Nick Matarese

Incredibly proud to have brought Flow to life with an incredible team. Flow truly was built with and for creatives since day 1 and I cant wait to see the stories creators tell with these amazing tools. #GoogleFlow try it out at flow.google

@LinusEkenstam Would have grabbed a coffee with ya. You are close by

Time for a social experiment: I’m downtown San Francisco, and if you see this, you can control me. yup. ➡️ Brunch Side-quest: Where should I go and eat brunch? Tag someone who I should invite New instructions & quests will be unlocked shortly. Live coverage below ⤵️

I had to do this of course - test out the new Google Omni Flash model with my favorite 3d art sandbox - Dreams. Just a quick test for now.. I'll be sharing more examples and techniques soon but wanted to show you this one. There's something very fitting about combining "handmade" 3d models and animations sculpted from scratch in software that runs on 2013 hardware, with some of the most advanced AI technology in the world. As part of my work for Google, I've used Google V2V models on a few different projects now - Ancestra, Dear Upstairs Neighbors and most recently one of the IO films (I'll share more about that project soon) 🥰 - and video continues to be my favorite form of input for Generative Ai workflows. If an image says more than a thousand words, a video says more than a million. And knowing that these capabilities are now in the hands of all of you, makes me very excited to see the new workflows and projects that will come out of it. What do you think of Omni so far?

@gcduncombe Thanks Gabi!!!

@nmatares congrats on the Tools launch, it's super fun!

One of the unsung heroes of a film set is the art department - they build the visible world of a film and make thoughtful and cohesive color choices. I had a lot of fun bringing a generative art department to life by building a custom tool in @FlowbyGoogle Try it yourself! labs.google/fx/tools/flow/…

I uploaded a screenshot of Google Maps to Gemini Omni with a route drawn on it. Then I prompted it to create a first person view of someone driving a taxi cab along the route in the reference image. Pretty close to the real thing.

@laszlogaal_ @FlowbyGoogle Its really unlike anything ive tried. Less “skinning” and more “reimagining” which is whats needed to truly transform a scene.

@nmatares @FlowbyGoogle very nice! What are your experiences with the precision of the v2v edits?

When we began testing #GeminiOmni I wanted to see the accuracy of the edits. So I made a tool directly in @FlowbyGoogle. DIFF TOOL allows you to compare images/videos in realtime or export videos in sync. Try it out or remix it to make it your own. labs.google/fx/tools/flow/…

@happy_ships @sundarpichai @ammaar Just have fun with it!! For this one @ammaar and I were using our respective platforms to build demos. He was in @GoogleAIStudio and I was in @FlowbyGoogle

@nmatares @sundarpichai @ammaar What was the most unexpected insight or piece of advice you picked up from working with them on the demo?

Working with @sundarpichai and @ammaar today at #Google Demo Slam

Was super impressed at text handling here with #GeminiOmni inside @FlowbyGoogle "add a serif font at center like a title that says Flow. it appears at 00:01 and fades out at 00:05. Lets add a logo to the tennis balls in dark green that say Omni"

@iabom @fofrAI @alexanderchen The teams are looking into it!

@fofrAI @nmatares @alexanderchen Yo, did you know a lot of people are getting, "this prompt is harmful message" for everything. I know u are not a support person but I can't get anyone to respond from Google. Sorry for commenting to you.

Y'all should follow @nmatares and @alexanderchen if you want to see what Omni is capable of.

@ammaar Excited for this one!

Approved and coming to your iPhone soon :) Preorder for free now: apps.apple.com/us/app/google-…

Love pushing the boundaries of what constitutes an “edit” with #GeminiOmni. For this one I started with my original generation in @FlowbyGoogle and then edited it with the prompt. “A construction worker in a high-visibility vest and hard hat, standing on a bustling job site with scaffolding in the background. He looks slightly off-camera, wiping his brow and gesturing as he delivers the same lines in a husky voice.”

I've been testing Google's new Gemini Omni model in Google Flow. I created a scene (using my character sheet), then asked Flow to change the time of day (nighttime), the render-type (animated), and the weather (snowscape). The results are below. I think this is pretty great to be honest - the integrity 1: Original 2: Nighttime 3: 3D Render 4: Snowscape

#GeminiOmni’s object removal is pretty mindblowing. All with a simple prompt “Clean up the alley!”

@FrontierModal @FlowbyGoogle YUP! All tools you create can be shared with anyone. When shared they can use or remix themselves.

@nmatares @FlowbyGoogle Got a great project I'll be testing the sketch to image tool on this weekend, and play with the ability to modify them for more specific use cases. If I make a new tool like that, is there a way to share it?

4 subsequent edits with Gemini Omni Flash in @FlowbyGoogle. 1. “Smartphone video of (character) as she rides a bike in the suburbs. Dappled light. No dialogue. Continuous shot.” 2. “Lets add sunglasses, a helmet, and a backpack. The backpack is white canvas. The helmet is chrome. Lets change the setting to be a different neighborhood.” 3. “Make it night. Lit from only streetlights.” 4. “add a Dalmatian in a basket to the front of the bike.”

Insanely excited to announce Tools in @FlowbyGoogle. Create your own creative tools in flow for just about anything!!

@petergyang @joshwoodward He’s the absolute best!

Can I just say @joshwoodward is probably my favorite executive at Google or possibly any company. The man’s energy is infectious and I’m glad he’s in charge of Google’s new Gemini Spark personal agent. I’m honored that he read my little blog post on personal agents too 😅

Excited for everyone to play with the all new Gemini Omni Flash in @FlowbyGoogle, @GeminiApp, and @YouTube! - 10s generation - incredible world knowledge - conversational editing - support for multi-modal references - character consistency

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 🧵