Trying to get llama3.2-vision working

Questions
1

Hello the community,

I’m trying to use llama3.2-vision to analyse image using a simple prompt. I use the prompt that has been shared within the community but it does not work.

Each time a send a image, it seems that the model the not received the file or is unable to read it. The same question has been asked by @Steve_Warburton (Trying to get llama3.2-vision working with a form) .

Have you been able to solve the issue?

Thank you fro your response.

Regards,
aduchesne

2

See if using AI Agent node with “Automatically Passthrough Binary Images” option enabled yields better results for you:

3

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.