LouisRouss/DiffuLab

DiffuLab is designed to provide a simple and flexible way to train diffusion models while allowing full customization of its core components.

30
/ 100
Emerging

This project helps machine learning engineers or researchers build and train custom diffusion models from scratch for tasks like image generation. It takes raw data and model configurations as input, then outputs a trained diffusion model ready for generating new content. This is for professionals working on advanced AI model development and customization.

Use this if you need to build and train specialized diffusion models with full control over the underlying architecture, formalization, and sampling components.

Not ideal if you are looking to use a pre-trained model out-of-the-box or fine-tune an existing model without deep customization.

generative-AI deep-learning-research model-training custom-AI-development image-synthesis
No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

43

Forks

Language

Python

License

MIT

Last pushed

Jan 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/LouisRouss/DiffuLab"

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