@GoogleDeepMind generative AI models agents | getting great tech into the hands of great creative people

Joined January 2009
658 Photos and videos
Kory Mathewson retweeted
Calling all filmmakers! Google is partnering with @XPRIZE to challenge you to shape a brighter tomorrow. Submit a 3-min trailer utilizing any production method: live-action, animation, or AI tools (like Google Flow!) winner gets $2.5M in funding to bring your full feature film to life. $1M in prizes for runners-up. Learn more and apply: futurevisionxprize.com
51
145
919
76,575
Kory Mathewson retweeted
Slow it down or speed it up with Gemini Omni. Omni understands behaviors associated with the scene without needing detailed descriptions. Simply use your starting frame and prompt for the action in your shot. For this one we prompted: “As the dog reaches the hoop, time begins to ramp down into extreme slow motion — reaching approximately 1% of real speed at the apex of the jump”
16
22
175
11,009
Kory Mathewson retweeted
I was going to charge for this, but f*** it. My team just put together a 40 page report of everything we’re seeing right now in the small biz economy. What’s inside: → Real market data on SBA lending → Business buyer demand trends → Data on the ownership succession gap → An inside look at what small businesses are doing with AI right now We’ve spent months doing hundreds of surveys and interviewing dozens of owners to put this together. Now it’s yours for free. Just: 1. Like this post 2. Comment “SMB” And I’ll send it over. (Make sure you’re following me so I can DM you.)
3,362
149
4,386
318,615
Interesting deep dive. Thanks!
May 29
For @GeminiApp, your prompt is the difference between Client V1 and Production Ready. We observed 10 designers going through a real world campaign workflow: >Hero stills >Social cuts >Secondary assets total: 29 deliverables. Only 24% were "Production Ready" And they all wrote prompts the same way. Below are the prompts and outputs 👇⬇️
2
7
2,531
less than 3 years ago people balked at the idea that they would use an ai to write their emails -- my how the times are changing. you can stop wasting hours repeating yourself. ai can handle the basics while you stay busy. I know professors, founders, influencers already using these tools by feeding their writing and data into context to create A.I. voice that answers questions from students, colleagues, fans and followers the goal is not to ditch human contact, it's to get to the deeper connections that are interrupts by the constant superficial distractions and annoyances.
2
1
5
1,482
Today is my birthday! Every year I ask friends for a contribution to my collective creativity project. This year I'm asking for two things (because I skipped last year): 1. a thing you broke and mended (ala kintsugi) 2. a word, or phrase, you carry with you (in any language) Email me a photo and a few words. More here: 🎂 korymathewson.com/baggage-of…
2
2
8
661
every flawless AI clip ships with a hidden folder of 200 cursed ones nobody will ever see
10
27
10,076
Kory Mathewson retweeted
Introducing Magenta RealTime 2, a new open model musicians can play as an instrument! Run low-latency, live music synthesis natively on your MacBook using MIDI, text, and audio. 🎶 We love seeing Google’s open model ecosystem grow!
80
336
2,884
230,674
Kory Mathewson retweeted
Introducing Flows Agent in ElevenCreative. Describe what you want to create and the agent builds your entire workflow - selecting models, creating nodes, wiring connections, and running the generations.
30
62
525
257,029
Head of Training └ Head of Fine-Tuning └ Head of Pre-Training └ Head of Post-Training └ Head of Post-Pre-Training Fine-Tuning └ the one person labeling the data
7
368
Kory Mathewson retweeted
Omni image2video is now live!!
Bring your images to life ⚡️ Upload your picture as a first frame and add a prompt to generate your own unique video with Gemini Omni Flash. Tag us and share your results!
2
9
36
4,025
Kory Mathewson retweeted
My full talk on the future of AI & media is up! I used @alexolegimas's prompt of "What will be scarce?" to propose 4 ways that media is changing, and how writers can still win in the AI age: 1) Secrets > summaries Reporting is the act of taking private knowledge and making it public: when you get a source to tell you about corporate malfeasance, or venture to a remote town that few people have been to, or sneak your way into an underground party, you are working in a space where there is no training data. 2) Live interaction > static content We’re not far from a world where AI can replicate any prose style. But readers want to know there's a real person generating the text—not just the final presentation, but the proof of work behind it. For creators, doing live events, podcasts, and meetups reveal the life behind the voice. And if I care about my ideas, I want people to know about them, no matter the format. 3) Founders > bureaucracies AI is already allowing startups to run leaner by helping founders act as their own marketer, data scientist, engineer, etc. It's the same in media — AI is a boon to jacks-of-all-trades. There’s a lot of stuff AI does that I don't want to: verifying cites, reading contracts, negotiating speaking fees. It's an amazing time for independent creatives who want to direct their own vision. 4) Personal style > polish The house style in most newsrooms is extremely LLMable. What stands out (besides reporting) is a distinct and authentic first-person voice, even if that means the occasional typo / provocation / admitting "I'm not really sure." After all, trust isn't about the perfect sentence: it’s about the track record of who says it. And the stronger your brand, the more trusted you’ll be. I spend a lot of time covering the real disruptions AI brings. But I also believe, for those with the gumption to seize the opportunity, there's never been a better time to be a writer 🧡
How AI will change media: “The value of polish is going to go down and the value of personal charisma, style, and weirdness is going to go up,” says @jasminewsun
16
32
237
55,239
Kory Mathewson retweeted
as always, i'm way too busy to properly promote my course but after a 2 month hiatus i'm bringing The AI Creative Director back in July! 100 people in the alumni network, new stress-tested curriculum, updated models like k2 and GPT Image2 and lots, lots more video the price is raised, but in honor of being in the top 100 of @MavenHQ experts theres an automatic 25% off discount which brings it down to (almost) the price of previous cohorts! 🔗 to enroll below
9
7
118
16,684
Kory Mathewson retweeted
We just shipped the ability to build apps that connect to Gmail, Drive, Sheets, and more directly inside of @GoogleAIStudio, no navigating to other sites, you can add testers right inside of AI Studio, with full public sharing coming soon!!
87
84
1,235
99,860
So excited to see this out into the world, these are amazing creative tools used by incredibly creative people. Shout out to the whole team.
We wanted to see if we could take simple, physical materials (like cardboard and markers) and use AI to bring them to life. What was the result? A short film starring a bunch of TPUs getting ready for the big stage at Google I/O 2026! Working with director Laurie Rowan and Nexus Studios, we kept human artistry at the center of the film by blending puppetry and 3D animation with our models to do the following ↓ Nano Banana: Generated beautifully stylized first frames from the raw puppet footage and basic 3D animations. @GoogleAIStudio: Built a custom tool inside the platform to test these frames at scale, ensuring pixel-perfect consistency Gemini Omni & experimental @GoogleDeepMind Models: Merged the base animation and stylized frames to elevate the final piece to a cinematic level. Our AI pipelines were specifically designed to protect the crafty details that give these films their heart, like the tiny human imperfections of puppetry, or the nuance an animator can build into an expression.
4
619
Kory Mathewson retweeted
Introducing Dubbing v2, our revolutionary new dubbing model. For the first time, the emotion and performance of the original content is carried over into every language.
79
191
1,845
522,539
hey hive mind. know anyone great at making interactive characters with generative ai? plz tag them -- id love to chat.
1
3
347
Kory Mathewson retweeted
Lately everyone’s been talking about AI agents, so we got curious and asked our community to share their best “agentic” creative workflows. We picked 3 to test through @LumaLabsAI, @runwayml and @UtopaiStudios and the big takeaway from all these tests is that agentic creative workflows still don’t seem that impressive in their current form. So here’s our next challenge: We’ll give $200 to anyone in the comments who can share an ACTUAL agentic creative AI workflow that’s genuinely better than just prompting manually yourself.
14
6
48
9,369
Kory Mathewson retweeted
Gemini Omni slightly adjusted scene lengths to better match the translation. I've never seen anything like this before 🤯
New day now Omni findings: it can translate audio (no original or translated text given in the prompt): - it keeps the background music intact - it adjusts the edit if needed. For example the japanese and spanish sentence during the creme close-up shot is longer, so it kept that shot longer and trims that edit point…
1
10
102
12,435