Tom Hume
@twhume
Sand into beauty. Product Lead, Generative Media @ Google DeepMind. Snagged on frowns and slowly dawns. SFO in the streets, BN2 in the sheets
The wait is over. @GeminiApp is now shipping Veo 3 *globally* for all Pro members! That means India, Indonesia, all of Europe, and more are starting to get access to create videos right now. As a member, you'll get 3 video generations per day, and that credit will replenish…
You’re going to see this flood of new stories that have never been heard before, from countries that no one would ever invest (in)” cnn.com/world/africa/a…
I found another fun Veo 3 prompt: "Realistic footage of the moon landing, but it took place in [year]" Here is 1883 AD, 1255 AD, 44 AD, 2300 BC, 30,000 BC, and 65 million years ago Yes, there is apparently wind on the moon back then, you are just going to have suspend disbelief
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…
Want to be part of a team redefining SOTA for generative video models? Excited about building models that can reach billions of users? The Veo team is hiring! We are looking for amazing researchers and engineers, in North America and Europe. Details below:
The wetransfer AI data panic, like the Dropbox AI data panic, makes no sense other than as a device to sow panic Why would profitable trusted storage businesses make file sharing stealthily insecure I really don’t think it is a good idea to sow panic
Veo3 is now usable in the Gemini API. Get your videos (with audio) in a few lines of python! developers.googleblog.com/en/veo-3-now-a…
Badger badger badger
The capability that enabled us to make Veodyssey (veodyssey-v0.appspot.com) is the new I2V + dialogue in Veo 3. Here's the prompt we used in @GoogleLabs Flow, using a character design made with Imagen 4. ✨ We were also able to keep the voice pretty consistent via these text…
Really love this commercial, but also check out the full thread for insights into how it was made...
This may be the best AI commercial we’ve ever made. We worked with one of the best directors in the world to create a wild new ad for Kalshi (Last one hit 100M views) Here’s a breakdown of how we made it in ONE WEEK (prompt included) 👇🏼🧵
New VST/AU Plugin! 🚨 Play with Lyria RealTime directly from inside your favorite DAW with “The Infinite Crate” 🎧🎶 Like other Lyria RT demos, you can mix together text prompts and other controls to steer the model in real-time. But now with a VST plugin you can feed audio…
That dog in your photo? He's got something to say. 🐶 Turn your images into eight-second video clips with sound effects and speech in the @GeminiApp and Flow from @GoogleLabs. This feature uses Veo 3 to generate motion that reflects real world physics and includes a new…
Two Flow.google updates for you! 1. Flow is now available in 76 more countries. Full list is here: support.google.com/labs/answer/16… 2. Big improvement to generating speech using Frames to Video and "Jump to" (with Veo 3 Fast and Veo 3 Quality). We're hustling to reach more…
Since I/O in May, you've created 40M+ videos with Veo 3! Now our new photo to video feature in the @Geminiapp lets you create clips inspired by the world around you. Here’s how I imagine our resident dino Stan roams the Google campus when we’re not looking:) Ultra/Pro…
Also card carrying member of the @vishwath fan club, so donating a RT, but having had a ringside seat to some of his work at Google, I’d quibble his description of his time there as “cushy”…
I want him to apply his brilliance to AGI-related problems, but Vish is a very smart and very loveable guy so when he does a thread like this I have to retweet!
Stop saying Hollywood is cooked and we will make movies costing $200. First, credits are expensive, even if costs are heading down, I don’t think producing 90 minutes of content will ever be that cheap. Currently for a 2min video you are easily going to spend $2k in GPU/ credits.…
Show don't tell... Magenta RealTime now supports audio prompting in addition to text prompting, so you can now use clips of audio as latent anchors to steer generation. youtu.be/vHIf2UKXmp4?si…
Beautiful song and clip, uplifting and hope inspiring. Incredible work, Öner! So rewarding to see what people do with Veo 3.
An official music video created entirely with Veo 3! We collaborated with @Google to produce a music video for the queen of Turkish pop, affectionately known as the “Little Sparrow.” On the 50th anniversary of her artistic career, we crafted this video using only Veo 3 and…
Last week, we shared a refresher on our favorite Flow features. Today, we're doing a deep dive into prompting with a few tips on how to craft the optimal prompt, create your dream video, and #FindYourFlow 🕺 Clearly identify your characters or objects and describe their…