Skip to content

huchenlei/ComfyUI-layerdiffuse

Repository files navigation

ComfyUI-layerdiffuse

ComfyUI implementation of https://github.com/layerdiffusion/LayerDiffuse.

Installation

Download the repository and unpack it into the custom_nodes folder in the ComfyUI installation directory.

Or clone via GIT, starting from ComfyUI installation directory:

cd custom_nodes
git clone [email protected]:huchenlei/ComfyUI-layerdiffuse.git

Run pip install -r requirements.txt to install python dependencies. You might experience version conflict on diffusers if you have other extensions that depend on other versions of diffusers. In this case, it is recommended to set up separate Python venvs.

Workflows

rgba

If you want more control of getting RGB images and alpha channel mask separately, you can use this workflow. readme1

Blending given FG fg_cond

Blending given BG bg_cond

diff_bg

Forge impl's sanity check sets Stop at to 0.5 to get better quality BG. This workflow might be inferior compared to other object removal workflows. diff_fg

In SD Forge impl, there is a stop at param that determines when layer diffuse should stop in the denoising process. In the background, what this param does is unapply the LoRA and c_concat cond after a certain step threshold. This is hard/risky to implement directly in ComfyUI as it requires manually loading a model that has every change except the layer diffusion change applied. A workaround in ComfyUI is to have another img2img pass on the layer diffuse result to simulate the effect of stop at param. diff_fg_stop_at

Combines previous workflows to generate blended and FG given BG. We found that there are some color variations in the extracted FG. Need to confirm with layer diffusion authors whether this is expected. fg_all

Need batch size = 2N. Currently only for SD15. sd15_cond_joint_bg

Need batch size = 2N. Currently only for SD15. sd15_cond_joint_fg

Need batch size = 3N. Currently only for SD15. sd15_joint

Note