github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-11-09 10:50:35 -06:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

[GH-ISSUE #15750] issue: Not able to generate image from a prompt by selecting an image model (dall-e-3 or gpt-image-1) #33185

New Issue
Closed
opened 2026-04-25 07:05:49 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-25 07:05:49 -05:00
Owner
Copy Link
Copy Source

Originally created by @cpappala-godaddy on GitHub (Jul 15, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/15750

Check Existing Issues

  • I have searched the existing issues and discussions.
  • I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

v0.6.16

Ollama Version (if applicable)

No response

Operating System

macOS Sonoma

Browser (if applicable)

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 should be able to generate image by selecting an Image model from dropdown.
For example: dall-e-3 or gpt-image-1

Actual Behavior

Image

Steps to Reproduce

  1. When I select dall-e-3 to target a model to produce an image error is thrown.
  2. Is it possible to switch image models for non-admin users? (apart from setting a default image model in Admin Panel Settings)

Logs & Screenshots

Image

Additional Information

No response

Originally created by @cpappala-godaddy on GitHub (Jul 15, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/15750 ### Check Existing Issues - [x] I have searched the existing issues and discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version v0.6.16 ### Ollama Version (if applicable) _No response_ ### Operating System macOS Sonoma ### Browser (if applicable) 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 should be able to generate image by selecting an Image model from dropdown. For example: dall-e-3 or gpt-image-1 ### Actual Behavior <img width="1410" height="315" alt="Image" src="https://github.com/user-attachments/assets/5f9552e2-4af7-458c-ba9e-5cacf252d727" /> ### Steps to Reproduce 1. When I select dall-e-3 to target a model to produce an image error is thrown. 2. Is it possible to switch image models for non-admin users? (apart from setting a default image model in Admin Panel Settings) ### Logs & Screenshots <img width="1410" height="315" alt="Image" src="https://github.com/user-attachments/assets/20458211-9408-4eae-9877-3156f64ae2fd" /> ### Additional Information _No response_
GiteaMirror added the bug label 2026-04-25 07:05:49 -05:00
GiteaMirror commented 2026-04-25 07:05:51 -05:00
Author
Owner
Copy Link
Copy Source

@rgaricano commented on GitHub (Jul 15, 2025):

what is your image setup?
(be sure that image sizes fit with used model requeriments, e.g. 1024x1024 for gpt-image-1, you can find that requirements in openai doc page, e.g. https://platform.openai.com/docs/api-reference/images/create#images-create-size )

<!-- gh-comment-id:3075777914 --> @rgaricano commented on GitHub (Jul 15, 2025): what is your image setup? (be sure that image sizes fit with used model requeriments, e.g. 1024x1024 for gpt-image-1, you can find that requirements in openai doc page, e.g. https://platform.openai.com/docs/api-reference/images/create#images-create-size )
GiteaMirror commented 2026-04-25 07:05:52 -05:00
Author
Owner
Copy Link
Copy Source

@cpappala-godaddy commented on GitHub (Jul 15, 2025):

@rgaricano it has 1024x1024 as the setting.
Does Web UI support selecting an image model like gpt-image-1 for prompts from the model selector dropdown?
I was not able to find an accurate answer for this in the docs.
It works when I use a text model and select Image icon in the prompt.

<!-- gh-comment-id:3075789136 --> @cpappala-godaddy commented on GitHub (Jul 15, 2025): @rgaricano it has 1024x1024 as the setting. Does Web UI support selecting an image model like gpt-image-1 for prompts from the model selector dropdown? I was not able to find an accurate answer for this in the docs. It works when I use a text model and select Image icon in the prompt.
GiteaMirror commented 2026-04-25 07:05:52 -05:00
Author
Owner
Copy Link
Copy Source

@rgaricano commented on GitHub (Jul 15, 2025):

yes
Image

<!-- gh-comment-id:3075814573 --> @rgaricano commented on GitHub (Jul 15, 2025): yes ![Image](https://github.com/user-attachments/assets/472ba84e-5656-44b1-a8bf-05ca16e01dc9)
GiteaMirror commented 2026-04-25 07:05:53 -05:00
Author
Owner
Copy Link
Copy Source

@tjbck commented on GitHub (Jul 16, 2025):

gpt-image-1 is not a chat completion model.

<!-- gh-comment-id:3077366211 --> @tjbck commented on GitHub (Jul 16, 2025): `gpt-image-1` is not a chat completion model.
GiteaMirror commented 2026-04-25 07:05:53 -05:00
Author
Owner
Copy Link
Copy Source

@rgaricano commented on GitHub (Jul 16, 2025):

yes, but it can do it... if you have quote!

Image

<!-- gh-comment-id:3077515434 --> @rgaricano commented on GitHub (Jul 16, 2025): yes, but it can do it... if you have quote! ![Image](https://github.com/user-attachments/assets/c2873b20-6f2b-4cbf-849b-4fbea6b09c25)
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 labels bug
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
GiteaMirror ninjasurge (Kaehlen Rog)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#33185