github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-05-06 19:08:59 -05:00
Code Issues 1.3k Packages Projects Releases 126 Wiki Activity

[GH-ISSUE #23478] Bug: Image sent as internal UUID instead of base64 in v0.8.12, vision models cannot see images #58662

New Issue
Closed
opened 2026-05-05 23:39:45 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-05 23:39:45 -05:00
Owner
Copy Link

Originally created by @zvwgvx on GitHub (Apr 7, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/23478

Check Existing Issues

  • I have searched for any existing and/or related issues.
  • I have searched for any existing and/or related discussions.
  • I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
  • I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

0.8.12

Ollama Version (if applicable)

No response

Operating System

Ubuntu 24.04.4 LTS

Browser (if applicable)

No response

Confirmation

  • I have read and followed all instructions in README.md.
  • I am using the latest version of both Open WebUI and Ollama.
  • I have included the browser console logs.
  • I have included the Docker container logs.
  • I have provided every relevant configuration, setting, and environment variable used in my setup.
  • I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
  • I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
  • Start with the initial platform/version/OS and dependencies used,
  • Specify exact install/launch/configure commands,
  • List URLs visited, user input (incl. example values/emails/passwords if needed),
  • Describe all options and toggles enabled or changed,
  • Include any files or environmental changes,
  • Identify the expected and actual result at each stage,
  • Ensure any reasonably skilled user can follow and hit the same issue.

Expected Behavior

When sending an image to a vision-capable model, the image should be properly passed to the model so it can analyze or describe the image normally, as it does in version 0.8.11.

Actual Behavior

In version 0.8.12, after uploading/sending an image to the model, the model behaves as if no image was received. The same model and the same image work correctly in version 0.8.11.

Steps to Reproduce

  1. Run Open WebUI version 0.8.12
  2. Select a model that supports image input
  3. Upload or send an image in the chat
  4. Ask the model to describe or analyze the image
  5. Observe that the model does not recognize or process the image
  6. Compare with version 0.8.11, where the same model and image work correctly

Logs & Screenshots

Image

Additional Information

No response

Originally created by @zvwgvx on GitHub (Apr 7, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/23478 ### Check Existing Issues - [x] I have searched for any existing and/or related issues. - [x] I have searched for any existing and/or related discussions. - [x] I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!). - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version 0.8.12 ### Ollama Version (if applicable) _No response_ ### Operating System Ubuntu 24.04.4 LTS ### Browser (if applicable) _No response_ ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### Expected Behavior When sending an image to a vision-capable model, the image should be properly passed to the model so it can analyze or describe the image normally, as it does in version `0.8.11`. ### Actual Behavior In version `0.8.12`, after uploading/sending an image to the model, the model behaves as if no image was received. The same model and the same image work correctly in version `0.8.11`. ### Steps to Reproduce 1. Run Open WebUI version `0.8.12` 2. Select a model that supports image input 3. Upload or send an image in the chat 4. Ask the model to describe or analyze the image 5. Observe that the model does not recognize or process the image 6. Compare with version `0.8.11`, where the same model and image work correctly ### Logs & Screenshots <img width="1334" height="657" alt="Image" src="https://github.com/user-attachments/assets/98bc081e-46c5-434c-9919-68621d4378b8" /> ### Additional Information _No response_
GiteaMirror added the bug label 2026-05-05 23:39:45 -05:00
GiteaMirror commented 2026-05-05 23:39:48 -05:00
Author
Owner
Copy Link

@Classic298 commented on GitHub (Apr 7, 2026):

cannot reproduce, also gpt oss 20b doesnt have image input

<!-- gh-comment-id:4200609036 --> @Classic298 commented on GitHub (Apr 7, 2026): cannot reproduce, also gpt oss 20b doesnt have image input
GiteaMirror commented 2026-05-05 23:39:48 -05:00
Author
Owner
Copy Link

@zvwgvx commented on GitHub (Apr 8, 2026):

sorry for wrong image

at time i use 0.8.12
Image

i return 0.8.11

Image
<!-- gh-comment-id:4203261428 --> @zvwgvx commented on GitHub (Apr 8, 2026): sorry for wrong image at time i use 0.8.12 <img width="993" height="769" alt="Image" src="https://github.com/user-attachments/assets/e7a25dc9-e016-41c3-8263-dae7523fcf19" /> i return 0.8.11 <img width="979" height="716" alt="Image" src="https://github.com/user-attachments/assets/8522ca36-f6bf-45e0-9347-70fe883a81b7" />
GiteaMirror commented 2026-05-05 23:39:49 -05:00
Author
Owner
Copy Link

@zvwgvx commented on GitHub (Apr 8, 2026):

I re-tested with v0.8.12 and image vision is now working correctly across all models I tried. I'm not sure why it wasn't working before despite trying multiple models and providers.

I apologize for the noise.

<!-- gh-comment-id:4203293605 --> @zvwgvx commented on GitHub (Apr 8, 2026): I re-tested with v0.8.12 and image vision is now working correctly across all models I tried. I'm not sure why it wasn't working before despite trying multiple models and providers. I apologize for the noise.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#58662
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?