1、Stable Diffusion

{% link stable-diffusion,CompVis,https://github.com/CompVis/stable-diffusion %}

Stable Diffusion is a latent text-to-image diffusion model.this model uses a frozen CLIP ViT-L/14 text encoder to condition the model on text prompts.

input	output

但是想要运行Stable Diffusion，需要至少10GB VRAM的GPU。

2、stable-diffusion-webui

{% link stable-diffusion-webui,AUTOMATIC1111,https://github.com/AUTOMATIC1111/stable-diffusion-webui %}

Stable Diffusion web UI

3、stable-diffusion-webui-colab

{% link stable-diffusion-webui-colab,camenduru,https://github.com/camenduru/stable-diffusion-webui-colab/tree/drive %}

Stable Diffusion WebUI Colab With Google Drive

🦒 Install the WebUI Colab to Google Drive

.ipynb File	Colab Page	Function
install.ipynb		One Time Install & Update
run.ipynb		Run
add.ipynb		Add Model