Shakker-Labs
/

FLUX.1-dev-ControlNet-Pose

image-generation

Stable Diffusion

Model card Files Files and versions Community

Edit model card

FLUX.1-dev-ControlNet-Pose

This repository contains a Pose ControlNet for FLUX.1-dev model trained by researchers from 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.
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 to extract conditions.
The recommended controlnet_conditioning_scale is 0.7.

Showcases

Resources

Acknowledgements

This project is released by Shakker AI. All copyright reserved.

Downloads last month: 0

Inference Examples

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Shakker-Labs/FLUX.1-dev-ControlNet-Pose

Base model

black-forest-labs/FLUX.1-dev

Finetuned

this model