MULTIMODAL AI

→ View original post on X — @ludosln

ChatGPT Vision: everything you can do

By

@ludosln

–

12 October 2023 16h56

That's it! My #ChatGPT has eyes and it's just INCREDIBLE! In this video, I present to you ChatGPT Vision and everything you can do —> https://youtu.be/Ao0EhzoX8kU #GPT4 #ChatGPTV #ChatGPTPlus

→ View original post on X — @runwayml

Runway ML Studios Premieres AI-Generated Film From Tweet

By

@runwayml

–

12 October 2023 15h16

Last week we asked you to help us generate a film with a Tweet. Today, @runwaymlstudios is excited to premiere, "Don't Pick Up." Thank you to all our collaborators. pic.twitter.com/qUj5JIeWBW
— Runway (@runwayml) 12 octobre 2023

Last week we asked you to help us generate a film with a Tweet. Today, @runwaymlstudios is excited to premiere, "Don't Pick Up." Thank you to all our collaborators.

→ View original post on X — @miketamir

Multimodal Evolution of Vector Embeddings in AI

By

@miketamir

–

12 October 2023 3h01

The Multimodal Evolution of Vector Embeddings https://
bit.ly/3PIx1AJ
#AI #MachineLearning #DeepLearning #LLMs #DataScience

→ View original post on X — @jeremyphoward

Legal implications of curated image datasets in AI training

By

@jeremyphoward

–

11 October 2023 23h23

And how about the "aesthetic" subsets? Are they likely to be treated differently because they're curated? (And they would have required accessing the image itself to do that curation.)

Coqui XTTS: Open Source Text-to-Speech with Voice Cloning

By

–

11 October 2023 18h50

18 – CoquiTTS (
@coqui_ai
) – @_josh_meyer_ and the Coqui team presented XTTS: A fully open source text to speech and voice generation model competitive with the commercial offerings, including instant-voice cloning http://
hf.co/spaces/coqui/X
TTS
…

HelloHola: AI Speech Translation with Lip Sync

By

–

11 October 2023 18h50

15 – HelloHola presented by @gary_Offbeat
, it translates speech into a chosen language, maintaining your style and synchronizing lip movements, check them out @

DINOv2: State-of-the-art open source self-supervised vision transformer

By

–

11 October 2023 18h50

9 – DINOv2 – presented by @TimDarcet
, DinoV2 is state of the art open source self supervised vision transformer model https://
dinov2.metademolab.com

YOLO SAM Combines Meta’s Segment Anything with Medical Imaging

By

–

11 October 2023 18h50

5 – Sumit Pandey showcased YOLO SAM, a pipeline that combined Segment Anything from @Meta with Medical Image Segmentation for X-Rays, CT Scans and Ultrasounds https://
mlshots.live/YOLO-SAM/softw
are
…