A-TIER technique
Veo — Google's text/image/video-to-video model (Google I/O)
100k ft — What is this?
Veo — Google's text/image/video-to-video model (Google I/O)
50k ft — Why care?
Official @google reel introducing Veo at Google I/O: high-def video generation from text, image, and video prompts. Reference for Veo launch.
10k ft — Key takeaways
(no takeaways yet)
5k ft — Tools & techniques
Veo
(no techniques tagged)
1k ft — Deep-dive / try it
Veo can create high-quality, high-def videos from a text, image and video prompt. #GoogleIO #AI
saulin.gomes.11
31w
👏👏👏
Transcript excerpt
Today, I'm excited to announce our newest, most capable genitive video model called VIO. VIO creates high-quality 1080p videos from text, image and video prompts. It can capture the details of your instructions in different visual and cinematic styles. You can prompt for things like aerial shots of a landscape or a time-lapse and further edit your videos using additional prompts. You can use VIO in our new experimental tool called VideoFX. We're exploring features like storyboarding and generating longer scenes. VIO gives you unprecedented creative control. VIO builds upon years of our pioneering genitive video model work, including GQN, Venaki, Walt, VideoPoet, Lumiere and much more. Over the coming weeks, some of these features will be available to select creators through VideoFX at labs.google and the waitlist is open now.