Zac Liu provides a tutorial on how you can use A360 AI Platform to easily run Stable Diffusion model without installing it yourself.
Introduction
Stable Diffusion, the newest generative text-to-image model, has been gaining popularity in the Machine Learning community. It is a powerful tool for content creators and artists. The possibility of its application is infinite.
Model
The checkpoint of Stable Diffusion, or model weights, have been made open source and publicly available. Now anyone can use Stable Diffusion to generate images with just a few words and a few minutes of their time.
However, installing Stable Diffusion model in your local environment might be tricky, depending on the operating system and the type of CPU/ GPU you have. Here we provide an easy way for you to run Stable Diffusion in cloud a environment without any complicated installation process, by using A360 AI Platform Community Edition.
A360 AI Community Edition is freely available to data scientists. You can sign up here.
A360 AI Platform
Once you have access to A360 AI Platform, navigate to Project. From there you can create a project. Then go to Workspace to create a new workspace. Select our custom “stable-diffusion-cpu” image to start a Jupyter Lab workspace; the recommended compute configuration for running Stable Diffusion model is 4 CPU/ 12 GB Memory.
Once your Jupyter server is configured, you will be able to use the starter notebook to begin your experiment! Try out different prompts and see what images can be generated by Stable Diffusion.
Note: Since we only provide CPU compute in the Community Edition, each image takes about 2-3 minutes to generate. If you are interested in using GPU on A360 AI Platform, please reach out to us here.
Resources
- Stable Diffusion public release.
- Refer to this guide to optimize your prompt writing.
- Refer to this guide for the basics of Stable Diffusion.
