2023-11-06 20:41:03 +03:00
2023-11-06 20:49:34 +03:00
2023-10-24 14:55:04 -07:00
2023-10-29 23:07:24 +03:00
2023-10-29 23:07:24 +03:00
2023-11-03 01:37:25 +03:00
2023-11-08 21:12:30 +03:00
2023-11-06 20:37:05 +03:00
2023-10-31 22:43:02 +03:00
2023-11-08 17:46:26 +03:00
2023-10-28 22:45:17 +03:00
2023-10-29 00:10:18 +03:00
2023-10-30 21:11:07 +03:00
2023-10-29 23:07:24 +03:00
2023-10-26 20:43:18 +03:00
2023-11-06 20:45:07 +03:00
2023-11-06 21:20:29 +03:00

LCM_Inpaint-Outpaint_Comfy

ComfyUI custom nodes for inpainting/outpainting using the new latent consistency model (LCM)

Inpaint

Outpaint

Prompt Weighting

Note: Requires CPU inference (select CPU in LCMLoader Node). (facing error that i dont know how to fix when using GPU)

Add '+' for more effect and '-' for less effect. Adding more '+' or '-' increases the effects.

FreeU

ReferenceOnly

Style Transfer

Image Variations

Promptless Outpainting

Image Blending

ControlNet/T2I Adapter

T2IAdapter thanks to Michael Poutre https://github.com/M1kep

Place model folders inside 'ComfyUI/models/controlnet'

IP Adapter

Place model folders inside 'ComfyUI/models/controlnet'

How to Use:

Clone into custom_nodes folder inside your ComfyUI directory

git clone https://github.com/taabata/LCM_Inpaint-Outpaint_Comfy

Install requirements after changing directory to LCM_Inpaint-Outpaint_Comfy folder

cd LCM_Inpaint-Outpaint_Comfy
pip install -r requirements.txt

Download the model in diffusers format from https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7/tree/main and place it inside model/diffusers folder in your ComfyUI directory. (The name of the model folder should be "LCM_Dreamshaper_v7")

Load the workflow by choosing the .json file for inpainting or outpainting.

Credits

nagolinc's img2img script

patrickvonplaten's StableDiffusionReferencePipeline

Michael Poutre https://github.com/M1kep T2IAdapters

S
Description
No description provided
Readme
5.7 MiB
Languages
Python 86.4%
JavaScript 11.1%
CSS 1.5%
HTML 1%