This repository provides a collection of ControlNet checkpoints for FLUX.1-dev model by Black Forest Labs

See our github for comfy ui workflows.

See our github for train script, train configs and demo script for inference.

Models

Our collection supports 3 models:

• Canny
• HED
• Depth (Midas)

Each ControlNet is trained on 1024x1024 resolution and works for 1024x1024 resolution. We release v3 versions - better and realistic versions, which can be used directly in ComfyUI!

Please, see our ComfyUI custom nodes installation guide

Examples

See examples of our models results below.
Also, some generation results with input images are provided in "Files and versions"

Inference

To try our models, you have 2 options:

1. Use main.py from our official repo
2. Use our custom nodes for ComfyUI and test it with provided workflows (check out folder /workflows)
3. Use gradio demo

See examples how to launch our models:

Canny ControlNet (version 3)

1. Clone our x-flux-comfyui custom nodes
2. Launch ComfyUI
3. Try our canny_workflow.json

Depth ControlNet (version 3)

1. Clone our x-flux-comfyui custom nodes
2. Launch ComfyUI
3. Try our depth_workflow.json

HED ControlNet (version 3)

1. Clone our x-flux-comfyui custom nodes
2. Launch ComfyUI
3. Try our hed_workflow.json

License

Our weights fall under the FLUX.1 [dev] Non-Commercial License