Any multimodal llm could do this in a heart beat locally.
And OpenAI has made their shit freely available to run locally, it’s like the worst company to use as an example.
Comment on Mozilla Firefox new alt-text generator powered by "fully private on-device AI model"
jherazob@beehaw.org 3 weeks ago
Now i want this standalone in a commandline binary, take an image and give me a single phrase description (gut feeling says this already exists but depending on Teh Cloudz and OpenAI, not fully local on-device for non-GPU-powered computers)
Marsupial@quokk.au 3 weeks ago
photonic_sorcerer@lemmy.dbzer0.com 3 weeks ago
Where is this freely available multimodal GPT4 you speak of?
umami_wasbi@lemmy.ml 3 weeks ago
Ollama + llava-llama3
You now just need a cli wrapper interact with the ollama api
jherazob@beehaw.org 3 weeks ago
So, it’s possible to build but no one has made it yet? Because i have negative interest in messing with that kinda tech, and would rather just “apt-get install whatever-image-describing-gizmo” so i wouldn’t be the one who does it
Swedneck@discuss.tchncs.de 3 weeks ago
this is how i feel about basically all technology nowadays, it’s all so artificially limited by capitalism.
nothing fucking progresses unless someone figures out a way to monetize it or an autistic furry decides to revolutionize things in a weekend because they were bored and inventing god was almost stimulating enough
drwho@beehaw.org 3 weeks ago
Folks have made it - I think ollama was name-checked specifically because it’s on Github and in Homebrew and in some distros’ package repositories (it’s definitely in Arch’s). I think some folks (at least) aren’t talking about it because of the general hate-on folks have for LLMs these days.
jherazob@beehaw.org 3 weeks ago
I don’t want an LLM to chat with or whatever folks do with those things, i want a command i can just install, i call the binary on a terminal window with an image of some sort as a parameter, it returns a single phrase describing the image, on a typical office machine with no significant GPU and zero internet access.
Right now i cannot do this as far as i know. Pointing me at some LLM and “Go build yourself something with that” is the direct opposite of what i stated that i desire. So, it doesn’t currently seem to exist, that’s why i stated that i wished somebody ripped it off the Firefox source and made it a standalone command.
Zworf@beehaw.org 3 weeks ago
Yes I was just writing that, I would love to see more integrations that can talk against ollama.