles synchronized with the translated speech.
|
|
5619
|
+
* On-screen text translation (visual) targets recognizable original video language text in the video frames, such as titles, product selling points, and descriptive text. It can be used independently without selecting speech subtitle translation first, and does not require the text to appear in the speech. Original subtitles within the processing scope may also be processed.
|
|
5620
|
+
* When both speech and visual are selected, the speech subtitle translation is completed and the video is synthesized first, and then the on-screen text processing is performed on this video. The translated dubbing is retained, and a final video is output. The order of features in the array does not affect the execution order. Therefore, not processing original subtitles only means that no subtitles are erased or added during the speech subtitle phase, and subsequent on-screen text processing may still change the original subtitles. Subtitles that have been replaced with translated subtitles are retained during subsequent on-screen text processing.
|
|
5589
5621
|
*
|
|
5590
5622
|
* @param tmpReq - VideoTranslationRequest
|
|
5591
5623
|
* @param runtime - runtime options for this request RuntimeOptions
|
|
@@ -5652,28 +5684,28 @@ export default class Client extends OpenApi {
|
|
|
5652
5684
|
}
|
|
5653
5685
|
|
|
5654
5686
|
/**
|
|
5655
|
-
* Translates the speech and on-screen text in a video into a target language. You can select speech subtitle translation, on-screen text translation, or both. This API applies to scenarios such as multilingual distribution of e-commerce videos, international social media marketing, and global brand advertising. The API uses an asynchronous invocation mode. After you submit a translation task, you can obtain the
|
|
5687
|
+
* Translates the speech and on-screen text in a video into a target language. You can select speech subtitle translation, on-screen text translation, or both. This API applies to scenarios such as multilingual distribution of e-commerce videos, international social media marketing, and global brand advertising. The API uses an asynchronous invocation mode. After you submit a translation task, you can obtain the TaskId and poll the task status by calling the query API until the task is completed and the result is returned.
|
|
5656
5688
|
*
|
|
5657
5689
|
* @remarks
|
|
5658
5690
|
* ## Product introduction
|
|
5659
5691
|
* The video translation API translates the speech and on-screen text in a video into a target language. You can select speech subtitle translation, on-screen text translation, or both. This API applies to scenarios such as multilingual distribution of e-commerce videos, international social media marketing, and global brand advertising.
|
|
5660
|
-
* The API uses an asynchronous invocation mode. After you submit a translation task, you can obtain the
|
|
5692
|
+
* The API uses an asynchronous invocation mode. After you submit a translation task, you can obtain the TaskId and poll the task status by calling the query API until the task is completed and the result is returned.
|
|
5661
5693
|
* ## Scenarios
|
|
5662
|
-
* * **Cross-border e-commerce video localization**: Translates the selling point text in product introduction videos into the language of the target market to
|
|
5694
|
+
* * **Cross-border e-commerce video localization**: Translates the speech subtitles and selling point text in product introduction videos into the language of the target market to promote products on overseas platforms.
|
|
5663
5695
|
*
|
|
5664
|
-
* * **International social media marketing**: Localizes
|
|
5696
|
+
* * **International social media marketing**: Localizes speech subtitles and on-screen text for platforms such as TikTok, Instagram, and YouTube with one click to improve comprehension and conversion rates among overseas users.
|
|
5665
5697
|
*
|
|
5666
|
-
* * **Global brand advertising**: Automatically generates video versions in the languages
|
|
5698
|
+
* * **Global brand advertising**: Automatically generates video versions in the corresponding languages based on the delivery regions to reduce manual production costs.
|
|
5667
5699
|
*
|
|
5668
|
-
* * **Training and product instructions**: Translates the on-screen text in training courses or product demo videos into multiple languages for global teams.
|
|
5700
|
+
* * **Training and product instructions**: Translates the speech subtitles and on-screen text in training courses or product demo videos into multiple languages for global teams.
|
|
5669
5701
|
* ## Features
|
|
5670
5702
|
* | Feature | Identifier | Description |
|
|
5671
5703
|
* | --- | --- | --- |
|
|
5672
|
-
* | Speech subtitle translation |
|
|
5673
|
-
* | On-screen text translation |
|
|
5674
|
-
* Speech subtitle translation (
|
|
5675
|
-
* On-screen text translation (
|
|
5676
|
-
* When both
|
|
5704
|
+
* | Speech subtitle translation | speech | Translates the video speech into target language dubbing. You can choose to erase the original subtitles only or replace them with translated subtitles. By default, the original subtitles are not processed and no new subtitles are added. |
|
|
5705
|
+
* | On-screen text translation | visual | Translates the source language text in the video frames, or erases the on-screen text without translation. You can choose to erase brand logos. |
|
|
5706
|
+
* Speech subtitle translation (speech) generates target language dubbing based on the spoken content in the video, processes the subtitles based on the original subtitle processing option, and synthesizes the final video. Original subtitles refer to the existing subtitles in the video frames that correspond to the spoken content. Replacing with translated subtitles erases the original subtitles first and then adds subtitles synchronized with the translated speech.
|
|
5707
|
+
* On-screen text translation (visual) targets recognizable original video language text in the video frames, such as titles, product selling points, and descriptive text. It can be used independently without selecting speech subtitle translation first, and does not require the text to appear in the speech. Original subtitles within the processing scope may also be processed.
|
|
5708
|
+
* When both speech and visual are selected, the speech subtitle translation is completed and the video is synthesized first, and then the on-screen text processing is performed on this video. The translated dubbing is retained, and a final video is output. The order of features in the array does not affect the execution order. Therefore, not processing original subtitles only means that no subtitles are erased or added during the speech subtitle phase, and subsequent on-screen text processing may still change the original subtitles. Subtitles that have been replaced with translated subtitles are retained during subsequent on-screen text processing.
|
|
5677
5709
|
*
|
|
5678
5710
|
* @param request - VideoTranslationRequest
|
|
5679
5711
|
* @returns VideoTranslationResponse
|