[GH-ISSUE #11736] feat: Separate image processing model #16337

New Issue

GiteaMirror · 2026-04-19T22:17:07-05:00

GiteaMirror commented

2026-04-19 22:17:07 -05:00

Originally created by @huanyan434 on GitHub (Mar 16, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/11736

Check Existing Issues

I have searched the existing issues and discussions.

Problem Description

my model does not support image processing

Desired Solution you'd like

I want image processing to be done using an external model like web search, because my model does not support image processing

Alternatives Considered

No response

Additional Context

No response

Originally created by @huanyan434 on GitHub (Mar 16, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/11736 ### Check Existing Issues - [x] I have searched the existing issues and discussions. ### Problem Description my model does not support image processing ### Desired Solution you'd like I want image processing to be done using an external model like web search, because my model does not support image processing ### Alternatives Considered _No response_ ### Additional Context _No response_

GiteaMirror closed this issue

2026-04-19 22:17:07 -05:00

GiteaMirror commented

2026-04-19 22:17:08 -05:00

@Classic298 commented on GitHub (Mar 16, 2025):

use a model that supports image processing and let it process the image
switch back to the desired model (that doesn't support image processing) for the next response

@Classic298 commented on GitHub (Mar 16, 2025): 1) use a model that supports image processing and let it process the image 2) switch back to the desired model (that doesn't support image processing) for the next response

GiteaMirror commented

2026-04-19 22:17:08 -05:00

@spammenotinoz commented on GitHub (Mar 16, 2025):

Agree, for testing I hard-coded a Model when image gen is used, faster, costs less and less ramblings.
The real question is why even use an LLM at all?
Except for Gemini, where it understands and can make changes to the picture created.

@spammenotinoz commented on GitHub (Mar 16, 2025): Agree, for testing I hard-coded a Model when image gen is used, faster, costs less and less ramblings. The real question is why even use an LLM at all? Except for Gemini, where it understands and can make changes to the picture created.

GiteaMirror commented

2026-04-19 22:17:08 -05:00

@AbdullahMPrograms commented on GitHub (Mar 16, 2025):

this is doable using pipes, here is a rough one I created and have been using for the last while: https://github.com/AbdullahMPrograms/DynamicVisionRouter

@AbdullahMPrograms commented on GitHub (Mar 16, 2025): this is doable using pipes, here is a rough one I created and have been using for the last while: https://github.com/AbdullahMPrograms/DynamicVisionRouter

GiteaMirror referenced this issue

2026-04-19 23:45:40 -05:00

[GH-ISSUE #16337] issue: Typing ``` 3 backticks followed by <shift-enter> removes backticks if "Enter Key Behavior" is "Enter to Send" #17866

GiteaMirror referenced this issue

2026-04-20 05:14:26 -05:00

[PR #16340] [CLOSED] fix: prevent backtick removal on Shift+Enter in chat input #24103

GiteaMirror referenced this issue

2026-04-20 05:14:27 -05:00

[PR #16341] [CLOSED] fix: prevent backtick removal on Shift+Enter in chat input #24104

GiteaMirror referenced this issue

2026-04-25 07:18:14 -05:00

[GH-ISSUE #16337] issue: Typing ``` 3 backticks followed by <shift-enter> removes backticks if "Enter Key Behavior" is "Enter to Send" #33395