What it is
A repository of Google Colab notebooks for launching a Stable Diffusion WebUI with a range of pretrained models, such as Stable Diffusion 1.4, 1.5 and 2.x, Waifu Diffusion, Anything v3 and Midjourney v4 diffusion. Each model has three notebook variants (lite, stable, nightly). The README says the repository is outdated and no longer receives updates, and recommends https://github.com/camenduru/TostUI instead.
Who it's for
- Users who want to run Stable Diffusion WebUI from Google Colab with a specific pretrained model
- Users looking for the DreamBooth & LoRA trainer or the Google Drive install with ControlNet, both of which live on separate branches
Requirements
Requirements
- Google Colab (notebooks open via Open In Colab links)
Setup
Pick a variant and model
Choose lite, stable or nightly, then click the Open In Colab badge in that column for the model you want. lite has a stable WebUI and stable installed extensions. stable has ControlNet v1.1, a stable WebUI, and stable installed extensions. nightly has ControlNet v1.1, the latest WebUI with PyTorch 2.0, and daily installed extension updates.
Use the training or drive branches for other workflows
For the DreamBooth & LoRA trainer, use the
trainingbranch. To install the latest version and ControlNet to Google Drive, use thedrivebranch. Both can be selected fromswitch branches/tags.
Examples
Modern Disney style prompt token
Promptmodern disney styleExpected output: The README says to use these tokens in prompts with the mo_di_diffusion_webui_colab notebook to get the model's effect.
Arcane style prompt token
Promptarcane styleExpected output: Token for the arcane_diffusion_3_webui_colab notebook (nitrosocke/Arcane-Diffusion).
Cyberpunk anime prompt token
Promptdgs illustration styleExpected output: Token for the cyberpunk_anime_diffusion_webui_colab notebook (DGSpitzer/Cyberpunk-Anime-Diffusion).
Midjourney v4 prompt token
Promptmdjrny-v4 styleExpected output: Token for the midjourney_v4_diffusion_webui_colab notebook (prompthero/midjourney-v4-diffusion).
Pros & cons
Pros
- Pro:Wide selection of ready-made notebooks for many models, including Stable Diffusion 1.x and 2.x, inpainting and depth variants
- Pro:Three variants (lite, stable, nightly) cover different stability and feature trade-offs, with ControlNet v1.1 in stable and nightly
- Pro:Separate branches provide a DreamBooth & LoRA trainer and a Google Drive install
Cons
- Con:The repository is outdated and no longer receives updates; the author recommends TostUI instead
- Con:Provided text gives no detailed setup steps beyond opening the Colab notebooks
Images
Related
Repo AUTOMATIC1111/stable-diffusion-webui
Stable Diffusion web UI
Repo Comfy-Org/ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Repo invoke-ai/InvokeAI
Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.
Repo hypit-ai/hypit
Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views.
Repo divamgupta/diffusionbee-stable-diffusion-ui
Diffusion Bee is the easiest way to run Stable Diffusion locally on your M1 Mac. Comes with a one-click installer. No dependencies or technical knowledge needed.
Repo Acly/krita-ai-diffusion
Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.