XingtongGe/SenseFlow
🚀 [ICLR 2026] SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillation
SenseFlow helps AI model developers speed up the process of generating high-quality images from text descriptions. It takes a large, slower text-to-image model (like Stable Diffusion 3.5 or FLUX) and distills its knowledge into a smaller, faster model. The output is a new, optimized model that can create excellent images with fewer computational steps, benefiting anyone building applications with real-time or efficient image generation needs.
Use this if you are developing AI applications that require generating images from text rapidly and efficiently, especially when working with advanced flow-based models like SD 3.5 or FLUX.
Not ideal if you are looking for an off-the-shelf image generation tool for end-users, rather than a framework for optimizing existing large models.
Stars
70
Forks
3
Language
Python
License
—
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/XingtongGe/SenseFlow"
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"...