|
--- |
|
license: other |
|
license_name: flux-1-dev-non-commercial-license |
|
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md |
|
|
|
language: |
|
- en |
|
library_name: diffusers |
|
pipeline_tag: text-to-image |
|
|
|
tags: |
|
- Text-to-Image |
|
- ControlNet |
|
- Diffusers |
|
- Flux.1-dev |
|
- image-generation |
|
- Stable Diffusion |
|
base_model: black-forest-labs/FLUX.1-dev |
|
--- |
|
|
|
# FLUX.1-dev-ControlNet-Pose |
|
|
|
This repository contains a Pose ControlNet for FLUX.1-dev model trained by researchers from [Shakker Labs](https://huggingface.co/Shakker-Labs). |
|
|
|
# Model Cards |
|
- The model consists of 4 FluxTransformerBlock and 1 FluxSingleTransformerBlock following the same setting in [Shakker-Labs/FLUX.1-dev-ControlNet-Depth](https://huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Depth). |
|
- This checkpoint is trained on both real and generated image datasets, with 40\*A800 for 75K steps. The batch size 40\*8=320 with resolution=512. The learning rate is set to 1e-5. We use [controlnet_aux](https://github.com/huggingface/controlnet_aux/tree/master/src/controlnet_aux/dwpose) to extract conditions. |
|
- The recommended controlnet_conditioning_scale is 0.7. |
|
|
|
# Showcases |
|
|
|
<div class="container"> |
|
<img src="./assets/teaser.png" width="1024"/> |
|
</div> |
|
|
|
|
|
# Resources |
|
- [InstantX/FLUX.1-dev-Controlnet-Canny](https://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Canny) |
|
- [Shakker-Labs/FLUX.1-dev-ControlNet-Depth](https://huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Depth) |
|
- [Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro](https://huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro) |
|
|
|
# Acknowledgements |
|
This project is released by [Shakker AI](https://www.shakker.ai/). All copyright reserved. |
|
|
