DongzeLi-CASIA/RiDDLE
Author implementation of RiDDLE: Reversible and Diversified De-identification with Latent Encryptor (CVPR 2023)
This tool helps you protect people's privacy by de-identifying faces in images and videos. You provide a photo or video, and it generates an anonymized version where the original identity is hidden, but can be restored later using a secret password. This is ideal for professionals in fields like public safety, journalism, or research who handle sensitive visual data.
No commits in the last 6 months.
Use this if you need to anonymize faces in images or videos for privacy reasons, but also require the ability to restore the original identity securely when necessary.
Not ideal if you need a simple, irreversible blurring or pixelation method for face anonymization without the need for identity restoration.
Stars
51
Forks
2
Language
Python
License
—
Category
Last pushed
Jul 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/DongzeLi-CASIA/RiDDLE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
bytedance/InfiniteYou
🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
River-Zhang/ICEdit
[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image...
muzishen/IMAGHarmony
🧩 IMAGHarmony 🧩: Controllable image editing with consistent object quantity and layout. A...
AMAP-ML/FE2E
[CVPR 2026] Beyond Generation: Advancing Image Editing Priors for Depth and Normal Estimation
TencentARC/BrushNet
[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting...