github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-05-08 12:58:11 -05:00
Code Issues 1.3k Packages Projects Releases 126 Wiki Activity

[GH-ISSUE #16948] issue: Set Step is not working for Open AI/Gemini Image Generation Engine #18106

New Issue
Closed
opened 2026-04-20 00:06:52 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-20 00:06:52 -05:00
Owner
Copy Link

Originally created by @Huanli-Gong on GitHub (Aug 27, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16948

Check Existing Issues

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

Installation Method

Git Clone

Open WebUI Version

v0.6.25

Ollama Version (if applicable)

No response

Operating System

Windows 10

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

After filling Set Steps in the image generation, "steps" or "num_inference_steps" parameter should be sent in the request.

Actual Behavior

If Image Generation Engine is set to OpenAI or Gemini, that parameter is not included in the request as show here: 1db8dec4f5/backend/open_webui/routers/images.py (L527)

Steps to Reproduce

  1. Go to Admin Panel → Settings → Images
  2. Configure OpenAI API
  3. Set URL and API key
  4. enable Image Generation (Experimental)
  5. Set Default Model, Image Size, Set Steps
  6. Click Save
  7. Using Image Generation
  8. Check if the request contains "steps" or "num_inference_steps"

Logs & Screenshots

Image [2025-08-27 06:32:12.145][329][llm_calculator][debug][http_image_gen_calculator.cc:163] HTTP request uri=/v3/images/generations body_size=123 preview="{\"model\": \"dreamlike-art/dreamlike-anime-1.0\", \"prompt\": \"anime\", \"n\": 1, \"size\": \"256x256\", \"response_format\": \"b64_json\"}"

[2025-08-27 06:32:12.145][329][serving][debug][imagegenutils.cpp:417] Image generation request options:

height: 256 (type: l)

num_images_per_prompt: 1 (type: i)

num_inference_steps: 50 (type: m)

width: 256 (type: l)

Additional Information

If it is by design since Openai and Gemini does not use that parameter, Set Step should be hidden when selecting OpenAI or Gemini. It is a visual issue that may confuse someone when it is not used or referred to in Open AI or Gemini api documentation.

Originally created by @Huanli-Gong on GitHub (Aug 27, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/16948 ### Check Existing Issues - [x] I have searched the existing issues and discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Git Clone ### Open WebUI Version v0.6.25 ### Ollama Version (if applicable) _No response_ ### Operating System Windows 10 ### 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 After filling Set Steps in the image generation, "steps" or "num_inference_steps" parameter should be sent in the request. ### Actual Behavior If Image Generation Engine is set to OpenAI or Gemini, that parameter is not included in the request as show here: https://github.com/open-webui/open-webui/blob/1db8dec4f52fc0fa8f8f7bfbb8ea5bde41fee17d/backend/open_webui/routers/images.py#L527 ### Steps to Reproduce 1. Go to Admin Panel → Settings → Images 2. Configure OpenAI API 3. Set URL and API key 4. enable Image Generation (Experimental) 5. Set Default Model, Image Size, Set Steps 6. Click Save 7. Using Image Generation 8. Check if the request contains "steps" or "num_inference_steps" ### Logs & Screenshots <img width="1920" height="877" alt="Image" src="https://github.com/user-attachments/assets/b2387f70-026c-4179-bd8b-b1f7ca6d4a23" /> [2025-08-27 06:32:12.145][329][llm_calculator][debug][http_image_gen_calculator.cc:163] HTTP request uri=/v3/images/generations body_size=123 preview="{\"model\": \"dreamlike-art/dreamlike-anime-1.0\", \"prompt\": \"anime\", \"n\": 1, \"size\": \"256x256\", \"response_format\": \"b64_json\"}" [2025-08-27 06:32:12.145][329][serving][debug][imagegenutils.cpp:417] Image generation request options: height: 256 (type: l) num_images_per_prompt: 1 (type: i) num_inference_steps: 50 (type: m) width: 256 (type: l) ### Additional Information If it is by design since Openai and Gemini does not use that parameter, Set Step should be hidden when selecting OpenAI or Gemini. It is a visual issue that may confuse someone when it is not used or referred to in Open AI or Gemini api documentation.
GiteaMirror added the bug label 2026-04-20 00:06:52 -05:00
GiteaMirror commented 2026-04-20 00:06:59 -05:00
Author
Owner
Copy Link

@tjbck commented on GitHub (Aug 27, 2025):

Addressed with 3d6605bbfd

<!-- gh-comment-id:3229982202 --> @tjbck commented on GitHub (Aug 27, 2025): Addressed with 3d6605bbfdc1326e726a176fbe2fe1e9801c7c75
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#18106
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?