Runpod Docker - Automatic1111 on Vast.AI (Archive)

These used to be my recommended config, but since Rob from AI Dock has written me a custom docker image that comes with everything I need, I no longer uses the images from Runpod

Instance Config

Read the official docs if you have never used vast before. My recommendation here is a modified version of the recommended settings, based on my experience.

My old recommended config (archive)

Find the config from the recommended list for runpod/stable-diffusion:web-automatic-8.0.1 image, but use the Select button to the right of the image, and change to runpod/stable-diffusion:web-automatic-8.0.3, keep everything else the same and deploy.

• Docker image: runpod/stable-diffusion:web-ui-10.1.1 Docker Hub Tag
  • vastai recommends the runpod/stable-diffusion:web-automatic-8.0.1 image but that image won’t run Control Net successfully. I have been using the 8.0.3 version instead, and it works perfectly.
• Disk Space to allocation: 50 - 100 GB
  • depending on how much space you need for generation and models
  • I usually set it to 100 GB because I generate at high res and with lots of models
  • You can’t change the disk size once an instance was created
  • If you’re running large batch jobs, having good amount of disk space would save you a lot of time
  • There might be more instances available if you allocate less disk space, though I personally won’t go under 30 GB

Docker Images

This is the latest docker image. It comes with SDXL models so it’s hanyd — you won’t need to dwonload the base nor refiner. But you should still download the VAE from hugging space

• runpod/stable-diffusion:web-ui-10.1.1
  • runpod/stable-diffusion:web-ui-10.1.1

Available tags

• Docker Hub: stable diffusion tags

Continue to Instance Setup