Image Moderation Enhanced Edition of Alibaba Cloud Content Moderation provides an image detection service for scenarios involving AI-generated content (AIGC) and forgeries. This service lets you determine if an image is generated by AIGC. It also detects violation risks, suspected infringing elements, and suspected recaptured images. This topic describes the AIGC and forgery detection features of the Image Moderation service.
1. Use case
Alibaba Cloud Content Moderation provides the following dedicated detection services tailored to AIGC moderation and AI-powered forgery detection:
AI-generated content detection:
AIGC image detection: As AIGC technology evolves, its generated images become harder to distinguish from user-generated content (UGC). Many platforms must determine if an image is AI-generated. To address this, Alibaba Cloud Content Moderation offers AI-generated image detection. This feature analyzes images for synthesis artifacts to determine if they contain suspected generated or synthetic content.
AI-Generated Image Detection_Implicit Identifier: This feature builds on standard AI-generated image detection by also checking for an implicit identifier in the image file's metadata to determine if the content is synthetic. If an implicit identifier is found, the service returns detailed AIGC metadata.
AI Image Detection (Video Screenshots): This feature is designed for video frame analysis and detects whether frames contain suspected generated or synthetic content by analyzing characteristics and artifacts specific to video generation.
AIGC Detection_Professional Edition: This feature enhances standard detection by identifying composite images (including synthetic face images). It specializes in determining if an image is synthetic.
AI-Generated Image Detection_Ultimate: Building on the Professional edition, this feature also detects composite images (including synthetic face images) and AI-powered local editing. It specializes in determining if an image is an AI forgery.
Image forgery detection:
Recapture Detection: Detects if an image is a recapture of another image or screen to help identify potential forgeries.
Doctored Image Detection: Detects if an image has been digitally altered, which helps identify forgeries.
AIGC content moderation (Recommended: AI safety guardrail):
AIGC Image Risk Check: Because their training data and generation process are unpredictable, AIGC images can contain high-risk content. To address this risk, Alibaba Cloud Content Moderation offers AIGC image risk detection. It detects content or elements in AIGC-generated images that may violate web content policies, disrupt platform order, or degrade user experience.
AIGC Violation Detection: Using AIGC images for commercial purposes, such as marketing assets or corporate illustrations, carries a significant risk of infringement. To mitigate this, Alibaba Cloud Content Moderation offers AIGC image infringement detection. This feature identifies potential infringements by detecting various infringing elements in an image.
2. Service description
The AIGC and forgery detection capabilities of Image Moderation Enhanced Edition support the following services:
Scenario | Service | Detection content | Scenario |
AI-generated content detection | Service name: AIGC image detection Service: aigcDetector | Detection object: Images. Detects if an image was generated or synthesized by AI. Note This service is available only in the China (Beijing) and China (Shanghai) regions. When you call this service, select China (Beijing) or China (Shanghai) as the region. | Identifies AI-generated or synthesized images in various scenarios. Use this service to detect generation or synthesis artifacts. |
Service name: AI-Generated Image Detection_Implicit Identifier Service: aigcDetectorFull Important When you call this service, set the infoType parameter to aigcData to get the identifier content. | Detection object: Images. Detection content: Detects whether an image is likely to have been generated or synthesized by AI and whether the image contains an implicit identifier. If an implicit identifier is detected, the service returns the image's AIGC metadata. Note This service is available only in the China (Beijing) and China (Shanghai) regions. When you call this service, select China (Beijing) or China (Shanghai) as the region. | Determines if an image was AI-generated or synthesized. Use this service to detect both implicit identifiers and generation artifacts. | |
Service name: AI Image Detection (Video Screenshots) Service: aigcDetectorForFrame | Detection object: Video frames. Detection content: Detects whether a video frame is likely to have been generated or synthesized by AI. Note This service is available only in the China (Beijing) and China (Shanghai) regions. When you call this service, select China (Beijing) or China (Shanghai) as the region. | Determines if a video frame was AI-generated or synthesized. Use this service to detect generation or synthesis artifacts in videos. | |
Service Name: AIGC Detection_Professional Edition Service: aigcDetector_pro | Detection object: Images. Detection content: Detects whether an image is likely to have been generated or synthesized by AI, or if it is a suspected composite image (including synthetic faces). Note This service is currently available only in the China (Beijing) and China (Shanghai) regions. When calling the service, select Beijing or Shanghai as the region. | This service determines if an image is forged in various scenarios. Use this service when you need to detect image forgery. | |
Service name: AI-Generated Image Detection_Ultimate Service: aigcDetector_ultra | Detection object: Images. Detection content: Detects whether an image is likely to have been generated or synthesized by AI, is a suspected composite image (including synthetic faces), or contains suspected AI local editing. Note This service is available only in the China (Beijing) region. When you call this service, select China (Beijing) as the region. | Determines if an image is forged. Use this service to detect image forgery, especially to check for potential AI local editing. | |
Service name: AI-Generated Image Detection - Flagship International Edition Service: aigcDetector_ultra_cb | Detection object: Images. Detection content: Detects whether an image is likely to have been generated or synthesized by AI, is a suspected composite image (including synthetic faces), or contains suspected AI local editing. Note This service edition is available only in the Singapore region. When you call this service, select Singapore as the region. | Determines if an image is forged. Use this service to detect image forgery, especially to check for potential AI local editing. | |
Image forgery detection | Service name: Image Recapture Detection Service: recapDetector | This service checks an input image to determine if it is a suspected recapture. Note This service is currently available only in the China (Beijing) region. When calling the service, select Beijing as the region. | Determines if an image is a recapture. Use this service to handle recaptured images. |
Service name: Photoshop Detection Service: psDetector | Detects if an image has been edited with Photoshop. Note This service is available only in the China (Beijing) and China (Shanghai) regions. When you call this service, select China (Beijing) or China (Shanghai) as the region. | Determines if an image has been edited with Photoshop. Use this service to handle images edited with Photoshop. | |
Content moderation | Service Name: AIGC Image Risk Check Service: aigcCheck | This service is optimized for AIGC-generated images. It detects content related to pornography, vulgarity, sexual suggestiveness, politics, terrorism, contraband, discomfort, and other undesirable themes. For a detailed list of check items, see the Content Moderation console. | For AIGC scenarios, this service detects non-compliant or inappropriate content in AIGC-generated images. We recommend using this service for all AIGC-generated images. |
Service Name: AIGC Image Risk Detection (Outside Chinese Mainland) Service: aigcCheck_cb | This service is designed for AIGC scenarios outside of mainland China. It detects content related to pornography, vulgarity, sexual suggestiveness, politics, terrorism, contraband, discomfort, and other undesirable themes. For a detailed list of check items, see the Content Moderation console. Note This service supports the Singapore, US (Virginia), US (Silicon Valley), and London regions. | For AIGC scenarios outside the Chinese mainland, this service detects non-compliant or inappropriate content in AIGC-generated images. We recommend using this service for all AIGC-generated images. | |
Service Name: AIGC Violation Detection (Public Preview) Service: aigcViolationDetection | This service checks an image for elements such as trademarks, special logos, and public figures to determine if there is a risk of infringement. | When you use AIGC-generated images, especially for commercial purposes, call this service to determine the risk of infringement. For comprehensive risk assessment, use this service with AIGC Image Risk Detection to check for other risks, such as pornographic, political, and violent content. |
3. Billing
The AIGC and forgery detection service of Image Moderation Enhanced Edition supports the pay-as-you-go and resource plan billing methods.
Pay-as-you-go
After you activate the Image Moderation Enhanced Edition service, the default billing method is pay-as-you-go. You are billed daily based on your actual usage. If you do not call the service, you are not charged.
Moderation type | Supported business scenarios (services) | Unit price |
general image moderation (image_standard) |
| CNY 15.00 per 10,000 calls Note Each call to any of the services on the left is counted as one call. You are charged based on the actual number of calls. For example, if you call the AIGC Image Risk Detection service 100 times, you are charged CNY 0.15. |
advanced image moderation (image_advanced) |
| CNY 30.00 per 10,000 calls Note Each call to any of the services on the left is counted as one call. You are charged based on the actual number of calls. For example, if you call the AIGC Image Risk Detection (for regions outside mainland China) service 100 times, you are charged CNY 0.30. |
advanced image forgery moderation (image_identify_standard) |
| CNY 200.00 per 10,000 calls Note You are charged for each call made to any of the services on the left. For example, if you call the image recapture detection service 100 times, you are charged CNY 2.00. |
Bills for Content ModerationEnhanced Edition in pay-as-you-go mode are generated every 1 hours. In the billing details, moderationType corresponds to the moderation type field. For more information, see Bill Details.
Deducting usage with resource plans
If you have a large volume of content to moderate or have consistent moderation needs, you can purchase a resource plan in advance. Larger resource plans offer greater discounts. You can purchase and use multiple resource plans at the same time. For more information, see Purchase a Content Moderation Pro resource plan.
This resource plan deducts usage for Content Moderation Pro and cannot be used with data transfer plans for Content Moderation 1.0. The offset factors are as follows:
Moderation type | Offset factor |
General Image Moderation (image_standard) | The offset factor is 2. For each successful API call, 2 calls are deducted from your resource plan. For example, if your resource plan has a capacity of 10 calls and you make one successful API call, 2 calls are deducted. 8 calls remain. |
Advanced Image Moderation (image_advanced) | The offset factor is 4. For each successful API call, 4 calls are deducted from your resource plan. For example, if your resource plan has a capacity of 10 calls and you make one successful API call, 4 calls are deducted. 6 calls remain. |
Standard Image Forgery Detection (image_identify_standard) | The offset factor is 26.67. For each successful API call, 26.67 calls are deducted from your resource plan. For example, if your resource plan has a capacity of 50 calls and you make one successful API call, 26.67 calls are deducted, leaving 23.33 calls. |
After you purchase a resource plan, usage of the Content Moderation Pro API is first deducted from the plan. If the plan's balance is insufficient, the system automatically switches to the pay-as-you-go billing method. You should monitor your resource plan balance and pay-as-you-go bills. You can set up balance alert notifications in the Resource Plan system in the Alibaba Cloud User Center.
4. Integration
Step 1: Activate the service
Go to the service activation page to activate the Image Moderation Enhanced Edition service.
After you activate the Image Moderation Enhanced Edition service, the default billing method is pay-as-you-go. Fees are settled daily based on your actual usage. You are not charged if you do not call the service. After you call the API, the system automatically generates bills based on your usage. For more information, see Billing details.You can also purchase resource plans. Resource plans offer tiered discounts compared to the pay-as-you-go billing method and are suitable for users with predictable and high usage.
Step 2: Grant permissions to a RAM user
Before you call API operations or use SDKs, you must grant permissions to a RAM user. You must create an AccessKey pair for your Alibaba Cloud account or the RAM user. When you call API operations, you must use the AccessKey pair to complete identity verification. To obtain an AccessKey pair, see Obtain an AccessKey pair.
Log on to the RAM console using your Alibaba Cloud account or as a RAM administrator.
Create a RAM user. For more information, see Create a RAM user.
Grant the AliyunYundunGreenWebFullAccess system policy to the RAM user. For more information, see Grant permissions to a RAM user. After you complete these configurations, you can call the Content Moderation API as the RAM user.
Step 3: Install and integrate an SDK
For more information, see Image Moderation 2.0 SDKs and usage guide. The following table lists the supported regions.
Region | Public endpoint | VPC endpoint | Supported services |
China (Shanghai) | green-cip.cn-shanghai.aliyuncs.com | green-cip-vpc.cn-shanghai.aliyuncs.com | aigcCheck, aigcDetector, aigcDetectorFull, aigcDetectorForFrame, aigcDetector_pro, aigcViolationDetection |
China (Beijing) | green-cip.cn-beijing.aliyuncs.com | green-cip-vpc.cn-beijing.aliyuncs.com | aigcCheck, aigcDetector, aigcDetectorFull, aigcDetectorForFrame, aigcDetector_pro, aigcViolationDetection, recapDetector |
China (Hangzhou) | green-cip.cn-hangzhou.aliyuncs.com | green-cip-vpc.cn-hangzhou.aliyuncs.com | aigcCheck, aigcViolationDetection |
China (Shenzhen) | green-cip.cn-shenzhen.aliyuncs.com | green-cip-vpc.cn-shenzhen.aliyuncs.com | |
China (Chengdu) | green-cip.cn-chengdu.aliyuncs.com | None | |
Singapore | https://green-cip.ap-southeast-1.aliyuncs.com | https://green-cip-vpc.ap-southeast-1.aliyuncs.com | aigcCheck_cb |
US (Virginia) | green-cip.us-east-1.aliyuncs.com | green-cip-vpc.us-east-1.aliyuncs.com | |
US (Silicon Valley) | green-cip.us-west-1.aliyuncs.com | None | |
London | green-cip.eu-west-1.aliyuncs.com | None |
Step 4: Adjust image moderation rules (Optional)
In the Content Moderation console, you can adjust the detection rules for the image moderation service. You can toggle detection scopes, copy a service, configure custom image libraries and vocabularies, and query detection records and usage. For more information, see the Console Operation Guide.
5. API
Usage notes
You can call this API to create an image moderation task. For more information about how to construct an HTTP request, see the Access Guide. You can also use a pre-constructed HTTP request. For more information, see the Access Guide.
API operation: ImageModeration
Billing information: This is a paid operation. You are billed only for requests that return an HTTP status code of 200. Requests that return other error codes are not billed. For more information about billing methods, see the Billing overview.
Image requirements:
The following image formats are supported: PNG, JPG, JPEG, BMP, WEBP, TIFF, SVG, HEIC (the longest side must be less than 8,192 pixels), GIF (only the first frame is processed), and ICO (only the last image is processed).
The image size cannot exceed 20 MB. The height or width cannot exceed 16,384 pixels, and the total number of pixels cannot exceed 250 million. We recommend that you use images with a resolution of at least 200 × 200 pixels to ensure the effectiveness of the detection algorithm.
The image download time is limited to 3 seconds. If the download takes longer than 3 seconds, a timeout error is returned.
QPS limits
The queries per second (QPS) limit for this API operation is 100 for each user. However, for the aigcDetector_pro, aigcDetector_ultra, aigcDetector_ultra_cb, recapDetector, and psDetector services, the limit is 20 QPS. API calls that exceed these limits will be throttled, which can impact your business. Pace your API calls accordingly. If you have a high workload or need to scale up urgently, contact your business manager to request a higher QPS limit.
Debug
Before you start, you can use Alibaba Cloud OpenAPI Explorer to test the Image Moderation Enhanced Edition or API online. You can also view sample code and SDK dependencies to understand how to use the API and its parameters.
The online debugging feature calls the Content Moderation API operation using the currently logged-on account. Therefore, the calls are included in your billable usage.
Request parameters
For information about the common parameters required in a request, see the Access Guide.
The request body is a JSON struct that contains the following fields:
Name | Type | Required | Example | Description |
Service | String | Yes | aigcDetectorFull | The detection service. Valid values:
Important When you call the aigcDetectorFull service, set the infoType parameter to aigcData to retrieve the identifier content. |
ServiceParameters | JSONString | Yes | A set of parameters for the content moderation object, provided as a JSON string. For a description of each string, see Table 1. ServiceParameters. |
Table 1. ServiceParameters
Name | Type | Required | Example | Description |
imageUrl | String | Yes. Image Moderation Enhanced Edition supports three methods for uploading images:
| https://img.alicdn.com/tfs/TB1U4r9AeH2gK0jSZJnXXaT1FXa-2880-480.png | The URL of the object to detect. Make sure the URL is accessible over the public network and is no more than 2,048 characters long. Note The URL cannot contain Chinese characters. Make sure you submit only one URL per request. |
ossBucketName | String | bucket_01 | The name of the authorized OSS bucket. Note To use an internal OSS URL for an image, you must first use your root account to go to the Cloud Resource Access Authorization page and grant the | |
ossObjectName | String | 2022023/04/24/test.jpg | The name of the file in the authorized OSS bucket. | |
ossRegionId | String | cn-beijing | The region where the OSS bucket is located. | |
dataId | String | No | img123**** | The data ID of the detection object. The ID can contain uppercase letters, lowercase letters, digits, underscores (_), hyphens (-), and periods (.). It can be up to 64 characters long and can be used to uniquely identify your business data. |
referer | String | No | www.aliyun.com | The referer request header, used for scenarios such as hotlink protection. The length cannot exceed 256 characters. |
infoType | String | Yes | aigcData | The type of auxiliary information to be returned. Valid values:
To specify multiple types, provide a comma-separated list, such as |
Response parameters
Name | Type | Example | Description |
RequestId | String | 70ED13B0-BC22-576D-9CCF-1CC12FEAC477 | The ID of the current request. This is a unique identifier generated by Alibaba Cloud for the request and can be used for troubleshooting. |
Data | Object | The result of image moderation. For more information, see Table 2. Data. | |
Code | Integer | 200 | The returned HTTP status code. For more information, see Response codes. |
Msg | String | OK | The response message for the current request. |
Table 2. Data
Name | Type | Example | Description |
Result | Array | The parameter results of image moderation, such as risk labels and confidence scores. For more information, see Table 3. result. | |
RiskLevel | String | high | The risk level, which is returned based on the configured high and low risk scores. Valid values:
Note It is recommended to handle high-risk content directly. Medium-risk content should be manually reviewed. Low-risk content should be handled only when high recall is required. Otherwise, treat it the same as content with no detected risk. You can configure risk scores in the Content Moderation console. |
DataId | String | img123****** | The data ID of the detection object. Note If you passed a dataId in the request parameters, the same dataId is returned here. |
Ext | Object | Additional information for the image. For more information, see Ext. |
Table 3. result
Name | Type | Example | Description |
Label | String | tm_auto | The label returned after image content detection. Multiple labels and scores may be returned for a single image. For supported labels, see:
|
Confidence | Float | 81.22 | The confidence score ranges from 0 to 100 and is accurate to two decimal places. Some labels do not have a confidence score. For more information, see Descriptions of risk labels. |
Description | String | Fireworks and pyrotechnics | A description of the Label field. Important This field explains the Label field and is subject to change. It is recommended to handle results based on the Label field, not this field. |
Table 4: Ext
Parameter | Type | Value | Description |
CustomImage | JSONArray | If a match is found in a custom library, this parameter returns that library's details. For more information, see CustomImage. | |
AigcData | Object | Returns AIGC implicit marker detection results for the image. For more information, see AigcData. |
Table 5. CustomImage
Parameter | Type | Example value | Description |
LibId | String | lib0001 | The unique ID of the matched custom image library. |
LibName | String | Custom Image Library A | The name of the matched custom image library. |
ImageId | String | 20240307 | The unique ID of the matched custom image. |
Table 6: AigcData
Parameter | Type | Value | Description |
AIGC | Object | "AIGC": {"Label": "1", "ContentPropagator": "", "ReservedCode1": "0424***", "ProduceID": "0307***", "ReservedCode2": "", "PropagateID": "", "ContentProducer": "0728***"} | The AIGC implicit watermark information in the image conforms to the standard AIGC metadata fields. For more information, see Implicit Watermark Metadata Information. |
Implicit identification metadata
Examples
Sample request
{
"Service": "aigcViolationDetection",
"ServiceParameters": {
"imageUrl": "https://img.alicdn.com/tfs/TB1U4r9AeH2gK0jSZJnXXaT1FXa-2880-480.png",
"dataId": "img123****"
}
}Sample responses
If the system detects risky content, the following response is returned:
{
"Msg": "OK",
"Code": 200,
"Data": {
"DataId": "img123****",
"Result": [
{
"Label": "tm_auto",
"Confidence": 81,
"Description": "Automotive brand trademark content"
},
{
"Label": "tm_electronic",
"Confidence": 98,
"Description": "Electronics and appliances trademark content"
}
],
"RiskLevel": "high"
},
"RequestId": "ABCD1234-1234-1234-1234-1234XYZ"
}If the system does not detect risky content, the following response is returned:
{
"Msg": "OK",
"Code": 200,
"Data": {
"DataId": "img123****",
"Result": [
{
"Label": "nonLabel",
"Description": "No risk detected"
}
],
"RiskLevel": "none"
},
"RequestId": "ABCD1234-1234-1234-1234-1234XYZ"
}If the system detects that the input image matches an image in your configured review-free image library, the following response is returned:
{
"Msg": "OK",
"Code": 200,
"Data": {
"DataId": "img123****",
"Result": [
{
"Label": "nonLabel_lib",
"Confidence": 87.28,
"Description": "Hit review-free image library"
}
],
"RiskLevel": "none"
},
"RequestId": "ABCD1234-1234-1234-1234-1234XYZ"
}When the system finds a match in a custom image library, the following is an example of the response:
The following is a sample response when an implicit AIGC identifier is detected:
{
"Code": 200,
"Data": {
"Ext": {
"AigcData": {
"AIGC": {
"Label": "1",
"ContentPropagator": "",
"ReservedCode1": "0424***",
"ProduceID": "0307***",
"ReservedCode2": "",
"PropagateID": "",
"ContentProducer": "0728***"
}
}
},
"RiskLevel": "high",
"Result": [
{
"Description": "The image contains AI-generated metadata.",
"Confidence": 100,
"Label": "aigc_byMeta",
"RiskLevel": "high"
}
]
},
"Msg": "success",
"RequestId": "TESTZGL-0307-2024-0728-FOREVER"
}The sample requests and responses in this topic are formatted for readability. Actual responses are not formatted with line breaks or indentation.
Risk label descriptions
The following table lists the risk labels, their corresponding confidence scores, and their definitions. You can enable or disable each risk label in the Content Moderation console. For some risk labels, you can also configure more specific detection scopes. For more information, see the Console User Guide.The following labels are supported by the AIGC image detection services:
Supported labels for AIGC image threat detection (aigcCheck)
Supported labels for AIGC image threat detection (International) (aigcCheck_cb)
AIGC-generated image detection (with metadata) (aigcDetectorFull)
AIGC-generated image detection (Professional Edition) (aigcDetector_pro)
AIGC-generated image detection (Ultimate Edition) (aigcDetector_ultra)
Supported labels for recaptured image detection (recapDetector)
Supported labels for AIGC image infringement detection (aigcViolationDetection)
We recommend that you store the risk labels and confidence scores returned by the system for a certain period. This data can be used as a reference for future content governance. You can set priorities for manual review or annotation and implement tiered content governance measures based on the risk labels.
Table 4.Labels supported by AIGC Image Risk Detection (aigcCheck)
Label (label) | Confidence score range (confidence) | Meaning |
pornographic_adultContent | 0 to 100. A higher score indicates a higher confidence level. | Suspected adult pornographic content. |
pornographic_adultToys | 0 to 100. A higher score indicates a higher confidence level. | Suspected adult toy content. |
pornographic_artwork | 0 to 100. A higher score indicates a higher confidence level. | Suspected pornographic artwork content. |
suggestiveContent_bump | 0 to 100. A higher score indicates a higher confidence level. | Content of the suspected raised-point contour. |
suggestiveContent_sexhint | 0 to 100. A higher score indicates a higher confidence level. | Suspected vulgar content involving gestures and body parts. |
sexual_exaggeratedbreast | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with exaggerated female breasts. |
sexual_exaggeratedhip | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with exaggerated hips. |
sexual_exaggeratedCleavage | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with deep cleavage. |
sexual_femaleLeg | 0 to 100. A higher score indicates a higher confidence level. | Suspected sexually suggestive content involving legs. |
sexual_femaleUnderwear | 0 to 100. A higher score indicates a higher confidence level. | Suspected underwear or swimwear content. |
sexual_femaleSeethrough | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with transparent clothing. |
sexual_generalbreast | 0 to 100. A higher score indicates a higher confidence level. | Suspected content featuring female cleavage. |
sexual_shoulder | 0 to 100. A higher score indicates a higher confidence level. | Suspected sexually suggestive content involving shoulders. |
sexual_pregnancy | 0 to 100. A higher score indicates a higher confidence level. | Suspected content related to maternity photos or breastfeeding. |
sexual_maleTopless | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with topless males. |
sexual_inBed | 0 to 100. A higher score indicates a higher confidence level. | Suspected content in a bed setting. |
sexual_inToilet | 0 to 100. A higher score indicates a higher confidence level. | Suspected content in a bathroom setting. |
PDA_kiss | 0 to 100. A higher score indicates a higher confidence level. | Suspected content involving kissing. |
PDA_physicalContact | 0 to 100. A higher score indicates a higher confidence level. | Suspected content involving intimate behavior. |
political_politicalFigure | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with political figures. |
political_prohibitedPerson | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with individuals who should not be promoted. |
political_taintedCelebrity | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with public figures involved in major negative events. |
political_CNFlag | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with the Chinese flag. |
political_otherFlag | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with flags of other countries or regions. |
political_CNMap | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with a map of China. |
political_logo | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with specific media or TV station logos. |
political_outfit | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with military or police uniforms. |
political_ACU | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with combat uniforms. |
political_badge | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with national or party emblems. |
violent_explosion | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with fireworks or explosions. |
violent_armedForces | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with armed elements. |
violent_crowding | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with crowd gatherings. |
violent_gun | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with firearms. |
violent_knives | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with knives. |
violent_othergunKnives | 0 to 100. A higher score indicates a higher confidence level. | Suspected content related to firearms. |
violent_blood | 0 to 100. A higher score indicates a higher confidence level. | Suspected bloody content. |
contraband_drug | 0 to 100. A higher score indicates a higher confidence level. | Suspected drug-related content. |
contraband_gamble | 0 to 100. A higher score indicates a higher confidence level. | Suspected gambling-related content. |
horrific_organs | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with internal organs. |
horrific_intensive | 0 to 100. A higher score indicates a higher confidence level. | Suspected content that may trigger trypophobia. |
horrific_excrement | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with excrement. |
horrific_horrific | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain horrific content. |
inappropriate_smoking | 0 to 100. A higher score indicates a higher confidence level. | Suspected smoking-related content. |
inappropriate_drinking | 0 to 100. A higher score indicates a higher confidence level. | Suspected alcohol-related content. |
inappropriate_tattoo | 0 to 100. A higher score indicates a higher confidence level. | Suspected tattoo-related content. |
religion_clothing | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with specific religious attire or symbols. For more information, see the Content Moderation console. |
religion_logo | 0 to 100. A higher score indicates a higher confidence level. | |
religion_flag | 0 to 100. A higher score indicates a higher confidence level. |
Table 5.Labels supported by AIGC Image Risk Detection (for regions outside mainland China) (aigcCheck_cb)
Label (label) | Confidence score range (confidence) | Meaning |
pornographic_adultContent | 0 to 100. A higher score indicates a higher confidence level. | Suspected adult pornographic content. |
pornographic_adultToys | 0 to 100. A higher score indicates a higher confidence level. | Suspected adult toy content. |
pornographic_artwork | 0 to 100. A higher score indicates a higher confidence level. | Suspected pornographic artwork content. |
sexual_suggestiveContent | 0 to 100. A higher score indicates a higher confidence level. | Suspected vulgar content involving gestures and body parts. |
sexual_femaleUnderwear | 0 to 100. A higher score indicates a higher confidence level. | Suspected underwear or swimwear content. |
sexual_cleavage | 0 to 100. A higher score indicates a higher confidence level. | Suspected content featuring female cleavage. |
sexual_maleTopless | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with topless males. |
sexual_cartoon | 0 to 100. A higher score indicates a higher confidence level. | Suspected sexually suggestive cartoon content. |
sexual_shoulder | 0 to 100. A higher score indicates a higher confidence level. | Suspected sexually suggestive content involving shoulders. |
sexual_femaleLeg | 0 to 100. A higher score indicates a higher confidence level. | Suspected sexually suggestive content involving legs. |
sexual_pregnancy | 0 to 100. A higher score indicates a higher confidence level. | Suspected content related to maternity photos or breastfeeding. |
sexual_kiss | 0 to 100. A higher score indicates a higher confidence level. | Suspected content involving kissing. |
sexual_intimacy | 0 to 100. A higher score indicates a higher confidence level. | Suspected content involving intimate behavior. |
sexual_intimacyCartoon | 0 to 100. A higher score indicates a higher confidence level. | Suspected intimate actions in cartoons or anime. |
political_historicalNihility | 0 to 100. A higher score indicates a higher confidence level. | Suspected content related to historical nihilism. |
political_politicalFigure_1 | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with political figures. For more information, see the Content Moderation console. |
political_politicalFigure_2 | 0 to 100. A higher score indicates a higher confidence level. | |
political_politicalFigure_3 | 0 to 100. A higher score indicates a higher confidence level. | |
political_politicalFigure_4 | 0 to 100. A higher score indicates a higher confidence level. | |
political_prohibitedPerson_1 | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain disgraced national-level officials. |
political_prohibitedPerson_2 | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain disgraced provincial- or municipal-level officials. |
political_prohibitedPerson | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with individuals who should not be promoted. |
political_taintedCelebrity | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with public figures involved in major negative events. |
political_CNFlag | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with the Chinese flag. |
political_CNMap | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with a map of China. |
political_logo | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with specific media or TV station logos. |
political_outfit | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with military or police uniforms. |
political_badge | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with national or party emblems. |
violent_explosion | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with fireworks or explosions. |
violent_armedForces | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with armed elements. |
violent_weapon | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with military equipment. |
violent_ACU | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with combat uniforms. |
violent_crowding | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with crowd gatherings. |
violent_gun | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with firearms. |
violent_knives | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with knives. |
violent_horrific | 0 to 100. A higher score indicates a higher confidence level. | Suspected horrific content. |
violent_nazi | 0 to 100. A higher score indicates a higher confidence level. | Suspected Nazi-related content. |
violent_blood | 0 to 100. A higher score indicates a higher confidence level. | Suspected bloody content. |
contraband_drug | 0 to 100. A higher score indicates a higher confidence level. | Suspected drug-related content. |
contraband_gamble | 0 to 100. A higher score indicates a higher confidence level. | Suspected gambling-related content. |
horrific_organs | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with internal organs. |
horrific_intensive | 0 to 100. A higher score indicates a higher confidence level. | Suspected content that may trigger trypophobia. |
horrific_excrement | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with excrement. |
horrific_horrific | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain horrific content. |
horrific_blood | 0 to 100. A higher score indicates a higher confidence level. | Suspected bloody content. |
inappropriate_smoking | 0 to 100. A higher score indicates a higher confidence level. | Suspected smoking-related content. |
inappropriate_drinking | 0 to 100. A higher score indicates a higher confidence level. | Suspected alcohol-related content. |
inappropriate_tattoo | 0 to 100. A higher score indicates a higher confidence level. | Suspected tattoo-related content. |
inappropriate_middleFinger | 0 to 100. A higher score indicates a higher confidence level. | Suspected content related to the middle finger gesture. |
inappropriate_foodWasting | 0 to 100. A higher score indicates a higher confidence level. | Suspected content related to food waste. |
religion_clothing | 0 to 100. A higher score indicates a higher confidence level. | Suspected content with specific religious attire or symbols. For more information, see the Content Moderation console. |
religion_logo | 0 to 100. A higher score indicates a higher confidence level. | |
religion_flag | 0 to 100. A higher score indicates a higher confidence level. | |
religion_taboo1_tii | 0 to 100. A higher score indicates a higher confidence level. | Text in the image contains religious taboo content. |
religion_taboo2_tii | 0 to 100. A higher score indicates a higher confidence level. | Text in the image contains taboo content. |
flag_country | 0 to 100. A higher score indicates a higher confidence level. | Suspected flag-related content. |
Table 6.Supported Labels for AIGC-Generated Image Identification (aigcDetector)
Label (label) | Confidence score range (confidence) | Meaning |
aigc | 0 to 100. A higher score indicates a higher confidence level. | The image is suspected to be generated by AIGC. |
ugc | 0 to 100. A higher score indicates a higher confidence level. | The image is not generated by AIGC. |
The ugc label is disabled by default. To enable it, you can configure the settings in the Content Moderation console. If no risk label is detected, the nonLabel label is returned.
Table 7. Labels for AI-generated image detection (with metadata) (aigcDetectorFull)
Label | Confidence score | Description |
aigc_byMeta | 0 to 100. Higher scores indicate greater confidence. | The image contains an implicit identifier for AI-generated or synthetic content. |
aigc_byFeature | 0 to 100. Higher scores indicate greater confidence. | The image is likely AI-generated or synthetic based on its visual features. |
Table 8.Labels for AIGC Image Generation Detection (Professional Edition) (aigcDetector_pro)
Label (label) | Confidence score range (confidence) | Meaning |
risk_aigc | 0 to 100. A higher score indicates a higher confidence level. | The image is suspected to be AIGC-generated. |
risk_fake | 0 to 100. A higher score indicates a higher confidence level. | The image is suspected to be a composite image. |
Table 9. Labels for AI-generated Image Detection (Ultimate Edition) (aigcDetector_ultra)
Label | Confidence | Description |
risk_aigc | 0 to 100. A higher score indicates greater confidence. | The image is likely generated by AIGC. |
risk_fake | 0 to 100. A higher score indicates greater confidence. | The image is likely a synthesized image. |
risk_edit | 0 to 100. A higher score indicates greater confidence. | The image is likely an AI-edited image. |
Table 10. Supported labels for image recapture detection (recapDetector)
Label (label) | Confidence score range (confidence) | Meaning |
recap | 0 to 100. A higher score indicates a higher confidence level. | The image is suspected to be a recaptured image. |
normal | 0 to 100. A higher score indicates a higher confidence level. | The image is not a recaptured image. |
Table 11. Labels for psDetector (Image Photoshop Detection)
Label | Confidence | Description |
risk_ps | A score from 0 to 100, where a higher score indicates greater confidence. | The image is suspected of being doctored. |
normal | A score from 0 to 100, where a higher score indicates greater confidence. | The image is not doctored. |
Table 12. AIGC image infringement detection (aigcViolationDetection): Supported labels
Label (label) | Confidence score range (confidence) | Meaning |
tm_auto | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain automotive brand trademarks. |
tm_electronic | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain electronics and appliance trademarks. |
tm_fashion | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain fashion and beauty trademarks. |
tm_goods | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain daily goods trademarks. |
logo_sns | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain social media logos. |
logo_lifestyle | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain lifestyle service logos. |
logo_streaming | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain entertainment and streaming service logos. |
logo_finance | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain financial service logos. |
logo_retail | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain e-commerce logos. |
logo_news | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain news and reading platform logos. |
logo_enterprise | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain corporate platform logos. |
logo_tv | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain TV station logos. |
cartoon_ip | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain anime characters. |
public_celebrity | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain celebrities. |
public_politician | 0 to 100. A higher score indicates a higher confidence level. | The image appears to contain political figures. |
Additionally, you can configure a custom library for each of the preceding risk labels. If a detected image is highly similar to an image in your custom library, the system returns the corresponding risk label. To distinguish these results, the label value is formatted as original_risk_label_lib. For example, if you configure a custom library for tm_auto and a detected image has a high similarity to an image in that library, the system returns tm_auto_lib in the label parameter. The corresponding confidence parameter indicates the degree of similarity.
If the system detects no abnormalities in the submitted image, or if the image has a high similarity to an image in your configured review-free library, the returned label and confidence score are as follows.
Label (label) | Confidence score range (confidence) | Meaning |
nonLabel | This field is not returned. | No risk was detected in the image, or you have disabled all detection items. For more information, see the Content Moderation console. |
nonLabel_lib | 0 to 100. A higher score indicates a higher confidence level. | The image is highly similar to an image in your configured review-free library. For more information, see the Content Moderation console. |
Code descriptions
The following table describes the meanings of the returned codes. The system charges only for requests that return a code of 200. No fees are charged for other codes.
Code | Description |
200 | The request is successful. |
400 | A request parameter is empty. |
401 | A request parameter is invalid. |
402 | The length of a request parameter does not meet the requirements. Check and modify the parameter. |
403 | The number of requests exceeds the QPS limit. Check and adjust the concurrency. |
404 | An error occurred while downloading the specified image. Check the image or retry. |
405 | The download of the specified image timed out. This may be because the image is inaccessible. Check the image and retry. |
406 | The specified image is too large. Check and adjust the image size, then retry. |
407 | The format of the specified image is not supported. Check and adjust the image format, then retry. |
408 | The account does not have permission to call this API operation. This may be because the service is not activated, the account has an overdue payment, or the account is not authorized. |
500 | A system error occurred. |