Home Projects zigma
zigma
Python

zigma

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

by CompVis · GitHub
Stars
Forks
License
Created
Last commit
Language
diffusion-modelsflow-matchingmambaApache-2.0Python
View on GitHub
In plain words

Run a video processing model that efficiently analyzes and generates content using a zigzag pattern for better results.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
zigma — GitHub preview card
📈 Star history
352351
2026-07-202026-08-31
📈 Track zigma

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

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

zigma has 351 stars on GitHub. It has been forked 23 times. zigma is written mainly in Python. It has been in active development since 2024. zigma is available under the Apache-2.0 license. Its main topics are diffusion-models, flow-matching, mamba, state-space-model.

Frequently asked questions

What is zigma?

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

Is zigma open source?

zigma is an open-source project. It is released under the Apache-2.0 license.

Is zigma free?

Yes. zigma is free and open source — you can use, modify and self-host it.

What license does zigma use?

zigma is available under the Apache-2.0 license.

What language is zigma written in?

zigma is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — zigma

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=compvis-zigma)](https://olud.ai/project/compvis-zigma.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.