haidog-yaqub/MeanFlow
Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling" by Geng et al.
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.
Stars
1,093
Forks
60
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
milad1378yz/MOTFM
Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality
OpenImagingLab/FlashVSR
[CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient...
X-GenGroup/Flow-Factory
A unified framework for easy reinforcement learning in Flow-Matching models
fallenshock/FlowEdit
Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using...
jy0205/Pyramid-Flow
[ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling