Most of my generative AI experimentation has so far been either with text, including learning ChatGPT and prompt engineering, or with images -- mostly Midjourney, with a little bit of DALL-E 3 and Stable Diffusion. This new creation involves generative audio and video, via Stable Audio and RunwayML respectively.
Space Bar
Midjourney Stills Behind Space Bar
These are the stills that animated the AI film above. Rendered by Midjourney and fed into RunwayML, the collection produced a pretty interesting music video to the soundtrack of a Stable Audio upbeat electronica track. It was a fun and novel way to create a video for a track.
