AI art has grown exponentially in the last few months. Developers, enthusiasts and artists have taken the tools provided and expanded on them in all sorts of unique and innovative ways. The public release of the Stable Diffusion model has allowed some truly stunning results, and one of the offshoots of this has been a very cool tool called Deforum Stable Diffusion. This notebook, which can be operated through Google Colab, creates fun and unique animations like this:
As a little note, I’m aware this might be nonsense to a lot of people. These are experimental projects, things break, things spark and smoke, things just don’t always work right. So patience and stick-to-it-iveness are your greatest allies when dealing with bleeding edge tools like this. You may have to repeat the process a few times to get all the kinks and quirks worked out, but don’t worry there’s a step by step video below for anyone who wants to just jump right in.
To get started you’ll need a Google Colab account, which you can find at this link: https://colab.research.google.com/
With your Colab account you can access powerful GPUs hosted by Google, which negates the need for a powerful computer. There are free and paid versions, the more you pay the more powerful GPU you can access and the faster you can render your animations.
Next you should head over to the Deforum site. Here you’ll find a link to the notebook, a link to the Stable Diffusion download from Huggingface.co and a link to the Discord where you can find a whole community of people working together to build the project and help one another with their art. It’s worth noting that Hugging Face has its own process for downloading and hosts descriptions on their site of how to go through the process.
From here you can follow the process in the video below that takes you through creating your first animation! Can’t wait to see what you make!
Want to learn to create generative art using AI with the author of this article? Check out Tongal Creator Noah Miller's blog tutorial on the subject here.
__
Note From Tongal: This blog is part of a series of Tongal Community-written blog posts that were originally sourced in the Tongal Blog Open Call Project. The views and opinions expressed in this article are those of the author(s) and do not necessarily reflect the official policy or position of Tongal. Read more Tongal Community-written posts here!
