[GH-ISSUE #1109] Exploring Multimodal LLMs: Incorporating Image as Input in ModelFile. #555

Closed
opened 2026-04-12 10:15:03 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @saifullah-N on GitHub (Nov 13, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1109

Hi, I'd like to experiment with multimodal language models that can handle both images and text as input. Is there a way to input an image.

My ModelFile looks like this

FROM ./my_model.gguf
PARAMERTER..
SYSTEM You are An Artist describe the image

I'm trying to run this on macos.
M1 chip

Originally created by @saifullah-N on GitHub (Nov 13, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1109 Hi, I'd like to experiment with multimodal language models that can handle both images and text as input. Is there a way to input an image. My ModelFile looks like this ``` FROM ./my_model.gguf PARAMERTER.. SYSTEM You are An Artist describe the image ``` I'm trying to run this on macos. M1 chip
Author
Owner

@jmorganca commented on GitHub (Nov 13, 2023):

Hi there! Thanks for creating an issue. I'll merge it with https://github.com/jmorganca/ollama/issues/746

<!-- gh-comment-id:1808663856 --> @jmorganca commented on GitHub (Nov 13, 2023): Hi there! Thanks for creating an issue. I'll merge it with https://github.com/jmorganca/ollama/issues/746
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#555