Skip to content

Stable Diffusion XL training and inference as a cog model

Notifications You must be signed in to change notification settings

gymdreams8/cog-sdxl

This branch is 15 commits behind replicate/cog-sdxl:main.

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ca9883b · Aug 22, 2023

History

38 Commits
Aug 3, 2023
Aug 1, 2023
Aug 10, 2023
Aug 6, 2023
Aug 16, 2023
Aug 22, 2023
Aug 6, 2023
Aug 6, 2023
Aug 16, 2023
Aug 19, 2023
Aug 6, 2023
Aug 12, 2023
Aug 10, 2023

Repository files navigation

Cog-SDXL

Replicate demo and cloud API

This is an implementation of Stability AI's SDXL as a Cog model.

Development

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

Basic Usage

for prediction,

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

Update notes

2023-08-17

  • ROI problem is fixed.
  • Now BLIP caption_prefix does not interfere with BLIP captioner.

2023-08-12

  • Input types are inferred from input name extensions, or from the input_images_filetype argument
  • Preprocssing are now done with fp16, and if no mask is found, the model will use the whole image

2023-08-11

  • Default to 768x768 resolution training
  • Rank as argument now, default to 32
  • Now uses Swin2SR caidas/swin2SR-realworld-sr-x4-64-bsrgan-psnr as default, and will upscale + downscale to 768x768

About

Stable Diffusion XL training and inference as a cog model

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%