sail-sg/finetune-fair-diffusion
Code of the paper: Finetuning Text-to-Image Diffusion Models for Fairness
This project helps creators and AI artists generate more balanced and representative images from text prompts. You provide a text description (like 'A photo of a doctor') and the system produces an image that avoids common biases related to gender, race, or age. It is ideal for content creators, marketers, or anyone using AI for image generation who prioritizes ethical and diverse visual outputs.
No commits in the last 6 months.
Use this if you need to generate images from text descriptions and want to ensure the visual representations are fair and inclusive across different demographics.
Not ideal if your primary goal is to generate highly stylized or specific artistic images where demographic representation is not a key concern, or if you lack the technical expertise for local model finetuning.
Stars
46
Forks
3
Language
Python
License
MIT
Category
Last pushed
Apr 26, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/sail-sg/finetune-fair-diffusion"
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