NEW: Qwen 235B A22B Vision Language Model is OUTT! Apache 2.0 licensed and upto 1 Million context length
MULTIMODAL AI
-
ChatGPT Launches Multimodal Video Feature for Voice Questions
By
–
New ChatGPT multimodal video feature incoming "Now you can capture videos and ask your questions out loud for faster answer"
-
MagicPath transforms design images into code in real-time
By
–
One of my favorite things about MagicPath is watching it recreate designs from images.
— Pietro Schirano (@skirano) 23 septembre 2025
The UI streams in real-time, building piece by piece like watching a designer at work.
Image to code in under a minute.
We live in an age of wonder. pic.twitter.com/J1TTuVzaT4One of my favorite things about MagicPath is watching it recreate designs from images. The UI streams in real-time, building piece by piece like watching a designer at work. Image to code in under a minute. We live in an age of wonder.
-
Qwen Image Edit Plus Now Available on Replicate Platform
By
–
Qwen Image Edit Plus is now on Replicate https://
replicate.com/qwen/qwen-imag
e-edit-plus
… Edit images in just 6 seconds We've worked with @PrunaAI again to deliver you the fastest speeds possible -
Copilot Mode Expands Multi-Tab Reasoning and Voice Navigation
By
–
In July, Copilot Mode rolled out multi-tab reasoning and voice navigation – now on their way to becoming ubiquitous, a new bar for all browsers.
-
Gemini Live API Native Audio for Voice AI Agents
By
–
Building voice AI Agents has never been easier. New updates to Gemini Live API with Native Audio lets you build AI Agents that understand emotion, ignore background noise, use tools like RAG, MCP & search.
-
Kling 2.5 Video Generation AI Tool Launches with Enhanced Features
By
–
🚨Kling 2.5 is here!
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 23 septembre 2025
Smoother motion, sharper visuals, and spot-on style control (anime to photoreal).
Even nails micro-expressions and abstract scenes.
Create cinematic clips straight from text or images. Faster, cost-effective, and ready to revolutionize video creation.
👉… pic.twitter.com/WZHU9m2X8lKling 2.5 is here!
Smoother motion, sharper visuals, and spot-on style control (anime to photoreal). Even nails micro-expressions and abstract scenes. Create cinematic clips straight from text or images. Faster, cost-effective, and ready to revolutionize video creation. -
MetaEmbed: Scaling Multimodal Retrieval with Flexible Late Interaction
By
–
MetaEmbed Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction
-
VideoFrom3D: 3D Scene Video Generation with Diffusion Models
By
–
VideoFrom3D
— AK (@_akhaliq) 23 septembre 2025
3D Scene Video Generation via Complementary Image and Video Diffusion Models pic.twitter.com/zwVJRtf1g1From3D 3D Scene Generation via Complementary Image and Diffusion Models