snap-research/stable-flow
Official implementation for "Stable Flow: Vital Layers for Training-Free Image Editing" [CVPR 2025]
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.
Stars
407
Forks
26
Language
Python
License
—
Category
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.
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"...