This is an implementation of Stability AI's SDXL as a Cog model with LCM LoRA for faster inference.
Follow the model pushing guide to push your own fork of SDXL to Replicate.
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