ali-vilab/DiffDoctor

[ICCV 2025] DiffDoctor: Diagnosing Image Diffusion Models Before Treating

29
/ 100
Experimental

This project helps AI researchers and developers improve the quality of images generated by diffusion models. It takes an existing image diffusion model as input, identifies common flaws or 'artifacts' in its generated images, and then helps retrain the model to produce higher-quality, more realistic outputs. It's designed for machine learning engineers and researchers working on generative AI.

No commits in the last 6 months.

Use this if you are developing or fine-tuning image diffusion models and want to systematically identify and fix common issues that lead to poor image quality or artifacts.

Not ideal if you are looking for a ready-to-use image generator or a tool to analyze images that were not created by a diffusion model.

generative-ai image-synthesis model-training diffusion-models image-quality-improvement
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 15 / 25
Community 5 / 25

How are scores calculated?

Stars

41

Forks

2

Language

Python

License

MIT

Last pushed

Sep 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ali-vilab/DiffDoctor"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.