LocalLLaMA

3 readers

1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago

MODERATORS

communick@poweruser.forum

Video-LLaVA can describe both image and video input. (github.com)

submitted 11 months ago by chibop1@alien.top to c/localllama@poweruser.forum

6 comments fedilink hide all child comments

top 6 comments

sorted by: hot top controversial new old

[–] Ok-Recognition-3177@alien.top 1 points 11 months ago

I wonder if this could be used to identify security cam events and notify me

[–] paryska99@alien.top 1 points 11 months ago

Yes! I've been waiting for progress in video for a while! Imagine dyi automated classification for the sake of compilations and edits. This is going to be sick! Can't wait and see an implementation on llamacpp

[–] fallingdowndizzyvr@alien.top 1 points 11 months ago

This is awesome. I've been processing individual frames of video at a time.

[–] secunder73@alien.top 1 points 11 months ago

If only we could use custom LLM models to write descriptions

[–] toothpastespiders@alien.top 1 points 11 months ago

Holy shit. I've been holding off on looking too deeply into LLaVA given how many things are always popping up. But that's just too cool to pass up on. The amount of potential applications, if it works as well as I'm hoping, is wild.

[–] fetballe@alien.top 1 points 11 months ago

Amazing!
Does it work with .ggml or quantized 4-bit gptq?