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

ShareGPT4V - New multi-modal model, improves on LLaVA (sharegpt4v.github.io)

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

17 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] yahma@alien.top 1 points 11 months ago (1 children)

Would love to use this for handling remote security camera footage.

Tried with LLAVA with little success. Has anyone successfully applied any of the Open Vision models to the problem of security?

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

I just think you have to set proper expectations. I use llava with my security cameras and it does what I want. Which is to know when something interesting is happening like when it sees someone. Llava gave me this from one of my security cameras earlier this morning.

The image features a person walking on a street, captured through a fisheye lens, which distorts the perspective of the scene. The person appears to be carrying a bag, possibly a backpack, while walking down the sidewalk.

Which IMO is very useful.