Real or AI Face
Upload a face photo, portrait, or profile image to check for AI-generated content signals across the whole image.
Check whether a face appears real or AI-generated, including signs of synthetic faces, AI face swaps, and heavy AI-assisted retouching. The model analyzes the whole image and returns an AI-generation risk score.
What does Real or AI Face mean?
Real or AI Face checks whether a face photo appears real or AI-generated. It analyzes the whole image for signals associated with synthetic faces, AI face swaps, local AI edits, and heavy AI-assisted retouching.
What ImgAuth detects
- Uploads a face photo, portrait, selfie, or profile image
- Analyzes AI-generation and AI-assisted editing signals across the whole image
- Checks for signals associated with synthetic faces, AI face swaps, and heavy retouching
What ImgAuth does not detect
- Editing, resizing, screenshots, and recompression can affect the score
- It does not perform facial-liveness checks, identity verification, or confirm the exact manipulation type
- Not a legal identity verification, KYC, ownership, or provenance workflow
Inputs
- face photo
- portrait or selfie
- profile image or avatar
- other face-centric image
Outputs
- Detection Result
- AI Generation Score
- Analyzed Image
How Real or AI Face works
- Uploads a face photo, portrait, selfie, or profile image
- Analyzes AI-generation and AI-assisted editing signals across the whole image
- Checks for signals associated with synthetic faces, AI face swaps, and heavy retouching
- Returns an overall moderation result and AI Generation Score
Use Cases
- Checking whether a profile photo appears real or AI-generated
- Reviewing selfies and portraits for synthetic-face signals
- Screening possible AI face swaps or heavy AI-assisted retouching
- Supporting profile moderation and trust-review workflows
Important capability boundary
Check whether a face appears real or AI-generated, including signs of synthetic faces, AI face swaps, and heavy AI-assisted retouching. The model analyzes the whole image and returns an AI-generation risk score.
Limitations
- The result is an overall model risk signal, not proof of origin or authenticity
- Editing, resizing, screenshots, and recompression can affect the score
- It does not perform facial-liveness checks, identity verification, or confirm the exact manipulation type
- Borderline results should be reviewed with the image context and other evidence
FAQ
What does Real or AI Face detect?
It checks the whole image for signals associated with AI-generated faces, synthetic faces, AI face swaps, local AI edits, and heavy AI-assisted retouching.
Does it only analyze the face region?
This page is intended for face-centric images, but the model evaluates the whole image, including the face, hair, clothing, and background.
Can it prove that a face photo is real?
No. A low score means the model found weaker AI-generation signals; it does not prove authenticity or origin.
Can it detect AI face swaps or heavy retouching?
It can flag whole-image signals associated with AI face swaps, local AI edits, or heavy retouching, but it does not confirm the exact manipulation type.
What does the AI Generation Score mean?
AI Generation Score is Tencent's model risk score for AI-generated content across the whole image. It is not a calibrated probability and does not prove that an image is authentic.