Sometimes it’s the seemingly simplest applications of tech that can be the most repeatably powerful. Here’s a quick demo of using a simple sketch of a lighting layout to direct Google Omni Flow in relighting an in-studio video:
Looks like you can relight a scene according to a top-down lighting diagram. @FlowbyGoogle pic.twitter.com/bVV280pM7F
— László Gaál (@laszlogaal_) May 22, 2026
I love the blend old-school puppetry, 3D animation, Gemini Omni, and the latest experimental video tools that went into creating TPU Training Day, the short film that debuted during Google I/O 2026.
I know you’ve heard it a million times, but it bears repeating: AI isn’t a substitute for human creativity, or in many cases even for traditional techniques. It’s just a whole new toolbox that can multiply our expressive powers.
And here’s the film itself:
Check out this cool little technique:
This is especially wild when you consider where typography stood just a couple of years ago—for which I’ll forever be kinda nostalgic. 🙂
Nano Banana & Flux are great & all, but I legit miss when DALL•E was gakked up on mescaline. pic.twitter.com/JBxPanywoF
— John Nack (@jnack) January 14, 2026
Democratize all the apps!!
I think this new platform will be a major sleeper hit:
With Google Flow Tools, you can build creative workflows customized to fit your creative process. Explore a gallery of premade Tools built by creatives, remix existing ones to fit your needs, or create your own from scratch by just typing a description of what you want to create. You can shape and iterate on these Tools fluidly, adjusting them for individual projects, or singular clips and images. All users can explore Tools in Google Flow, and Google AI subscribers can create custom Tools from scratch or remix existing ones.
Check out the ways some artists have been spinning up tools & putting them to work:
From nailing text rendering to camera control, these tips should help you get the best possible results.
My friend Bilawal, who used to work in Google’s Geo group (Earth, Maps, and more), has created an eye-popping faux-drone video using Omni Flash:
Gave google omni a sketched camera path and asked it to generate drone POV footage. pic.twitter.com/cQZFMtOkEi
— Bilawal Sidhu (@bilawalsidhu) May 26, 2026
Here’s another exploration, inspired by Bilawal’s:
けっこうヤバかった https://t.co/Doi85TMvzf pic.twitter.com/jLX9T83ryS
— KEETY｜AIクリエイター (@KEETY2591756) May 27, 2026
The Flavawagon rides again—emotionally safely! 😀
Context: 25 years ago she helped me flame the original Flav. https://t.co/dxukPMwd3q pic.twitter.com/oLBd3t4E7T
— John Nack (@jnack) May 19, 2026
Here’s a great little one-minute explainer, featuring a couple of fun examples I hadn’t yet seen:
This is such a wild, game-changing feature:
Gemini Omni is a major leap in world understanding & multimodal editing! It can take photos, video & audio and build entirely new scenes. Over time it’ll be able to handle any input & any output – starting w/ video
You can even give it your own videos & iterate on your ideas: pic.twitter.com/VrHPJKRJXH
— Demis Hassabis (@demishassabis) May 19, 2026
I think Carlos gets it exactly right: “I think many are focusing on the wrong aspect of the Gemini Omni model when comparing it to Seedance 2.0, since conceptually they are entirely different things. This is a model for editing videos (like Nano Banana) like we’ve never had before!“
Creo que muchos están enfocando mal el modelo de Gemini Omni al compararlo con Seedance 2.0 cuando conceptualmente son cosas distintas.
Este es un modelo para editar vídeos (a la Nano Banana) como nunca antes habíamos tenido! pic.twitter.com/eaqngSnbCD
— Carlos Santana (@DotCSV) May 19, 2026
i don’t think you understand how insane omni is pic.twitter.com/wvj4B4a59B
— Sam Sheffer (@samsheffer) May 19, 2026
Editing videos is where Gemini Omni Flash really shines. It is so incredibly capable.
> Make it New Year’s Eve with fireworks. Update the clock
London launched the fireworks early. https://t.co/cTGMPbT3tZ pic.twitter.com/c3Kh1y2KO5
— fofr (@fofrAI) May 19, 2026
I need Omni fireflies in @AdobeFirefly (Yo dawg…) https://t.co/BqvcTPo905
— John Nack (@jnack) May 19, 2026
I’m so pleased to be playing a very small role in bringing breakthrough video transformation to the world. Check out the new Gemini Omni:
The team writes,
We’re introducing Gemini Omni, where Gemini’s ability to reason meets the ability to create. Omni is our new model that can create anything from any input — starting with video. With Omni, you can combine images, audio, video and text as input and generate high-quality videos grounded in Gemini’s real-world knowledge. You can also easily edit your videos through conversation.
Today, we’re rolling out the first model in the Omni family: Gemini Omni Flash, to the Gemini app, Google Flow and YouTube Shorts. In time we will support output modalities like image and audio.
Conversational video editing is the real breakthrough:
Check it out & let us know what you think!