Skip to content

Stable Diffusion XL training and inference with LCM LoRA as a cog model

Notifications You must be signed in to change notification settings

lucataco/cog-sdxl-lcm

 
 

Repository files navigation

Cog-SDXL-LCM

This is an implementation of Stability AI's SDXL as a Cog model with LCM LoRA for faster inference.

Development

Follow the model pushing guide to push your own fork of SDXL to Replicate.

Basic Usage

Download weights first to apply the LCM-LoRA for SDXL

cog run python script/download_weights.py

Then for predictions,

cog predict -i prompt="a photo of TOK"
cog train -i input_images=@example_datasets/__data.zip -i use_face_detection_instead=True
cog run -p 5000 python -m cog.server.http

About

Stable Diffusion XL training and inference with LCM LoRA as a cog model

Topics

Resources

Stars

Watchers

Forks

Languages

  • Python 100.0%