fallenshock/FlowEdit

Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"

47
/ 100
Emerging

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.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

954

Forks

52

Language

Python

License

MIT

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.