Skip to main content

Image scan for all models

Feature Requests

I think that Qwen 2.5 VL is not smart enough to recognize images or describe them correctly. From my perspective, it would be nice if Llama 3.1 or Deepseek were the ones to recognize images.

Status: Rejected1 comment

Log in to comment and vote

Comments1

  • JP

    Team•

    Mar 7, 2025

    Qwen 2.5 VL is a vision model and is trained on image recognition. The other referenced models are not vision models and can only do text inference.