snap-research/stable-flow

Official implementation for "Stable Flow: Vital Layers for Training-Free Image Editing" [CVPR 2025]

41
/ 100
Emerging

This project helps graphic designers, digital artists, and marketers modify existing images or generate new ones with precise control, all without needing to retrain complex AI models. You input an image or a starting text description and a series of text prompts describing desired changes. The output is a new or edited image that reflects these modifications, allowing for consistent stylistic changes, object additions, or subtle non-rigid transformations across a scene.

407 stars. No commits in the last 6 months.

Use this if you need to perform diverse and consistent image edits, such as changing an object's pose, adding new elements, or altering the overall style of a scene, using simple text descriptions.

Not ideal if you prefer a graphical user interface for visual editing rather than text-based prompts, or if you need extremely fast processing on consumer-grade hardware without significant memory.

digital-art graphic-design content-creation visual-marketing image-manipulation
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

407

Forks

26

Language

Python

License

Last pushed

Jun 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/snap-research/stable-flow"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.