
Staff RS @GoogleDeepMind, Gemini Omni controllability, co-led Veo3 and Veo3.1 Ingredients-to-Video. Physical and spacial reasoning, agentic video generation.
London, England
Joined October 2015
- Tweets129
- Following581
- Followers1K
- Likes526
We worked hard on this Omni 1.2 Flash launch to bring you a model that's faster, with better dialogue and lip sync, and better ability to condition on audio and video clips. And my favorite feature: multi-turn conversational editing to continue refining your vision. Try it out!
Meet Gemini Omni 1.2 Flash ⚡️
We’ve made the model more cost-effective, bumped the video generation and editing limit up to 15 seconds, and made updates to how scenes hold together over time. We've also given character speech an upgrade, reduced visual glitches like jump cuts, and made sure the model stays even truer to any reference assets you upload.
So… what does all of that actually mean for you?
It gives you more room to tell your story. With up to 15 seconds to work with, you have more flexibility to create what you need — videos look more cinematic and smooth, offering stronger consistency that keeps objects anchored from start to finish. And when characters speak, the dialogue sounds more fluid and natural.
Creators and everyday users can start directing scenes and multi-turn edits in @FlowbyGoogle, generating 15-second clips at no additional cost in Google Vids, or creating 15-second videos in the @GeminiApp. Plus, for developers and businesses building with the API, we've dropped the price by 30% from the previous generation, making it available at just $0.07 per second for 720p video.
Watch the model in action as it turns a single style frame into a 4-shot, 15-second macro science explainer of a living beehive ↓
7
31
1,010
Our Gemini Omni team is hiring in London and Zurich! If you want to work on exciting new challenges in video generation with the fantastic team of people, consider applying!
We are hiring research engineers and scientists for the Gemini Omni team in London and Zurich.
If you are excited about pushing the frontier of generative media, join us!
google.com/about/careers/app…
google.com/about/careers/app…
Gemini Omni 1.1 Flash is our newest multimodal model for video generation and editing. It delivers a new suite of creative capabilities and controls for developers 🎥
With this update you can:
🎬 Extend your scenes
🎯 Specify starting and ending frames of a shot
➕ Add video input references
✨ Upscale your favorite takes up to 4K
⚡ Test ideas quickly in 360p
See these in action 🧵
Yulia Rubanova retweeted
What if your footage could become anything?
It can. Just use Gemini Omni on the Pika MCP.
Omni takes the top spot in the Video Arena 👑
BREAKING: Gemini Omni Flash by @GoogleDeepMind is 1st overall on Video Arena with an Elo of 1404.
Gemini Omni Flash establishes a 101 point Elo gap over Seedance 2.0 Mini by @BytePlusGlobal in 2nd place, one of the largest leaps we’ve ever seen on Video Arena.
This establishes Google as the world’s leading video generation lab, with a leap of 7 positions from their Veo series.
Congratulations to the @GoogleDeepMind team on this accomplishment!
One year later with Omni and this test can pass. I saw it getting pretty close, so I tweaked the prompt:
> A video of a man counting to 10 on his fingers, show the number in the corner. A new number every 1s, no dialogue other than the numbers he says. He uses two hands for numbers bigger than 5.
- the model does 1 to 5 consistently well
- struggles more when two hands are used, usually on 7 and 8
- if you ask it to count faster, errors increase
- it keeps a good cadence
🤖 Made with AI
A few days post-I/O, people are starting to see what Gemini Omni is capable of.
Being a part of this project from the early days, it’s been amazing to watch native multimodality open up a new space of possibilities for video generation. Give it a try.
We’re dropping Gemini Omni: our first step towards a model that can create anything from anything - starting with video.
It combines Gemini’s intelligence with our generative media systems - representing a leap forward in world understanding, multimodality, and editing 🧵
6
773
not sure why nobody is talking about this but Google Omni is insane at video editing
Original Video (left) vs Omni Edited Video (right)
everyone is comparing it to Seedance and missing the point completely. Seedance is for generating videos from scratch. Google Omni is for editing videos that already exist. which are two completely different use cases
this is like when Nano Banana 1 first came out and nobody realized how big it was going to be. this is the first AI that can actually properly edit videos..
i've generated a few hundred videos with this model and it can do literally any type of edit you can think of. changing voices, swapping characters, removing watermarks, adding captions, transitions, pop ups, whatever. if you can describe the edit you want it can do it
this completely crushes every other model on the market when it comes to video editing. nothing else even comes close right now
and this is just the flash model. imagine what the pro version is going to be able to do when it drops in a couple months
this should have way more hype than it's getting..
Yulia Rubanova retweeted
The likeness preservation and natural realism coming out of Gemini #Omni Flash is absolutely unreal 🤯
Huge shoutout to the insanely talented team for pushing these boundaries. The team absolutely cooked. 👨🍳🔥
If Flash is this good... imagine what Pro is about to unleash. 👀✨
🤖 Made with AI
Yulia Rubanova retweeted
We sat down with @OfficialLoganK @nbrichtova @doomie @gbarthmaron to talk about Gemini Omni Flash. It was pretty wild.
Yulia Rubanova retweeted
Super excited to see Gemini Omni finally out in the world! Having been part of this project since its inception, I've seen how its native multimodal capabilities can redefine what's possible. We're truly entering the "Nano Banana era" for video generation. Give it a try!
Excited to head to ICLR 2026 in Rio de Janeiro 🇧🇷!
Happy to chat about video generation, controllability and world models!
We released Veo 3.1 Ingredients more than 6 months ago, and it is still ranking on top!
BREAKING: Veo 3.1 Fast and Veo 3.1 by @GoogleDeepMind are in 1st and 2nd place on Multi-Image to Video Arena
These models can successfully reference multiple input images to create a video that users love
At an average generation time of 48 seconds, they are also the two fastest video generation models
Huge congrats to the @GoogleDeepMind team for this achievement!
7
658
New version Ingredients to Video is out!
Now with a portrait mode, better storytelling and consistency -- now available directly on Youtube Shorts.
It is the most rewarding experience to be part of this team and put this into the hands of real users.
We’re updating Veo 3.1 Ingredients to Video to help create more expressive and dynamic clips, produce better visual consistency and more. 📽️
Here’s what’s new 🧵
8
452
Veo is officially a world simulator for robotics! 🤖🎥
We used action-conditioned Veo to evaluate robotics policies entirely in a generated video. This is a game-changer for scalable, safe robotics testing. Loved working with the team on this!
Generalist robots need a generalist evaluator. But how do you test safety without breaking things? 💥
🌎 Introducing our new work from @GoogleDeepMind:
Evaluating Gemini Robotics Policies in a Veo World Simulator
veo-robotics.github.io
🧵👇
Yulia Rubanova retweeted
So excited to finally talk about this work!
Veo is a surprisingly strong world simulator. We fine-tuned Veo on action-conditioned, multi-view robotics data.
Key result: running a policy in the world model is strongly correlated with real-world results.
A few important take-aways:
1) Veo Robotics models real-world physics and robot interactions
2) The base model's world knowledge is retained after fine-tuning and can model OOD scenarios not seen in the robotics data
3) The world model can be used to score task success or failure for a given policy
4) This proves useful for predictive red teaming: simulate dangerous or rare scenarios that would be difficult or irresponsible to execute on the real robot, and judge its performance
I couldn't be more excited about where generalist video models are headed.
Generalist robots need a generalist evaluator. But how do you test safety without breaking things? 💥
🌎 Introducing our new work from @GoogleDeepMind:
Evaluating Gemini Robotics Policies in a Veo World Simulator
veo-robotics.github.io
🧵👇
Yulia Rubanova retweeted
Our second Nano Banana in three months 🚢 🚢. Super proud of the team!!
Looking forward to seeing what you'll create with it. Any feedback welcome!





















