https://github.com/dhanushreddy291/sdxl-turbo-cog

SDXL-Turbo is a real-time synthesis model, derived from SDXL 1.0, and utilizes a training method called Adversarial Diffusion Distillation (ADD). It achieves high image quality within one to four sampling steps
https://github.com/dhanushreddy291/sdxl-turbo-cog

replicate sdxl sdxlturbo stable-diffusion

Last synced: 28 days ago
JSON representation

SDXL-Turbo is a real-time synthesis model, derived from SDXL 1.0, and utilizes a training method called Adversarial Diffusion Distillation (ADD). It achieves high image quality within one to four sampling steps

• Host: GitHub
• URL: https://github.com/dhanushreddy291/sdxl-turbo-cog
• Owner: dhanushreddy291
• License: mit
• Created: 2023-12-01T17:36:55.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2023-12-02T05:53:40.000Z (almost 2 years ago)
• Last Synced: 2024-04-28T05:05:13.042Z (over 1 year ago)
• Topics: replicate, sdxl, sdxlturbo, stable-diffusion
• Language: Python
• Homepage: https://replicate.com/dhanushreddy291/sdxl-turbo
• Size: 332 KB
• Stars: 7
• Watchers: 1
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README.MD
  • License: LICENSE

Awesome Lists containing this project

README

          
# stabilityai/sdxl-turbo

This is an implementation of the [stabilityai/sdxl-turbo](https://huggingface.co/stabilityai/sdxl-turbo) as a Cog model. [Cog packages machine learning models as standard containers.](https://github.com/replicate/cog)

First, download the pre-trained weights:

    cog run script/download-weights

Then, you can run predictions:

    cog predict -i prompt="21 years old girl,short cut,beauty,dusk,Ghibli style illustration"

## Example:

"21 years old girl,short cut,beauty,dusk,Ghibli style illustration"

![21 years old girl,short cut,beauty,dusk,Ghibli style illustration](out-0.png)

# Note:

The model is intended for research purposes only. Possible research areas and tasks include

 - Research on generative models.

 - Research on real-time applications of generative models.

 - Research on the impact of real-time generative models.

 - Safe deployment of models which have the potential to generate harmful content.

 - Probing and understanding the limitations and biases of generative models.

 - Generation of artworks and use in design and other artistic processes.

 - Applications in educational or creative tools.