
This repository provides a checkpoint with trained ControlNet Canny model for FLUX.1-dev model by Black Forest Labs
Training details
XLabs AI team is happy to publish fune-tuning Flux scripts, including: - LoRA π₯ - ControlNet π₯
See our github for train script and train configs.
Training dataset
Dataset has the following format for the training process:
βββ images/
β    βββ 1.png
β    βββ 1.json
β    βββ 2.png
β    βββ 2.json
β    βββ ...
A .json file contains βcaptionβ field with a text prompt.
Inference
To test our checkpoints, use commands presented below.
python3 demo_controlnet_inference.py \
    --checkpoint controlnet.safetensors \
    --control_image "input_image.jpg" \
    --prompt "a handsome viking man with white hair, cinematic, MM full HD"

python3 demo_controlnet_inference.py \
    --checkpoint controlnet.safetensors \
    --control_image "input_image.jpg" \
    --prompt "a dark evil mysterius house with ghosts, cinematic, MM full HD"

License
controlnet.safetensors falls under the FLUX.1 [dev] Non-Commercial License