Comment a prompt for the Sora 2 video you want to see. If yours is interesting enough, I’ll generate and share!
MULTIMODAL AI
-
Sora 2 Generation Capabilities Impress Users
By
–
I’m absolutely cracking up from this Sora 2 gen pic.twitter.com/uYOT8J0zME
— Matt Shumer (@mattshumer_) 30 septembre 2025I’m absolutely cracking up from this Sora 2 gen
-
LandingAI Upgrades Document Extraction with DPT Technology
By
–
Announcing a significant upgrade to Agentic Document Extraction!
— Andrew Ng (@AndrewYNg) 30 septembre 2025
LandingAI's new DPT (Document Pre-trained Transformer) accurately extracts even from complex docs. For example, from large, complex tables, which is important for many finance and healthcare applications. And a… pic.twitter.com/TFkgtpQYhsAnnouncing a significant upgrade to Agentic Document Extraction! LandingAI's new DPT (Document Pre-trained Transformer) accurately extracts even from complex docs. For example, from large, complex tables, which is important for many finance and healthcare applications. And a
-
AI-Generated Images Becoming Increasingly Difficult to Distinguish
By
–
Really impressive. Some of the shots really don't look AI at all. Other shots are still obvious, but it's getting harder and harder to tell.
-
Sora 2 Access Granted: AI Video Generation Reaches New Heights
By
–
Got Sora 2 access, and yes, it’s as good as it seems Wow
-
Sora 2 vs Sora 1: One Year of Dramatic AI Video Generation Improvement
By
–
what an insane difference a year makes
— Matt Shumer (@mattshumer_) 30 septembre 2025
sora 1 (left) vs. sora 2 (right)
both using the same prompt pic.twitter.com/zUpvZX1Z94what an insane difference a year makes sora 1 (left) vs. sora 2 (right) both using the same prompt
-
AI Search Gets Visual Understanding with Lens Integration
By
–
Got the vibe but not the words? Starting today, you can simply show or tell AI Mode about what you're looking for and get rich, visual results to explore. ✨
— Google AI (@GoogleAI) 30 septembre 2025
This experience works by bringing together Search’s world-class visual understanding from Lens and Image search with… pic.twitter.com/xxbHtLDrxFGot the vibe but not the words? Starting today, you can simply show or tell AI Mode about what you're looking for and get rich, visual results to explore. This experience works by bringing together Search’s world-class visual understanding from Lens and Image search with
-
AI-Generated Images Now Indistinguishable From Real Photography
By
–
Photo AI is definitely passable as real pics for me now but I'm highly biased (and blind)
— @levelsio (@levelsio) 30 septembre 2025
Back in the Stable Diffusion days 2 years ago, I thought those pics were passable as real too (and they definitely weren't I see now) so you shouldn't listen to me ever 😂
Can you find any… https://t.co/QFSeyyyVbB pic.twitter.com/DpeihodFIIPhoto AI is definitely passable as real pics for me now but I'm highly biased (and blind) Back in the Stable Diffusion days 2 years ago, I thought those pics were passable as real too (and they definitely weren't I see now) so you shouldn't listen to me ever Can you find any
-
Hyper Realism AI: Improving Image Remix and Virtual Try-On
By
–
Some things that don't work yet with Hyper Realism:
– remix (img2img)
– try on clothes
– hold product But I'll try make them work today! -
Stitching Multiple AI Models Together Like Flux
By
–
Yes so it's mostly stitching a lot of models to work together like Flux