Tatiana

Research Scientist @GoogleDeepMind - GenMedia - Veo 🇨🇴

[PJ Ace @PJaccetturo]

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 👇🏼)

[Ruben Villegas @RubenEVillegas]

The best video I have seen by far. Obviously not biased lol

[Yuge Shi (Jimmy) @YugeTen]

I'm going to generate 1000 of these and stare at them when I'm sad #Veo3

[Ben Poole @poolio]

knock knock #veo3

[Ruben Villegas @RubenEVillegas]

Classic #veo3

[Tatiana @ZePoLiTaT]

more veo capybaras <3

[Ben Poole @poolio]

critical capybara #veo3

[Ruiqi Gao @RuiqiGao]

And Veo 2 now supports camera control :) 📸 #veo

[Tatiana @ZePoLiTaT]

Pour me a glass of that magical #Veo3 drink! 🌟

[Ruben Villegas @RubenEVillegas]

Ever wonder what a chicken dog sounds like? #veo3

[Ruben Villegas @RubenEVillegas]

Bars! #veo3

[Yutian Chen @yutianc]

Tough twister challenge #Veo3

[Nikos Kolotouros @nikoskolot]

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:

[Tatiana @ZePoLiTaT]

Very excited to showcase our work on Veo controls 🤩

[Google DeepMind @GoogleDeepMind]

Motion master 👋

Define the exact movement of objects in your video. Select an object 🤏 and define its path ↩️, and Veo will bring them to life in motion.

[Nick Matarese @nmatares]

"a giraffe pulls a wheelie on a dirt bike in the streets of NYC" - #Veo3

[Google DeepMind @GoogleDeepMind]

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. 🧵

[Marques Brownlee @MKBHD]

Can confirm: Google's VEO 2 consistently produces more "correct" results than SORA. Make of that what you will

[Jerrod Lew @jerrod_lew]

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?

[Jon Barron @jon_barron]

I've never seen a more polished paper teaser video than this one. The 3D Gaussians even cast shadows!

[Daniel Geng @dangengdg]

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!

[Google Colombia @GoogleColombia]

🚨📣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 → https://t.co/mVDHf4wVr3