[GH-ISSUE #13958] feat: Add Image Localization to the chat preview #120398

Closed
opened 2026-05-20 22:00:22 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @Notbici on GitHub (May 16, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/13958

Check Existing Issues

  • I have searched the existing issues and discussions.

Problem Description

Qwen 2.5vl has added image localization where it can output JSON with coordinates for where it found certain objects.

This could be a fantastic feature, see about it here https://ollama.com/library/qwen2.5v

Desired Solution you'd like

When I upload an image and use the appropriate model, if I ask "Please find where the oranges are" I want the preview that I uploaded to be overlayed in the response with boundary boxes outlined based on the models JSON response.

Alternatives Considered

No response

Additional Context

No response

Originally created by @Notbici on GitHub (May 16, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/13958 ### Check Existing Issues - [x] I have searched the existing issues and discussions. ### Problem Description Qwen 2.5vl has added image localization where it can output JSON with coordinates for where it found certain objects. This could be a fantastic feature, see about it here https://ollama.com/library/qwen2.5v ### Desired Solution you'd like When I upload an image and use the appropriate model, if I ask "Please find where the oranges are" I want the preview that I uploaded to be overlayed in the response with boundary boxes outlined based on the models JSON response. ### Alternatives Considered _No response_ ### Additional Context _No response_
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#120398