nmboffi/flow-maps
Official codebase for the paper "How to build a consistency model: Learning flow maps via self-distillation" (NeurIPS 2025).
This project helps researchers and practitioners in generative AI efficiently create high-quality synthetic images or data. It takes raw image datasets (like CIFAR-10 or CelebA) and processes them to output advanced generative models capable of quickly producing new, diverse samples. Its primary users are machine learning researchers and engineers focused on developing state-of-the-art generative models.
No commits in the last 6 months.
Use this if you need to train next-generation generative models that can produce high-fidelity samples in very few steps, significantly speeding up the generation process compared to traditional diffusion models.
Not ideal if you are looking for an out-of-the-box solution for basic image generation with existing, well-established methods, or if you do not have a strong background in deep learning model development.
Stars
89
Forks
6
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 08, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/nmboffi/flow-maps"
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...
haidog-yaqub/MeanFlow
Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling"...