haidog-yaqub/MeanFlow

Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling" by Geng et al.

46
/ 100
Emerging

This project offers a PyTorch implementation for generating images quickly, often in a single step, rather than the many steps typically required by other methods. It takes training data like MNIST or CIFAR-10 images as input and produces new, similar images as output. This tool is designed for researchers and practitioners in machine learning who are developing or experimenting with generative models.

1,093 stars.

Use this if you are a machine learning researcher focused on developing or evaluating one-step generative image models and need a clean PyTorch implementation.

Not ideal if you need a user-friendly application for generating images or require features like adjustable Classifier-Free Guidance scales or negative prompts at inference time.

generative-modeling image-synthesis deep-learning-research pytorch-development
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 15 / 25

How are scores calculated?

Stars

1,093

Forks

60

Language

Python

License

MIT

Last pushed

Dec 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/haidog-yaqub/MeanFlow"

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