Researchers at @EPCCed are using the CS-3 for cutting-edge AI workloads at unprecedented speeds — from long-context modeling to multi-modal research.
MULTIMODAL AI
-
Open-Source AI Tool Generates Video Locally on 6GB GPU
By
–
Une IA open-source permet de générer des vidéos localement, gratuitement, sans cloud ni abonnement.
— VISION IA (@vision_ia) 2 mai 2025
Elle tourne sur une simple carte graphique 6GB.
FramePak (développé par des chercheurs de l'université de Stanford) pourrait faire pour la vidéo ce que Stable Diffusion a fait… pic.twitter.com/FtbdHDxJ44Une IA open-source permet de générer des vidéos localement, gratuitement, sans cloud ni abonnement. Elle tourne sur une simple carte graphique 6GB. FramePak (développé par des chercheurs de l'université de Stanford) pourrait faire pour la vidéo ce que Stable Diffusion a fait
-
CodeLLM Generates Code from Mockups and Screenshots
By
–
With CodeLLM, you can upload mock-ups and screenshots and generate code.
-
Kling 2.0 Advanced Video Model Launches on Poe Platform
By
–
New on Poe: Kling 2.0!
— Poe (@poe_platform) 2 mai 2025
This advanced video model sets new standards for motion quality and image-to-video capabilities. It excels at transforming images you create on Poe, including those generated with GPT-4o, into high-quality videos. (1/2) pic.twitter.com/Thk8zEr3XoNew on Poe: Kling 2.0! This advanced video model sets new standards for motion quality and image-to-video capabilities. It excels at transforming images you create on Poe, including those generated with GPT-4o, into high-quality videos. (1/2)
-
Kling 2.0 AI Video Generation Model Now Available
By
–
Kling 2.0 is hosted by @FAL and is available at https://
poe.com/Kling-2.0-Mast
er
… and on all platforms. (2/2) -
Real-time Music Video Creation with Gen-4 References Livestream
By
–
Join us here at 1:30 pm EST as @iamneubert and @notiansans livestream the real-time making of a music video using Gen-4 References. https://
x.com/i/broadcasts/1
BdGYqgDlaBGX
… -
GPT Presets: AI-Powered Image Generation and Creative Tools
By
–
introducing GPT Presets.
— KREA AI (@krea_ai) 2 mai 2025
turn yourself into an action figure, create realistic 3D logos, or even combine images into comic strips!
available now in Krea Image with ChatGPT model. pic.twitter.com/80IjLdQnUwintroducing GPT Presets. turn yourself into an action figure, create realistic 3D logos, or even combine images into comic strips! available now in Krea Image with ChatGPT model.
-
Perplexity AI Now Available on WhatsApp for Instant Fact-Checking
By
–
Perplexity is back up and running on WhatsApp again: : +1 (833) 436-3285 Have fun forwarding messages to it for fact checks, or directly chatting for answers and free form text conversations and creating images.
-
Niji images integration in oref v7 AI tool
By
–
probably not! but try putting a niji image into oref in v7 and it might work very well!
-
AI Model Dataset Expansion for Image Generation Tasks
By
–
We got slightly better results when doing something simple like "a perfume bottle in a forest" with a square aspect ratio, but actually it looks like our dataset doesn't have much in the way of data like this right now. We'll send it to our researchers as a good example for