Using stable diffusion AI to make this creative video

Software used:

No items found.

November 10, 2022

Creator Justin Alvey who works on AI, robotics and creative projects created this ingenious video in collaboration with Karen X Cheng.

Testing out Stable Diffusion inpainting on a video
- by @justLV
See below for his process#inpainting #stablediffusion #artificialintelligence pic.twitter.com/XyFk4c1aUg
— Karen X. Cheng (@karenxcheng) November 1, 2022

They have used Stable Infused inpainting method for creating 1000's of variation of phone models and then handpicking the right ones to integrate in the video and used After effects for cleanup and blend it better into the table.
‍

If you want to look at the whole process you should check out this tweeter thread which gives you more detailed insight about the process.

1/ I created this with Stable Diffusion using image inpainting and “walking through the latent space”

Without using tweening, every frame is generated by an interpolated embedding and variable denoising strength, so keeping continuity was tricky

See 🧵for process https://t.co/PI443WQoQg
— Justin Alvey (@justLV) November 1, 2022

Here is a link to Threadreader app for better viewing.

You should definitely check out Justin and Karen's profiles for more similar AI projects.

And a shoutout to Paul Trillo for the inspiration of this project as well as to inspire many other creators to experiment with the AI inpainting technique.

Don't forget to check out our Twitter and Instagram for more.