CompVis/zigma

A PyTorch implementation of the paper "ZigMa: A DiT-Style Mamba-based Diffusion Model" (ECCV 2024)

39
/ 100
Emerging

This project creates realistic, high-resolution images and videos from noise using a novel 'zigzag' pattern. It takes an initial noisy image or video and refines it iteratively, producing clear, high-quality visual content. Researchers and creators working with generative AI for image and video synthesis would find this tool valuable.

345 stars. No commits in the last 6 months.

Use this if you need to generate high-quality images of faces, landscapes, or videos efficiently from scratch or enhance existing noisy visual data.

Not ideal if you are looking for tools to analyze existing images, perform image classification, or conduct traditional video editing.

generative-AI image-synthesis video-generation computational-photography AI-art
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

345

Forks

23

Language

Python

License

Apache-2.0

Last pushed

Mar 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/CompVis/zigma"

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