PeterWang512/FALdetector

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1600 stars · 230 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

FALdetector is the official PyTorch implementation of the ICCV 2019 paper 'Detecting Photoshopped Faces by Scripting Photoshop'. It provides a global classifier that detects facial warping manipulations and a local detector that localizes edited regions, with pretrained model weights and an evaluation dataset.

Use cases

• detect if a face photo has been warped or edited in photoshop
• localize which parts of a face image were manipulated
• detect liquify-style facial warping in images
• research image forensics and face manipulation detection
• evaluate face forgery detection models on a benchmark dataset
• reproduce results from the FAL paper

When to choose

• you need to detect Face-aware Liquify style facial warping in photos
• you are doing research on image forensics or manipulation detection
• you want pretrained models from a peer-reviewed ICCV paper with an evaluation dataset

When to avoid

• you need general-purpose image forgery or deepfake detection beyond facial warping
• you need to detect airbrushing, splicing, or other retouching the model was not trained on
• you need a production-ready service with support and guarantees rather than research code

Facets

library · maturity maintenance

computer-vision image-processing machine-learning deep-learning computer-vision image-processing deep-learning artificial-intelligence python face-manipulation-detection photoshop-detection image-forensics face-warping research-code pytorch iccv-2019 pretrained-models gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="PeterWang512/FALdetector")