Image Editing

Open-weight models

We currently offer two open-weight text-to-image models.

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 kontext --loop

Or to generate a single sample run

python -m flux kontext \
  --img_cond_path <path_to_input_image> \
  --prompt <your_prompt> \
  --num_steps 30 --aspect_ratio "16:9" --guidance 2.5 --seed 1

Note that the flags num_steps, aspect_ratio, guidance and seed are optional. For more available flags see the code.

TRT engine infernece

We provide exports in BF16, FP8, and FP4 precision. Note that you need to install the repository with TensorRT support as outlined here.

python -m flux kontext --loop --trt --trt_transformer_precision <precision>

where <trt_transformer_precision> is either bf16, fp8, or fp4_sdvd32.