LouisRouss/DiffuLab
DiffuLab is designed to provide a simple and flexible way to train diffusion models while allowing full customization of its core components.
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.
Stars
43
Forks
—
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
huggingface/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
bghira/SimpleTuner
A general fine-tuning kit geared toward image/video/audio diffusion models.
mcmonkeyprojects/SwarmUI
SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an...
nateraw/stable-diffusion-videos
Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
TheDesignFounder/DreamLayer
Benchmark diffusion models faster. Automate evals, seeds, and metrics for reproducible results.