We've now released pan / zoom / vary (region) on V6
MULTIMODAL AI
-
SDXL Fine-tune Creates Watercolors from Cassini Saturn Images
By
–
I've made an SDXL fine-tune based on the beautiful Cassini spacecraft images of Saturn. It doesn't fix how SDXL generates Saturn, but it was able to make some nice watercolours.
-
AI as Personal Fashion Guru: Innovation in Style
By
–
AI Wednesday: How AI Could Become Your Personal Fashion Guru https://
linkedin.com/pulse/ai-wedne
sday-how-could-become-your-personal-fashion-guru-babin-9ibde
…
#ArtificialIntelligence #fashion #data #innovation #technology @enilev @PawlowskiMario @MargaretSiegien @SpirosMargaris @Fabriziobustama @Shi4Tech @smaksked @jblefevre60 @kalydeoo @3itcom -
Google Lumiere: Integrated Generative AI Platform for Multimodal Content
By
–
Lumiere from Google. Wow. Imagine what happens in the generative AI space when Google productizes all the pieces (text, images, video, audio, coding, reasoning, etc) in an elegant way. https://
lumiere-video.github.io -
WHO Releases Guidance on Ethics and Governance of Large Multimodal Models
By
–
WHO is releasing new guidance on the ethics and governance of large multi-modal models(LMMs). #AI #GenerativeAI #Data #ML #health #LMMs #ethics #AIgovernance #technews #tech #healthcare https://
bit.ly/3u45mCq -
AI Animation Breakthrough: Outstanding Generative Video Application
By
–
I love this AI animation so much… One of the best uses I've seen of generative video yet. https://t.co/Fw7a7vTCeF
— Matt Wolfe (@mreflow) 24 janvier 2024I love this AI animation so much… One of the best uses I've seen of generative video yet.
-
Fully Generated Videos: The Next Frontier in AI Content Creation
By
–
Full videos with stock footage can already be done pretty easily with tools like @invideoOfficial – I'm talking about fully generated videos.
-
Moondream1 Vision Model Outperforms Larger Models Locally
By
–
This vision model, Moondream1 is so good that I had to make a @streamlit app for it.
— Pietro Schirano (@skirano) 23 janvier 2024
Despite being just 1.6B parameters, it outperforms much larger models I've tested.
And it runs completely locally and free on your CPU.
Video is at real speed.
Link to the repo 👇 https://t.co/v1gxvwSp4R pic.twitter.com/PPqiOgdCXNThis vision model, Moondream1 is so good that I had to make a @streamlit app for it. Despite being just 1.6B parameters, it outperforms much larger models I've tested. And it runs completely locally and free on your CPU. is at real speed. Link to the repo