CompVis/fm-boosting
[ECCV 2024, Oral] FMBoost: Boosting Latent Diffusion with Flow Matching
This project helps generate high-resolution images from lower-resolution inputs much faster than standard methods. You provide a low-resolution image representation, and it quickly outputs a high-fidelity, high-resolution image, up to 2048x2048 pixels. This is ideal for researchers or artists who need to upscale images with exceptional speed and quality, reducing computational time significantly.
256 stars.
Use this if you need to rapidly generate or upscale images to high resolutions (1024x1024 or 2048x2048) without compromising on visual quality.
Not ideal if you primarily work with very low-resolution image generation where speed is not a critical factor, or if you require fine-grained control over the upscaling process that deviates from the core model's capabilities.
Stars
256
Forks
5
Language
Python
License
MIT
Category
Last pushed
Oct 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/CompVis/fm-boosting"
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"...