Lemon-cmd/diffusion-jax

Diffusion Probabilistic Model in Jax

27
/ 100
Experimental

This project offers a clear and flexible codebase for experimenting with original Diffusion Probabilistic Models (DDIM and DDPM) to generate images. It takes random noise or existing images and transforms them into new, high-quality images based on a trained model. Image generation researchers and practitioners working on novel diffusion model architectures will find this useful for their experiments.

No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer specifically looking to build, train, and experiment with DDIM and DDPM models for image generation using JAX.

Not ideal if you are looking for an out-of-the-box solution for stable diffusion or general image editing without diving into the model's core mechanics.

image-generation deep-learning-research generative-models computer-vision AI-experimentation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

13

Forks

1

Language

Python

License

MIT

Last pushed

Apr 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Lemon-cmd/diffusion-jax"

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