Fill

Open-weight models

FLUX.1 Fill introduces advanced inpainting and outpainting capabilities. It allows for seamless edits that integrate naturally with existing images.

Examples

Open-weights usage

The weights will be downloaded automatically to checkpoints/ from HuggingFace once you start one of the demos. Alternatively, you may download the weights manually and put them in checkpoints/, or you can also manually link them with the following environment variables:

export FLUX_MODEL=<your model path here>
export FLUX_AE=<your autoencoder path here>

For interactive sampling run

python -m flux fill --loop

Or to generate a single sample run

python -m flux fill \
  --img_cond_path <path_to_input_image> \
  --img_mask_path <path_to_input_mask>

The input_mask should be an image of the same size as the conditioning image that only contains black and white pixels; see an example mask for this image.

We also provide an interactive streamlit demo. The demo can be run via

streamlit run demo_st_fill.py