Home

Awesome

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 model.

Usage

Results

<img alt="Astronaut on Mars" src="https://github.com/woctezuma/stable-diffusion-colab/wiki/img/astronaut_3xl.jpg" width="256"> <img alt="Astronaut on Mars" src="https://github.com/woctezuma/stable-diffusion-colab/wiki/img/astronaut_1xl.jpg" width="256"> <img alt="Astronaut on Mars" src="https://github.com/woctezuma/stable-diffusion-colab/wiki/img/astronaut_2xl.jpg" width="256">

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

<img alt="Pikachu in Paris" src="https://github.com/woctezuma/stable-diffusion-colab/wiki/img/pikachu_3xl.jpg" width="256"> <img alt="Pikachu in Paris" src="https://github.com/woctezuma/stable-diffusion-colab/wiki/img/pikachu_1xl.jpg" width="256"> <img alt="Pikachu in Paris" src="https://github.com/woctezuma/stable-diffusion-colab/wiki/img/pikachu_2xl.jpg" width="256">

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

References

[1] Rombach, Robin, et al. High-resolution image synthesis with latent diffusion models. CVPR 2022. (models & demo)

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

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

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