Yulia Rubanova (@YuliaRubanova) header
Yulia Rubanova (@YuliaRubanova) profile picture

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
Photo by Yulia Rubanova (@YuliaRubanova)Photo by Yulia Rubanova (@YuliaRubanova)Photo by Yulia Rubanova (@YuliaRubanova)Photo by Yulia Rubanova (@YuliaRubanova)Photo by Yulia Rubanova (@YuliaRubanova)Photo by Yulia Rubanova (@YuliaRubanova)Photo by Yulia Rubanova (@YuliaRubanova)Photo by Yulia Rubanova (@YuliaRubanova)Photo by Yulia Rubanova (@YuliaRubanova)Photo by Yulia Rubanova (@YuliaRubanova)
Yulia Rubanova retweeted
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 🧵
142
212
114
2,093
811,465
Yulia Rubanova retweeted
What if your footage could become anything? It can. Just use Gemini Omni on the Pika MCP.
13
18
9
115
65,682
Yulia Rubanova retweeted
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 new prompt to add to the fofr-benchmark: > a man counts out loud from 1 to 10, using his fingers and holding them up as he goes > a man counts out loud from 1 to 10, "1, 2, 3, 4, 6, 7, 8, 9, 10", he counts using his fingers and holds them up as he goes
15
11
9
168
42,916
Yulia Rubanova retweeted
Genuinely amazed by how many generalist visual capabilities one can squeeze out of this model
A quick test of using Omni to edit a video and add labelled bounding boxes around objects. > Add a labelled bounding box around the monster truck and the flag
1
5
60
8,852
Yulia Rubanova retweeted
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..
41
35
6
417
30,402
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
2
13
64
3,472
Yulia Rubanova retweeted
We sat down with @OfficialLoganK @nbrichtova @doomie @gbarthmaron to talk about Gemini Omni Flash. It was pretty wild.
5
20
8
203
42,373
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!
4
7
2
60
4,395
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 🧵👇
15
29
2
223
44,626
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!
You went 🍌🍌 for Nano Banana. Now, meet Nano Banana Pro.  It’s SOTA for image generation + editing with more advanced world knowledge, text rendering, precision + controls. Built on Gemini 3, it’s really good at complex infographics - much like how engineers see the world:)
1
10
71
11,571
Yulia Rubanova retweeted
Character consistency is all the rage now. Give it a try in Flow!
Keeping characters consistent in your AI films can be difficult. Flow's Ingredients to Video feature makes character consistency a breeze - and better yet, it's now available to both Ultra AND Pro users! 🔥
1
1
8
2,182
Yulia Rubanova retweeted
Here is @GoogleDeepMind's Sima agent following different instructions inside a world generated by Genie 3.
7
24
5
177
62,663
Yulia Rubanova retweeted
Even though my team built this capability, it’s still absolutely mind-blowing to me that this works: you can literally put anything (consistent characters, objects, scenes, …) into the worlds you generate with Veo.
In filmmaking, consistency is key to a strong narrative. Using Flow, you can build stories with consistent characters, scenes, and objects across multiple clips— giving you more creative control.
5
6
92
10,956
Yulia Rubanova retweeted
Greenfield (@GDMGreenfield), our in-house creative team, is now on X! Follow them to learn about the latest tips and tricks for Veo 3 and our other generative models.
Greenfield prompt tip of the day: Add excitement to your shots with Veo 3 camera controls! You can use multiple camera controls within a single prompt by stringing together a sequence of camera movements. For example, you can try combining effects over time: "The camera position is stationary," "Move the camera backward," "Move the camera down," "Move the camera to the right." Experiment to create dynamic scenes!
2
16
4,070
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:
2
2
15
3,634
Yulia Rubanova retweeted
Can’t wait for everyone to give this a try. 🔥This has been long in the making by a fantastic team. Bringing multiple characters, objects, scenes or literally anything you want into your generations with Veo’s stunning visual quality is a big unlock for visual storytelling, filmmaking, and world building. Now in Flow: labs.google/flow/about
Replying to @SebJefferies
Reference-powered video You can now give Veo images of a scene, outfit, or object, and it will generate a full video aligned with your creative direction. You give the look,Veo gives you motion. 👇
3
20
2,560
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. 🧵
641
1,292
619
7,952
1,565,374
Get into the zone with Flow. 🎬 It combines the best of our most advanced models Veo, Imagen and Gemini into 1️⃣ master filmmaking tool - helping you weave cinematic clips, dynamic scenes, and compelling narratives into stories with consistent results.
33
127
42
790
134,793
Yulia Rubanova retweeted
Brush🖌️ is now a competitive 3D Gaussian Splatting engine for real-world data and supports dynamic scenes too! Check out the release notes here: github.com/ArthurBrussee/bru…
12
61
6
384
28,891
Yulia Rubanova retweeted
[1/4] Ever wondered what it would be like to use images—rather than text—to generate object and background compositions? We introduce VisualComposer, a method for compositional image generation with object-level visual prompts.
1
24
2
150
18,356