aleksandrinvictor/flow-matching
Simple reimplementation of Flow Matching for Generative Modeling (https://arxiv.org/abs/2210.02747) paper in PyTorch
This tool helps machine learning engineers and researchers generate new, realistic images based on patterns learned from existing image datasets, like MNIST. You input a collection of images and it outputs a new set of images that share the same visual characteristics and style. It's for those experimenting with new generative modeling techniques.
No commits in the last 6 months.
Use this if you are a machine learning researcher or engineer interested in exploring and implementing generative modeling techniques using Flow Matching to create new images.
Not ideal if you need an out-of-the-box solution for complex image generation tasks or if you are not comfortable with Python and machine learning development.
Stars
23
Forks
3
Language
Python
License
—
Category
Last pushed
Aug 10, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/aleksandrinvictor/flow-matching"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.