Connect with us

Hi, what are you looking for?

GainThatFlavour.comGainThatFlavour.com

Tech News

Google’s Lumiere brings AI video closer to real than unreal

Single frame from a video showing multiple AI-generated clips
Still frame from a teaser reel of Lumiere clips | Image: Google

Google’s new video generation AI model Lumiere uses a new diffusion model called Space-Time-U-Net, or STUNet, that figures out where things are in a video (space) and how they simultaneously move and change (time). Ars Technica reports this method lets Lumiere create the video in one process instead of putting smaller still frames together.

Lumiere starts with creating a base frame from the prompt. Then, it uses the STUNet framework to begin approximating where objects within that frame will move to create more frames that flow into each other, creating the appearance of seamless motion. Lumiere also generates 80 frames compared to 25 frames from Stable Video Diffusion.

Admittedly, I am more of a text reporter than a video person, but…

Continue reading…

You May Also Like

Editor's Pick

Travis Fisher The Environmental Protection Agency’s (EPA’s) greenhouse gas (GHG) rule for power plants was published in May 2023 and the original comment period...

Tech News

The OnePlus Keyboard 81 Pro shares a lot in common with the Keychron Q1 Pro, rendering it a great alternative when it’s on sale....

Editor's Pick

Colin Grabow The George II is a case study in Jones Act dysfunction. Delivered in December 1980 by a now‐​defunct Louisiana shipyard, the forty‐​three‐​year‐​old containership—long in...

Editor's Pick

Jeffrey A. Singer I wrote here in 2020 and here in 2022, and I warned lawmakers in oral testimony here last March, nitazenes might soon...