Show HN: NExT-GPT – First LLM working with multimodal input and output

Posted by Anil1331 on Thursday September 21, 2023 @10:02AM
from the show-hn dept.

NExT-GPT is the first end-to-end MM-LLM that perceives input and generates output in arbitrary combinations (any-to-any) of text, image, video, and audio and beyond.

( 2 comments | 2 points | on HN )

Re:Show HN: NExT-GPT – First LLM working with multimodal inp... by jdwg on Thursday September 21, 2023 @10:12AM (#37597894)

I gave it a photo of my face, and it said that I look approachable and friendly. I asked it to improve my hair, and it replaced me with a completely different person. Oh well! Still very impressive tech.

[ Parent | on HN ]

Re:Show HN: NExT-GPT – First LLM working with multimodal inp... by Anil1331 on Thursday September 21, 2023 @10:20AM (#37598012)

Initial stages of Multi Modal AI but should get much better results soon. Believe it is going to come soon in GPT-5 and Google's Gemini

[ Parent | on HN ]