Anshumaan-Chauhan02/Guided-Flow-Matching
Utilized attention incorporated UNet model for conditional image generation using Flow Matching with Conditional Optimal Transport Objective
This project helps researchers and developers create new images based on specific descriptions or generate images without any conditions. You provide text descriptions (like "a red car") and it outputs corresponding images, or you can get diverse images without any input text. This is for machine learning researchers, AI artists, or engineers working on computer vision applications.
No commits in the last 6 months.
Use this if you need to generate high-quality images conditionally from text prompts or produce new images unconditionally for datasets or creative projects.
Not ideal if you are looking for a pre-trained model ready for immediate use in a production application without any further training or development.
Stars
13
Forks
4
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Dec 29, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Anshumaan-Chauhan02/Guided-Flow-Matching"
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"...