XingtongGe/SenseFlow

🚀 [ICLR 2026] SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillation

40
/ 100
Emerging

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.

AI model optimization text-to-image generation generative AI deep learning engineering computational efficiency
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 15 / 25
Community 6 / 25

How are scores calculated?

Stars

70

Forks

3

Language

Python

License

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.