Top stories in AI today: -OpenAI co-founder raises $1B for AI safety
-The fastest AI model goes multimodal
-Turn any text into speech in seconds
-AI gets smarter by re-reading questions
-6 new AI tools & 4 new AI jobs Read more: http://
therundown.ai/p/safe-superin
telligence-1-billion
…
MULTIMODAL AI
-
OpenAI’s $1B safety fund and latest AI breakthroughs
By
–
-
Generate image morphing from one concept to another, like Mannerism to Cubism
By
–
Very cool space by @linoy_tsaban and @multimodalart : you can generate an image an make it morph from one concept to the other!
— m_ric (@AymericRoucher) 5 septembre 2024
Mine below is:
"A painting of a woman"
Mannerism ⬅️➡️ Cubism pic.twitter.com/wiq7SDLh9KVery cool space by @linoy_tsaban and @multimodalart : you can generate an image an make it morph from one concept to the other! Mine below is:
"A painting of a woman"
Mannerism Cubism -
Comparative analysis of Ideogram and Imagen 3 image generation
By
–
They are comparable. Ideogram is better with text but imagen3 is good for non realistic images
-
Loopy: Audio-Driven Portrait Avatar with Long-Term Motion Dependency
By
–
Loopy
— AK (@_akhaliq) 5 septembre 2024
Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency
paper page: https://t.co/sThcr8KfMF
With the introduction of diffusion-based video generation techniques, audio-conditioned human video generation has recently achieved significant breakthroughs in both… pic.twitter.com/XluXhvRoCbLoopy Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency paper page: https://
huggingface.co/papers/2409.02
634
… With the introduction of diffusion-based video generation techniques, audio-conditioned human video generation has recently achieved significant breakthroughs in both -
Infinite Interactive Worlds: AI Training via Diffusion Models
By
–
> create interactive world
— Yohei (@yoheinakajima) 5 septembre 2024
> train ai to play
> record video of ai playing
> train diffusion model on frames/actions
> you now haz infinite interactive world https://t.co/bBBS38J0rf> create interactive world
> train ai to play
> record video of ai playing
> train diffusion model on frames/actions
> you now haz infinite interactive world -
User gains access to Imagen3 on Gemini
By
–
Also finally got Imagen3 on Gemini! But only on my free account for now. This one is a really big upgrade. It is still rolling out gradually.
-
Discussion on Gemini Live product release status and rollout
By
–
I think it was a plan to launch it today b/c in today's announcement placeholder there were 3 items but only 1 got published (gemini live) but if it didn't go well it may get postponed
-
SEAL Leaderboard Adds GPT-4o, Gemini 1.5 Pro, Mistral Large 2
By
–
SEAL Leaderboard Update We added 3 new models to the SEAL Leaderboards: – GPT-4o-latest (gpt-4o-2024-08-06)
– Gemini 1.5 Pro (Aug 27, 2024) (gemini-1.5-pro-exp-0827)
– Mistral Large 2 (mistral-large-2407) More detailed results in thread -
AI Integration Enhances Be My Eyes Accessibility Features
By
–
1/ Be My Eyes Visual Assistance
— Jouhatsu | AI Influence Operator (@Jouhatsu_ai) 4 septembre 2024
Un outil qui met en relation des personnes malvoyantes et des bénévoles par le biais de la vidéo en direct.
L'IA améliore la correspondance, rendant le processus plus rapide et plus efficace, et permet également la description des images. pic.twitter.com/u4b31PD2Uk1/ Be My Eyes Visual Assistance Un outil qui met en relation des personnes malvoyantes et des bénévoles par le biais de la vidéo en direct. L'IA améliore la correspondance, rendant le processus plus rapide et plus efficace, et permet également la description des images.
-
Gemini update brings file and photo uploads to iOS
By
–
Gemini changelog got updated: “Go Live with Gemini” I still don’t have it on iOS and have it for a week already on Android. But on iOS there is also a new addition – now you can upload files and photos