Generating video from textual descriptions with Phenaki
In this new episode of #ResearchBytes, Mohammad Babaeizadeh and Ruben Villegas from the Brain Team at Google Research tell us how they developed Phenaki, a model that can generate realistic videos from sequences of text prompts. Watch this episode to learn more about Phenaki and how it was created, and watch some interesting results with the authors’ commentary and insights!
Resources:
Read the paper → https://arxiv.org/abs/2210.02399
Learn how it works → https://phenaki.research.google/
Chapters:
0:00 - Intro
0:31 - Which real world problem is Phenaki solving?
1:21 - What did the team do to develop this tool?
3:16 - How did the team create this tool?
3:55 - Team observations about Phenaki
7:25 - What’s next for Phenaki?
Watch more episodes of ResearchBytes → https://goo.gle/ResearchBytes
Subscribe to the Google Research Channel → https://goo.gle/GoogleResearch
#ResearchBytes