fallenshock/FlowEdit
Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"
Leverages pre-trained diffusion flow models (Stable Diffusion 3, FLUX) to perform zero-shot image editing directly in latent space without requiring image inversion, using configurable hyperparameters (`n_max`, `n_min`) to control edit magnitude. Built on PyTorch with diffusers integration, supporting both standalone CLI usage via YAML configuration and ComfyUI node implementations for visual workflows. Handles multi-prompt editing by encoding source-target prompt pairs as flow guidance signals to achieve localized semantic transformations.
954 stars.
Stars
954
Forks
52
Language
Python
License
MIT
Category
Last pushed
Dec 23, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/fallenshock/FlowEdit"
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
X-GenGroup/Flow-Factory
A unified framework for easy reinforcement learning in Flow-Matching models
OpenImagingLab/FlashVSR
[CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient...
haidog-yaqub/MeanFlow
Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling"...
jy0205/Pyramid-Flow
[ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling