Skip to main content

🧬 Automatic1111

Jarvislabs.ai Create Stable Diffusion

Use Automatic 1111 - Stable Diffusion web UI on Jarvislabs out of the box in less than 60+ seconds ⏰. It comes with 10+ preloaded models.

Get started in 2 simple steps.

  • Launch an instance
  • Start with your creative journey

Launch an instance

Start a instance with framework as Automatic 1111. Choose required GPUs and storage.

Jarvislabs.ai Create Stable Diffusion

Access the web UI

Once the instance is up and running, right click on your running instance and select the API endpoint.

Jarvislabs.ai Web Stable Diffusion

This may take a few seconds to load. You can start with your creative journey.

Launch/Modify the parameters used to launch

When the instance is started, we start the launch.py from inside a tmux session. You can check that from the JupyterLab terminal.

From the terminal run the below command

tmux attach -t automatic

The output would look somthing like this.

Jarvislabs.ai Web Stable Diffusion

If you do a 'CTRL + C', the application will stop. You can launch it again using the below command.

cd /home/stable-diffusion-webui/
python launch.py --xformers --subpath=$TOKEN

Use Automatic1111 API

You can use Automatic1111 through API's too. To launch through API, follow the below steps.

tmux kill -t automatic
cd /home/stable-diffusion-webui/
python launch.py --xformers --api --subpath=$TOKEN

Access the API endpoint from the UI.

Jarvislabs.ai Web Stable Diffusion

Right-click on the instance to get the API endpoint, to access the API.

Example:

curl "API_ENDPOINT/sdapi/v1/sd-models"

Learn more about Automatic1111 api here.

Preloaded models

ModelsLink
openjourney-4.0https://civitai.com/models/86/openjourney
nitrosocke/Arcane-Diffusionhttps://huggingface.co/nitrosocke/Arcane-Diffusion
waifu-diffusionhttps://civitai.com/models/44/waifu-diffusion
wavymulder/Analog-Diffusionhttps://huggingface.co/wavymulder/Analog-Diffusion
nitrosocke/classic-anim-diffusionhttps://huggingface.co/nitrosocke/classic-anim-diffusion
nitrosocke/archer-diffusionhttps://huggingface.co/nitrosocke/archer-diffusion
nitrosocke/redshift-diffusionhttps://huggingface.co/nitrosocke/redshift-diffusion
22h/vintedois-diffusion-v0-2https://huggingface.co/22h/vintedois-diffusion-v0-2
wavymulder/portraitplushttps://huggingface.co/wavymulder/portraitplus
deliberate-1.0https://civitai.com/models/4823/deliberate

How to run custom models

If you want to use custom model weights, please place them under /home/stable-diffusion-webui/models/Stable-diffusion/

For example to get started with SD1.5 you can follow the below steps from /home directory.

wget https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt
mv v1-5-pruned-emaonly.ckpt /home/stable-diffusion-webui/models/Stable-diffusion/

You can learn more how to use the UI from the official wiki page.

note
  • Find your favourite open source model missing, let us know on chat option or drop us an email at hello@jarvislabs.ai. We will be happy to add it.

  • We are not the creators of Automatic1111 😊, we are just making it easier to use with Jarvislabs GPU instances. If you are stuck somewhere, we will try our best to help. You can always ping us using the chat.