Skip to main content

🧬 Automatic1111

Jarvislabs.ai Create Stable Diffusion

Use Automatic1111 - 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

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

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​

We have loaded 50+ models for you to start with. You can find the list of models here.

ControlNet​

ControlNet is a popular technique, that gives you control over the images generated using StableDiffusion. We have created a guide for you to help with you to understand the various techniques you can use ControlNet in Automatic1111. You can find the guide here.