Multi Modality

[aamir-gmail]

I see there i support for image2text in the supported model in ollama , I would resume they relate to llava:13b . I tried using them however the image I uploaded in the chat ended up in the knowledge base. My question is whether there is support for using Multi-modal models like llava 7 or 13 b

[KevinHuSh]

It supports image to text, but it does not support text to image.

[aamir-gmail]

when you say " It supports image to text", you mean multimodal models like LLava https://llava-vl.github.io/

…

On Mon, Sep 16, 2024 at 6:22 PM Kevin Hu ***@***.***> wrote: It supports image to text, but it does not support text to image. — Reply to this email directly, view it on GitHub <#2453 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AJA2ECPGGASMCNVEURD6ZYTZW2IMRAVCNFSM6AAAAABOIUOIJSVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTANRVGY3TEMY> . You are receiving this because you authored the thread.Message ID: ***@***.***>

-- Kind Regards Aamir Mirza

[KevinHuSh]

Yes.