Kory Mathewson
@korymath
@GoogleDeepMind working on Veo + Flow -- getting great generative AI into the hands of great creative people
I am proud to be working with @primordialsoup_, a storytelling venture by @DarrenAronofsky, and @Eliza_McNitt The team at @GoogleDeepMind are getting our newest generative models into the hands of top filmmakers to push the boundaries of creative and emotional storytelling.
We’re teaming up with @PrimordialSoup_, a new venture by visionary director @DarrenAronofsky, to redefine AI’s role in filmmaking and put artists in control of technological innovation. The first film explores how emotional live-action performance integrates with Veo-generated…
New video on the details of diffusion models: youtu.be/iv-5mZ_9CPY Produced by @welchlabs, this is the first in a small series of 3b1b this summer. I enjoyed providing editorial feedback throughout the last several months, and couldn't be happier with the result.
Google just discovered a powerful emergent capability in Veo 3 - visually annotate your instructions on the start frame, and Veo just does it for you! Instead of iterating endlessly on the perfect prompt, defining complex spatial relationships in words, you can just draw it out…
Can confirm. This is an absolutely magical interaction mode. I’m so excited what people are able to do with this new trick. Also continually impressed with how creative people push these models beyond their capabilities with creativity and ingenuity.
We just discovered the 🔥 COOLEST 🔥 trick in Flow that we have to share: Instead of wordsmithing the perfect prompt, you can just... draw it. Take the image of your scene, doodle what you'd like on it (through any editing app), and then briefly describe what needs to happen…
Martin is always pushing these models WAY past their previously understood functionality frontier...
Veo 3 + a screenshot from my Webcam? With some creative prompting, Veo can do some very surprising things out of the box. Earlier, we looked at "Instantly jump/cut on frame 1" prompts that lets you upload a single start frame and then "trick" Veo to do a near-instant scene…
Interested to work together on generative AI models closing the gap between imagination and reality? We are hiring on the Veo team!📽️ Product Manager (US) job-boards.greenhouse.io/deepmind/jobs/… Research Engineering and Scientist Europe (London, Zurich) job-boards.greenhouse.io/deepmind/jobs/… (US)…
wait, i legit slept on google’s AI suite. gemini writes, flow films, notebooklm researches, stitch designs, project mariner automates. i filmed a 38-minute tutorial with google’s VP of gemini and it just rewired my whole workflow.
Just figured out another pretty useful way to leverage @MartinNebelong's "instant jump or cut on frame 1" trick in @GoogleDeepMind's VEO (2 and 3) image-to-video: Simply write "instant jump or cut on frame 1. A character sheet of the (describe character here) against a white…
I wrote a blog post on the best models to use for generating consistent characters from a single reference image: replicate.com/blog/generate-…
Here's a Replicate model to help you compare character consistency with kontext, seededit and runway models. replicate.com/fofr/compare-c… Below: "put him underwater in diving gear"
An advanced version of Gemini with Deep Think has officially achieved gold medal-level performance at the International Mathematical Olympiad. 🥇 It solved 5️⃣ out of 6️⃣ exceptionally difficult problems, involving algebra, combinatorics, geometry and number theory. Here’s how 🧵
If you haven't watched Cop Files Part IV & V, I definitely suggest doing that first! Written, directed, edited, performed, and sound designed by me. Tools used: Runway Act Two Elevenlabs LTX Studio Flux Veo 3 Kling Sora Udio Photoshop Premiere
New Essay by @BlaiseAguera (@Google): “AI Is Evolving — And Changing Our Understanding Of Intelligence” Advances in AI are making us reconsider what intelligence is and giving us clues to unlocking AI’s full potential. noemamag.com/ai-is-evolving…
Veo 3 room explosions 🤯 Turns out this works for making themed rooms starring brands and characters! I spent several hours and tons of credits optimizing this prompt so you don't have to 👇
The costumes. The sets. The acting. 👌 kirby, portal, mario, pacman, sonic, minecraft
"[video game] as a community theater production" may be one of the most delightful Veo 3 Fast prompts Please enjoy, in order: GTA, Pokemon, Mario Kart, The Witcher 3, Stardew Valley, Tetris, Mortal Kombat, The Sims, & Death Stranding(!) Yes, the whole prompt was the one above.
We made a 25-minute FULLY AI TV show in 3 months, and I’m sharing all our secrets for free 👀 See EXACTLY how we brought Jonah’s story to life. Here's how to create a full TV show in 15 easy steps. Copy my PROMPTS and process below 👇🏼🧵
Check out the article about us on the @nytimes 💯👀 Some of the information shared there is being revealed for the very first time. nytimes.com/2025/07/18/tec…
The floodgates have opened on AI in the creative industry. This is a strong pro-AI statement from Netflix CEO Ted Sarandos on an earnings call. Netflix is using AI-generated and edited video in TV shows and movies they produce. And the results are better, faster, and cheaper.
Veo 3 is now live in the Gemini API 📽️!! Veo 3 is state of the art, can natively generative audio in the videos, comes with rate limits for scaled production use, and is priced at $0.75 per second w/ audio and $0.50 w/o audio. More in 🧵
whoa. this is pretty great. Congrats to the team at @runwayml
Introducing Act-Two, our next-generation motion capture model with major improvements in generation quality and support for head, face, body and hand tracking. Act-Two only requires a driving performance video and reference character. Available now to all our Enterprise…
hey... this is pretty cool.
introducing OpenArt Story — turn any idea, script, beat, or character into a stunning 1-min video, complete with motion, music, and a narrative arc not just a clip - it's a full story edit if you want, or post as-is powered by amazing tech from @bfl_ml , @Kling_ai @Hailuo_AI…