dariant/ID-Booth
Official repository of the paper: "ID-Booth: Identity-consistent Face Generation with Diffusion Models"
This tool helps researchers and developers in facial recognition generate realistic, diverse images of specific individuals. You provide a small set of images of a person, and it outputs many new images of that same person in varied settings and poses. This is ideal for anyone working on improving or evaluating face recognition systems, especially those needing to expand limited datasets.
Use this if you need to create a large, varied dataset of a specific person's face for training or testing face recognition models, starting from only a few initial images.
Not ideal if you need to generate completely novel faces or images of individuals not represented in your initial dataset.
Stars
40
Forks
9
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 28, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/dariant/ID-Booth"
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