Tatiana (@zepolitat) 's Twitter Profile
Tatiana

@zepolitat

Research Scientist @GoogleDeepMind. Ph.D. in Robotics and Autonomous Systems. Love cycling, doodling and making robots play with squishy/liquidy things. 🇨🇴

ID: 53661871

calendar_today04-07-2009 12:48:44

743 Tweet

647 Followers

1,1K Following

Google Colombia (@googlecolombia) 's Twitter Profile Photo

🚨📣NUEVO CURSO disponible en Colombia: Fundamentos de #IA de Google Aprende a utilizar herramientas de IA para aumentar tu productividad y hacer realidad tus ideas. ✅Sin experiencia previa ✅A tu propio ritmo ✅Certificado y en español Más info → goo.gle/CertificadosDe…

Daniel Geng (@dangengdg) 's Twitter Profile Photo

What happens when you train a video generation model to be conditioned on motion? Turns out you can perform "motion prompting," just like you might prompt an LLM! Doing so enables many different capabilities. Here’s a few examples – check out this thread 🧵 for more results!

Jerrod Lew (@jerrod_lew) 's Twitter Profile Photo

Google Veo 2 is fantastic when it comes to physics. I put it to the test with a range of outputs to see how liquids and solids would react with each other. What do you think?

Google DeepMind (@googledeepmind) 's Twitter Profile Photo

Video, meet audio. 🎥🤝🔊 With Veo 3, our new state-of-the-art generative video model, you can add soundtracks to clips you make. Create talking characters, include sound effects, and more while developing videos in a range of cinematic styles. 🧵

Nikos Kolotouros (@nikoskolot) 's Twitter Profile Photo

TLDR: Given 1-3 reference images and a text prompt, you can use Veo to compose them in a video. Here's me in a few weeks from now in Greece:

PJ Ace (@pjaccetturo) 's Twitter Profile Photo

I used to shoot $500k pharmaceutical commercials. I made this for $500 in Veo 3 credits in less than a day. What’s the argument for spending $500K now? (Steal my prompt below 👇🏼)