Flexible Diffusion Modeling of Long Videos

…a paper on an astounding new deep generative model for video. Think OpenAI‘s GPT-3 but, instead of generating text given a prompt, their “Flexible Diffusion Model” (FDM) does videos… [Source]

3 Likes

Combine this with my automatic story generation and we’ll have bespoke movies and TV shows soon.

Adobe already has the sound effects covered.

https://research.adobe.com/news/ai-can-generate-realistic-sound-for-video-clips/

2 Likes

Lots of compute → Content

1 Like