Image created with Flux Pro v1.1 Ultra. Image prompt: Assembly instruction diagram for a vintage film projector with reel mechanism, 1950s cinema style, chrome and burgundy colors, theater technical manual background, “VIDEO” in art deco style font, film threading path illustrated, lamp housing assembly shown
Flow TV | It’s All Yarn https://labs.google/flow/tv/channel/its-all-yarn/Jj9W2h28kQruM7Vgewoe?random=true
Using Veo 3 to create fictional product reviews (unsurprisingly, it does YouTube review style very well, sound on.) https://x.com/emollick/status/1926514452754579724
Google Streetview + @runwayml References = Cinematic AI “on location”. A new process for doing “on location” AI shoots.
https://x.com/lifeofc/status/1927135049918357981
Conjuring burning man interviews out of latent space. Veo 3 is too good! https://x.com/bilawalsidhu/status/1926652175255474493
Just so everyone knows, we have passed the point where you can tell what is AI at a glance (or even, in many cases, a close look) These were all made by me with text prompts alone using Veo 3. https://x.com/emollick/status/1927117736179589631
Is it Gorgonzola?”” The natural follow-on to “”Is it cake?”” https://x.com/emollick/status/1927585857432637716
I don’t really watch any Youtube video right now without the Comet Assistant. I just ask it to take me to whatever I want to hear, and it does it by pulling the relevant time stamp and opening it on a new tab. In future, I envision just users asking the AI to consume ther web in”” / X https://x.com/AravSrinivas/status/1927130728954835289
🚀 Introducing HunyuanVideo-Avatar, a model jointly developed by Tencent Hunyuan and Tencent Music, bringing photos to life. ✅ Upload a photo + audio — auto-detect scene context & emotion, then generate lifelike speech/singing with dynamic visuals. ✅ Supports multi-style, https://x.com/TencentHunyuan/status/1927575170710974560
zeenolife/ai-baby-monitor: Local Video-LLM powered AI Baby Monitor https://github.com/zeenolife/ai-baby-monitor
🚨 Flow, our AI filmmaking tool, is now available in 71 more countries 🌍 through the Google AI Pro and Ultra subscriptions. Also, Veo 3 is now available for Pro subscribers to try (create your videos with sound!), and we’ve increased capacity even more for Ultra subscribers. ✨ https://x.com/GoogleLabs/status/1926315147607310376
I’ve been reading Bethany Hughes book on the 7 Wonders & the myths of the Colossus of Rhodes (eg it did not span the harbor) As an experiment, I asked Google Deep Research to come make a prompt to describe the historical Colossus for veo 3. Nice, down to the location & riveting https://x.com/emollick/status/1926896178651701654
google is all over hugging face today! ❤️ https://x.com/reach_vb/status/1926558763760177396
🚨 Just launched: an AI-powered YouTube Shorts machine 🎯 Fully automated → Generates riddles, turns them into videos, uploads to YouTube. No editing. No scripting. Just results. Built with n8n + AI + Creatomate 🔥 Watch it work below 👇 #n8n #NoCode #AI #YouTubeAutomation https://x.com/juppfy/status/1919818122233561164
While Luma and Odyssey may have pivoted to video, World Labs, Niantic and now SpAItial continue to push on a 3D-first approach.”” / X https://x.com/bilawalsidhu/status/1927372170419695898
HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation
https://kkakkkka.github.io/HunyuanPortrait/
I don’t take any money from any of the AI companies, but that doesn’t mean I can’t enjoy the fact that I am getting direct responses on bug reports from the CEO of Google. https://x.com/emollick/status/1925410747498029332
LoRAvatar https://starc52.github.io/publications/2025-05-28-LoRAvatar/
ChatHuman https://chathuman.github.io/
DreamDance https://kebii.github.io/DreamDance/
Damn. And it just keeps going ! Veo, Runway and After Effects are my holy trinity. Now it’s time to put Flow to work. https://x.com/bilawalsidhu/status/1925375536983154858
I didn’t have street interviews being replaced by AI on my bingo card for 2025″” / X https://x.com/bilawalsidhu/status/1926304237945852138
Introducing AI video you can watch and interact with, in real-time! Powering this is a new world model that imagines and streams video frames every 40ms(!). No game engine in sight. We call it interactive video, and it’s free for anyone to try right now (GPUs permitting)! https://x.com/odysseyml/status/1927767196756853179
Street view + character reference with Runway and Veo 3 is a powerful combo to tell stories in the real world https://x.com/bilawalsidhu/status/1927162778357252281
veo 3, make something incredibly meme worthy, just the most viral thing that people will send to each other.”” https://x.com/emollick/status/1926175860685463617
This real-time, interactive AI video by Odyssey feels like navigating a VHS recording of a dream — if you squint, you can see the holodeck is closer than we thought. If you want to make some H100’s purr and stream video up to 30 fps, check out the demo and channel surf some https://x.com/bilawalsidhu/status/1927811913339081141
