Opening ceremony best on Groq prize track announcement Turbocharge your Multimodal and Agentic Apps with Groq Workshop Increased rate limits for dozens of hackers (and counting) Fully stocked swag table Can't wait to see what's built on Groq at uOttaHack!
MULTIMODAL AI
-
Smart Glasses for Deaf People Deliver Real-Time Subtitles
By
–
Awesome smart glasses for deaf people…
— Amitav Bhattacharjee (@bamitav) 18 janvier 2025
It captures real-time subtitles!
pic.twitter.com/TbTpAMPaak#smartglasses #Deaf #subtitles #AR #VR #MR #XR #technology #TechRevolution #tech #Engineering @SpirosMargaris @DataDiva @CloudMaster99 @AI_Whiz @CyberSecPro @DigitalNomad…Awesome smart glasses for deaf people…
It captures real-time subtitles! #smartglasses #Deaf #subtitles #AR #VR #MR #XR #technology #TechRevolution #tech #Engineering @SpirosMargaris @DataDiva @CloudMaster99 @AI_Whiz @CyberSecPro @DigitalNomad -
AI-Generated Content Becomes Indistinguishable From Human Work
By
–
will also be a very good exercise while watching the video for you is to spot where the AI stuff starts and where it ends. I really don’t think most people will be able to tell.
-
VR Canvas and Generative AI for Interactive Worlds
By
–
VR gives us the canvas and generative AI is the means to populate it – def close for static or lightly interactive worlds but full-blown interactivity still seems further out
-
Runway adds Frames for text-to-image generation
By
–
Runway announced Frames, a new text-to-image model within their core toolset 👀
— 🚨 AI News | TestingCatalog (@testingcatalog) 17 janvier 2025
It is quite natural for AI video tools to have image-gen right next to video-gen. Creator tooling will never be the same 👀 https://t.co/BkU1FfqnOH pic.twitter.com/NFwh9K4wgMRunway announced Frames, a new text-to-image model within their core toolset It is quite natural for AI video tools to have image-gen right next to video-gen. Creator tooling will never be the same
-
Frames: Advanced Image Generation Model with Unprecedented Stylistic Control
By
–
Today we are releasing Frames. Our most advanced base model for image generation, offering unprecedented stylistic control and visual fidelity. Learn more below.
— Runway (@runwayml) 17 janvier 2025
(1/10) pic.twitter.com/3E8Y9l5ODIToday we are releasing Frames. Our most advanced base model for image generation, offering unprecedented stylistic control and visual fidelity. Learn more below. (1/10)
-
Combining Krea Train Flux and RT for 3D Skeleton Systems
By
–
yea! oh great point—i guess u can combine Krea Train with Flux and then onto RT with 3D and play around… so cool! You can pose on Flux while we build some sort of skeleton system… sick!
-
PopAI: AI Suite Generates Documents, Videos, Images from Text
By
–
AI productivity suite @popaiinone can create not only documents, speeches, and powerpoints, but can create video and images from text now. https://
popai.pro/ai-image https://
popai.pro/ai-video #AITools #aivideo #aiimage -
StarGen: Spatiotemporal Video Generation Framework for Scene Synthesis
By
–
StarGen: A Spatiotemporal Autoregression Framework with Diffusion Model for Scalable and Controllable Scene Generation https://
arxiv.org/pdf/2501.05763 https://
zju3dv.github.io/StarGen/ -
ZeroBAS: Neural Method Synthesizes Binaural Audio from Mono
By
–
Today we introduce ZeroBAS, a neural method to synthesize binaural audio from mono audio recordings paired with positional information, without training on any binaural data. Learn how it’s done at https://
goo.gle/4hcAq5Q