fdbtrs/IDiff-Face
Official repository of the paper: IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-conditioned Diffusion Models (ICCV 2023)
This project helps researchers and developers in facial recognition create high-quality synthetic datasets for training face recognition models. It takes existing identity information and generates diverse, realistic synthetic face images. This allows them to overcome privacy concerns associated with using authentic human face data, enabling continued research and development in facial recognition.
No commits in the last 6 months.
Use this if you need to develop or test face recognition systems but are constrained by access to large, diverse, and privacy-compliant authentic face datasets.
Not ideal if your primary goal is to perform face recognition directly on existing images, rather than to generate new training data.
Stars
92
Forks
4
Language
Python
License
—
Category
Last pushed
Apr 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/fdbtrs/IDiff-Face"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OPTML-Group/Unlearn-Saliency
[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in...
Shilin-LU/VINE
[ICLR 2025] "Robust Watermarking Using Generative Priors Against Image Editing: From...
WindVChen/DiffAttack
An unrestricted attack based on diffusion models that can achieve both good transferability and...
koninik/DiffusionPen
Official PyTorch Implementation of "DiffusionPen: Towards Controlling the Style of Handwritten...
Wuyxin/DISC
(ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation