Make sure you have cog installed.
To run a prediction:
cog predict -i image="./image.png" -i model_type="FLUX" -i source_prompt="a cat sitting in the grass" -i target_prompt="a puppy sitting in the grass"
- Steps = 28
- Guidance (CFG) = 1.5
- TAR guidance = 5.5 – n_max = 24
- Steps = 50
- Guidance (CFG) = 3.5
- TAR guidance = 13.5 – n_max = 33
Project | Arxiv | Demo | ComfyUI
Official Pytorch implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"
The code in this repository is licensed under the Apache-2.0 License.
Flux Dev falls under the FLUX.1 [dev] Non-Commercial License.
FLUX.1 [dev] fine-tuned weights and their outputs are non-commercial by default, but can be used commercially when running on Replicate.