You can give Omni a reference video and a lighting diagram and it'll relight your shot for you. https://t.co/CxDMDUQi8j
— fofr (@fofrAI) 22 mai 2026
You can give Omni a reference video and a lighting diagram and it'll relight your shot for you.
MULTIMODAL AI
-
Omni AI Tool Relights Video Shots Automatically
By
–
-
Gemini 3.5 Flash Outperforms 3.1 Pro in Vision Use Cases
By
–
Gemini 3.5 Flash outperforms 3.1 Pro on many vision use cases (like the below Roboflow eval) while being ~6x faster on average Gemini multimodal understanding for the win.
-
Gemini Omni enables native multimodal video editing
By
–
I think people don't realize why Gemini Omni is different than other video AIs. It is fully multimodal, so it can edit video natively, too
— Ethan Mollick (@emollick) 22 mai 2026
I took the famous "train " movie from 1896 & made it a bullet train, LEGO, added a time traveler, a centipede, muppets… (see reflections?) pic.twitter.com/WxSO5h9x1ZI think people don't realize why Gemini Omni is different than other video AIs. It is fully multimodal, so it can edit video natively, too I took the famous "train " movie from 1896 & made it a bullet train, LEGO, added a time traveler, a centipede, muppets… (see reflections?)
-
Zalando integrates AI 3D scanning platform for product production
By
–
Zalando is scaling high-fidelity 3D product production to drive confident customer decisions. By integrating ALLSIDES’ AI‑powered photometric 3D scanning platform, powered by NVIDIA Cosmos™, Gen‑3C, and DiffusionRenderer, they’ve created a "Scan to Storefront in 48 Hours"
-
AI + 3D renders for Times Square and NASDAQ displays
By
–
Your AI render could literally end up in Times Square Not a gallery.
Not a Discord channel.
The NASDAQ screen. 6 seconds is all you get. If you’re building with AI + 3D and still need a reason to lock in… This is it. -
Realistic Trollface Meme Generated with Google Veo 3
By
–
I made the realistic trollface meme with Google Veo 3 and Nanobanan Pro in late November for fun. In the last week it picked up over 500.000.000 views combined on TikTok amongst the late Gen-z generation. “told teach to check email”
-
YouTube launches conversational AI video search experiment
By
–
9/ Ask YouTube — conversational video search
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 22 mai 2026
Ask complex questions → get structured answers from across YouTube's entire catalog (Shorts + long-form)
Rolling out this month on desktop (US, English) as an experiment 🎥 pic.twitter.com/hWaUpxWtco9/ Ask YouTube — conversational video search Ask complex questions → get structured answers from across YouTube's entire catalog (Shorts + long-form) Rolling out this month on desktop (US, English) as an experiment
-
Google Search undergoes major AI-driven transformation
By
–
6/ Google Search got its biggest upgrade in 30 years
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 22 mai 2026
🤖 AI-powered box that generates answers, images + short videos
🎨 Generative UI that adapts layouts based on your intent
📡 More assistant, less search engine
This is not a tweak. This is a rebuild. pic.twitter.com/87Iel7OJwO6/ Google Search got its biggest upgrade in 30 years AI-powered box that generates answers, images + short videos Generative UI that adapts layouts based on your intent More assistant, less search engine This is not a tweak. This is a rebuild.
-
Google Releases Gemini 3.5 Flash Model
By
–
1/ Gemini 3.5 Flash is live NOW
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 22 mai 2026
▫️ 4x faster than competing frontier models
▫️ Beats Gemini 3.1 Pro on coding, agentic + multimodal benchmarks
▫️ Available in the Gemini app, Search, Antigravity 2.0 + Gemini API
The "fast AND smart" model finally exists. pic.twitter.com/TctzckYTzu1/ Gemini 3.5 Flash is live NOW 4x faster than competing frontier models Beats Gemini 3.1 Pro on coding, agentic + multimodal benchmarks Available in the Gemini app, Search, Antigravity 2.0 + Gemini API The "fast AND smart" model finally exists.
-
SenseNova U1 positioned for dense visual communication
By
–
Infographics are where weak models get exposed. Tiny labels break.
Layouts collapse.
Text turns into alien noodles.
The message gets lost. SenseNova U1 is built for dense visual communication: posters, PPTs, knowledge maps, comics, diagrams, explainers.