Episode Summary
– With prompts that can change over time, and videos that can be as long as multiple minutes
– Can generate 30-second videos (128×128 at 8fps) in 22 seconds!
– Can animate an existing image (cat example)
– Upscale quality with another model
– Not available to the general public (yet)
YouTube Video
Resources
Phenaki
paper.pdf
Dumitru Erhan – Google Scholar
Home ← Dumitru Erhan
Dumitru Erhan | LinkedIn
Julius Kunze | LinkedIn
Julius Kunze – Google Scholar
Santiago Castro – Google Scholar
Mohammad Taghi Saffar – Google Scholar
Home
Han Zhang – Google Scholar
Hernan Moraldo – Google Search
https://twitter.com/hhm
H. Hernan Moraldo
Pieter-Jan Kindermans | LinkedIn
Ruben Villegas | LinkedIn
Ruben Villegas
Google Text to Video AI Phenaki : Longer Video Generation with text story as input – YouTube
Google demos two new text-to-video AI systems, focusing on quality and length – The Verge
Google’s AI Videos Point to a Machine-Generated Future – The Washington Post
Artificial Intelligence: Google and Phenaki release AI video generators
Phenaki – Voicebot.ai
Google launched Phenaki Text to Video AI Generator – Android Infotech
Google’s Imagen takes on Meta’s Make-A-Video as text-to-video AI models ramp up | VentureBeat
Google answers Meta’s video-generating AI with its own, dubbed Imagen Video | TechCrunch
Google Introduces “Phenaki” a text-to-video system turns into 2-minute video – Govt, Policy, and Business Issues forum at WebmasterWorld – WebmasterWorld
Google Unveils Text-To-Video With Imagen Video – YouTube
Imagen Video
AI Now Generates 2Min Videos & Longer! | by Taffy Das | Geek Culture | Oct, 2022 | Medium
https://twitter.com/sundarpichai/status/1578162216335179778
https://twitter.com/doomie
Affiliates
Shure MV7
Shure SM7B
Hashtags
text to video,text to video ai,imagen video,imagen,google ai,google brain,midjourney,make-a-video,meta,stable diffusion,stability ai,craiyon,dalle,dalle2,openai,image generation,video generation,generative ai,meta ai,dall e 2
Automated Transcription
