RunPod: Train your model and upload it to Storj
Playing with the stock Stable Diffusion models is fun, but eventually, you will want to train your own model. The template has a Jupyter notebook to guide you in fine-tuning a Stable Diffusion model with DreamBooth.
JupyterLab is deployed with secure access enabled. It requires an access token, which RunPod generated for you when creating the Docker container.
To get to the access token, click on the hamburger button of your pod and select the Edit Pod menu item.
Expand the Environment Variables sections, find the JUPYTER_PASSWORD variable, and copy its value to the clipboard.
The JupyterLab runs on port 8888.
Click on the "Connect to HTTP Service [Port 8888]" button, and it will open in a separate tab in your web browser.
Paste the password from the clipboard in the "Password or token" field and click the "Log in" button.
You are now in the JupyterLab interface. Look at the file browser sidebar on the left. Find the DreamBooth_Stable_Diffusion.ipynb file and double-click it.
The notebook will open. Follow the instructions inside the notebook on how to train your model with DreamBooth.
To execute a step from the notebook, click on the Play button or use the Ctrl+Enter keyboard shortcut.
