[GH-ISSUE #17341] issue: Can't view images in responses #18246

Closed
opened 2026-04-20 00:27:11 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @liucoj on GitHub (Sep 10, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/17341

Check Existing Issues

  • I have searched for any existing and/or related issues.
  • I have searched for any existing and/or related discussions.
  • I am using the latest version of Open WebUI.

Installation Method

Pip Install

Open WebUI Version

v0.6.26

Ollama Version (if applicable)

No response

Operating System

MacOS 15.6.1

Browser (if applicable)

Safari, Firefox, Chrome

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

I used for an year a tool (https://openwebui.com/t/myria/flux) for querying Replicate.com API to generate images with Flux. Generated image appears in response with some details.

Actual Behavior

Since latest update of OWUI images can't render in chat anymore, a message appear:
"The image generation completed successfully!
Note that the generated image ALREADY HAS been automatically sent and displayed to the user by the tool."
"The image has been successfully generated. Is there anything you’d like changed?

Image

Steps to Reproduce

  1. Load my Flux Tool (https://openwebui.com/t/myria/flux) or something similar to generate images via API
  2. Fire up a prompt and wait for response
  3. Image will not appear in chat.

Logs & Screenshots

Image

Additional Information

No response

Originally created by @liucoj on GitHub (Sep 10, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/17341 ### 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 am using the latest version of Open WebUI. ### Installation Method Pip Install ### Open WebUI Version v0.6.26 ### Ollama Version (if applicable) _No response_ ### Operating System MacOS 15.6.1 ### Browser (if applicable) Safari, Firefox, Chrome ### 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 I used for an year a tool (https://openwebui.com/t/myria/flux) for querying Replicate.com API to generate images with Flux. Generated image appears in response with some details. ### Actual Behavior Since latest update of OWUI images can't render in chat anymore, a message appear: "The image generation completed successfully! Note that the generated image ALREADY HAS been automatically sent and displayed to the user by the tool." "The image has been successfully generated. Is there anything you’d like changed? <img width="1022" height="522" alt="Image" src="https://github.com/user-attachments/assets/4e125de7-05ce-499f-a354-56ee370b2104" /> ### Steps to Reproduce 1. Load my Flux Tool (https://openwebui.com/t/myria/flux) or something similar to generate images via API 2. Fire up a prompt and wait for response 3. Image will not appear in chat. ### Logs & Screenshots <img width="1029" height="380" alt="Image" src="https://github.com/user-attachments/assets/7f3e05ea-30af-4525-962c-436bc5154a6b" /> ### Additional Information _No response_
GiteaMirror added the bug label 2026-04-20 00:27:11 -05:00
Author
Owner

@tjbck commented on GitHub (Sep 11, 2025):

Have you tried disabling native function calling mode?

<!-- gh-comment-id:3279365700 --> @tjbck commented on GitHub (Sep 11, 2025): Have you tried disabling native function calling mode?
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#18246