https://github.com/woctezuma/stable-diffusion-colab

Colab notebook for Stable Diffusion Hyper-SDXL.
https://github.com/woctezuma/stable-diffusion-colab

colab colab-notebook colaboratory deep-learning diffusers diffusion diffusion-models google-colab google-colab-notebook google-colaboratory huggingface-diffusers hyper-sd hyper-sdxl image-generation stable-diffusion stable-diffusion-xl text-to-image text-to-image-generation text-to-image-synthesis text2image

Last synced: 7 days ago
JSON representation

Colab notebook for Stable Diffusion Hyper-SDXL.

• Host: GitHub
• URL: https://github.com/woctezuma/stable-diffusion-colab
• Owner: woctezuma
• License: mit
• Created: 2022-08-24T19:02:08.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-08-02T16:52:34.000Z (7 months ago)
• Last Synced: 2025-02-07T19:13:41.334Z (14 days ago)
• Topics: colab, colab-notebook, colaboratory, deep-learning, diffusers, diffusion, diffusion-models, google-colab, google-colab-notebook, google-colaboratory, huggingface-diffusers, hyper-sd, hyper-sdxl, image-generation, stable-diffusion, stable-diffusion-xl, text-to-image, text-to-image-generation, text-to-image-synthesis, text2image
• Language: Jupyter Notebook
• Homepage: https://github.com/Stability-AI/generative-models
• Size: 51.8 KB
• Stars: 320
• Watchers: 5
• Forks: 81
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-stable-diffusion - stable-diffusion-colab

README

        
# Stable Diffusion Hyper-SDXL - Colab

The goal of this repository is to provide a Colab notebook to run the text-to-image [Stable Diffusion Hyper-SDXL][huggingface-latest-weights] model.

## Usage

-   Run [`stable_diffusion.ipynb`][colab-notebook-stable-diffusion].

[![Open In Colab][colab-badge]][colab-notebook-stable-diffusion]

## Results

  



Different results obtained with the text prompt: "a photo of an astronaut riding a horse on Mars" using Stable Diffusion XL.



---

  



Different results obtained with the text prompt: "a photo of Pikachu fine dining with a view to the Eiffel Tower" using Stable Diffusion XL.



## References

[1] Rombach, Robin, et al. [*High-resolution image synthesis with latent diffusion models*][stable-diffusion-paper]. CVPR 2022.

([models][huggingface-models] & [demo][huggingface-demo])

[2] Karras, Tero, et al. [*Elucidating the Design Space of Diffusion-Based Generative Models*][sampler-schedule-paper]. NeurIPS 2022. ([code][edm-implementation])

[3] Luo, Simian, et al. [*Latent Consistency Models: Synthesizing HR Images with Few-Step Inference.*][lcm-paper] arXiv 2023. ([code][lcm-github])

[4] Luo, Simian, et al. [*LCM-LoRA: A Universal Stable-Diffusion Acceleration Module.*][lcm-lora-paper] arXiv 2023.

[stable-diffusion-paper]: 

[sampler-schedule-paper]: 

[lcm-paper]: 

[lcm-lora-paper]: 

[huggingface-blogpost]: 

[huggingface-lcm-blogpost]: 

[huggingface-models]: 

[huggingface-latest-weights]: 

[huggingface-sd2-resolution-512]: 

[huggingface-sd2-resolution-768]: 

[huggingface-sd2-examples]: 

[huggingface-sd21-examples]: 

[huggingface-demo]: 

[dreamstudio-demo]: 

[edm-implementation]: 

[lcm-github]: 

[colab-notebook-stable-diffusion]: 

[colab-badge]: