VinAIResearch/LFM
Official PyTorch implementation of the paper: Flow Matching in Latent Space
This project provides an efficient way to generate high-quality images from various inputs, including labels, partial images, or semantic maps. It takes diverse image datasets (like faces, bedrooms, or general objects) and conditions (like text descriptions or image masks) to produce detailed, high-resolution synthetic images. This tool is ideal for researchers and practitioners in fields requiring realistic image synthesis or creative content generation.
337 stars. No commits in the last 6 months.
Use this if you need to generate high-resolution images conditionally, such as creating faces from specific attributes, completing missing parts of an image, or turning semantic layouts into realistic scenes, while being mindful of computational resources.
Not ideal if your primary goal is simpler image manipulation or if you don't require generative capabilities for complex image synthesis tasks.
Stars
337
Forks
19
Language
Python
License
AGPL-3.0
Category
Last pushed
Jan 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/VinAIResearch/LFM"
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"...