$ show fallenshock/FlowEdit
FlowEdit is a PyTorch-based implementation of the FlowEdit algorithm for inversion-free text-guided image editing using pre-trained flow models (Stable Diffusion 3 and FLUX). The system takes an input image and source/target prompts, and edits the image by solving an ODE that combines the source and target trajectories in the latent space. The core algorithm is implemented in FlowEdit_utils.py, with run_script.py orchestrating the experiment execution based on YAML configurations. The repository includes a dataset of images and prompts for numerical evaluation.
The LLM identified 1 files worth highlighting for reuse:
Implements the core FlowEdit algorithm for Stable Diffusion 3 and FLUX models. Provides functions `FlowEditSD3` and `FlowEditFLUX` that perform inversion-free text-based image editing by solving an ODE combining source and target trajectories in latent space. The algorithm is self-contained and relies on the diffusers library, making it reusable in other projects using these models.