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
v0.6.43
Ollama Version (if applicable)
No response
Operating System
azure container app
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 I upload an image, turn on the image feature and provide instructions, I expect the original image to be edited. It worked like this in v 0.6.41!
Actual Behavior
The image produced is always a random one, that has nothing to do with the original. With further prompts i can edit the generated image perfectly, but the original - first image is always ignored.
Steps to Reproduce
Use v0.6.43. It works perfectly fine in v0.6.41!
Set up create image and edit image to use gemini-2.5-flash-image
Start a new chat, turn on the image feature
Provide any image .png, .jpg and any prompt for the image to be edited
The provided image is completely ignored.
Further image edits on the generated image work just fine!
Logs & Screenshots
Additional Information
No response
Originally created by @tomasloksa on GitHub (Dec 29, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20237
### 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
v0.6.43
### Ollama Version (if applicable)
_No response_
### Operating System
azure container app
### 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 I upload an image, turn on the image feature and provide instructions, I expect the original image to be edited. It worked like this in v 0.6.41!
### Actual Behavior
The image produced is always a random one, that has nothing to do with the original. With further prompts i can edit the generated image perfectly, but the original - first image is always ignored.
### Steps to Reproduce
1. Use v0.6.43. It works perfectly fine in v0.6.41!
2. Set up create image and edit image to use gemini-2.5-flash-image
3. Start a new chat, turn on the image feature
4. Provide any image .png, .jpg and any prompt for the image to be edited
5. The provided image is completely ignored.
6. Further image edits on the generated image work just fine!
### Logs & Screenshots
<img width="1053" height="910" alt="Image" src="https://github.com/user-attachments/assets/390aae33-bde0-4c70-8c0c-15324351af4c" />
<img width="1004" height="995" alt="Image" src="https://github.com/user-attachments/assets/f6fd6dd6-b42e-4682-bdfa-0c22f1478b19" />
### Additional Information
_No response_
#19215issue:Server Failed opening Admin > Settings > Images Panel by fordinator • Nov 16, 2025 • bug
💡Tips:
If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
If you found a solution in any of these issues, please share it here to help others
This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
<!-- gh-comment-id:3696164547 -->
@owui-terminator[bot] commented on GitHub (Dec 29, 2025):
🔍 **Similar Issues Found**
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
1. [#18995](https://github.com/open-webui/open-webui/issues/18995) **issue: image generation and edition doesn’t work on temporary chats**
*by futureshield • Nov 06, 2025 • `bug`*
2. [#20019](https://github.com/open-webui/open-webui/issues/20019) **issue:**
*by j63440490 • Dec 17, 2025 • `bug`*
3. [#19777](https://github.com/open-webui/open-webui/issues/19777) **issue:**
*by Yaute7 • Dec 05, 2025 • `bug`*
4. [#20092](https://github.com/open-webui/open-webui/issues/20092) **issue:**
*by VideoRyan • Dec 22, 2025 • `bug`*
5. [#20091](https://github.com/open-webui/open-webui/issues/20091) **issue: image is regarded as binary in temp chat**
*by funnycups • Dec 22, 2025 • `bug`*
<details>
<summary>Show 5 more related issues</summary>
6. [#19711](https://github.com/open-webui/open-webui/issues/19711) **issue: Editing function for models broken**
*by skleffmann • Dec 03, 2025 • `bug`*
7. [#19187](https://github.com/open-webui/open-webui/issues/19187) **issue: Image generation menu gone.**
*by calebrio02 • Nov 14, 2025 • `bug`*
8. [#19481](https://github.com/open-webui/open-webui/issues/19481) **issue: admin panel not working**
*by kybeq • Nov 25, 2025 • `bug`*
9. [#19563](https://github.com/open-webui/open-webui/issues/19563) **issue:**
*by naruto7g • Nov 28, 2025 • `bug`*
10. [#19215](https://github.com/open-webui/open-webui/issues/19215) **issue:Server Failed opening Admin > Settings > Images Panel**
*by fordinator • Nov 16, 2025 • `bug`*
</details>
---
💡 **Tips:**
- If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
- If you found a solution in any of these issues, please share it here to help others
*This comment was generated automatically by a bot.* Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
@Classic298 Not sure if I'm doing something wrong, but it's still not working for me.
I pulled your fork, switched to the image-fix branch and then did a docker compose up. I set everything up - openai key, gemini image api with create and edit image and it still behaves in the same way - generates the first image and only after that edits can be made.
<!-- gh-comment-id:3698544493 -->
@tomasloksa commented on GitHub (Dec 30, 2025):
@Classic298 Not sure if I'm doing something wrong, but it's still not working for me.
I pulled your fork, switched to the image-fix branch and then did a `docker compose up`. I set everything up - openai key, gemini image api with create and edit image and it still behaves in the same way - generates the first image and only after that edits can be made.
@Classic298 Not sure if I'm doing something wrong, but it's still not working for me.
I pulled your fork, switched to the image-fix branch and then did a docker compose up. I set everything up - openai key, gemini image api with create and edit image and it still behaves in the same way - generates the first image and only after that edits can be made.
You would have to build a Docker image from his fork first and then reference that image in your compose file.
<!-- gh-comment-id:3698888120 -->
@Ithanil commented on GitHub (Dec 30, 2025):
> [@Classic298](https://github.com/Classic298) Not sure if I'm doing something wrong, but it's still not working for me.
>
> I pulled your fork, switched to the image-fix branch and then did a `docker compose up`. I set everything up - openai key, gemini image api with create and edit image and it still behaves in the same way - generates the first image and only after that edits can be made.
You would have to _build_ a Docker image from his fork first and then reference that image in your compose file.
It does the same thing to me and I've noticed that the issue is it never sends it to the edit endpoint it it sends everything to generate regardless I don't know why it broke that but it did But if I knew any other way to fix it myself I would because database won't go backwards so I'd start over but I did it on one copy just to use it and just exported the settings but I got to wait for them to fix it to use the other copy Unless there's a way somewhere in there we ourselves that I can fix this issue but if you look hard enough it's sending everything to generate it's not sending the edits to edit an URI regardless of the back end
<!-- gh-comment-id:3701450544 -->
@formytech commented on GitHub (Dec 31, 2025):
It does the same thing to me and I've noticed that the issue is it never sends it to the edit endpoint it it sends everything to generate regardless I don't know why it broke that but it did But if I knew any other way to fix it myself I would because database won't go backwards so I'd start over but I did it on one copy just to use it and just exported the settings but I got to wait for them to fix it to use the other copy Unless there's a way somewhere in there we ourselves that I can fix this issue but if you look hard enough it's sending everything to generate it's not sending the edits to edit an URI regardless of the back end
<!-- gh-comment-id:3708491570 -->
@maglat commented on GitHub (Jan 4, 2026):
There is a pull request already with the fix
https://github.com/open-webui/open-webui/pull/20239
should be addressed in dev, though, confirmation needed here @tomasloksa CC everyone else
PLEASE test it. New version soon - need confirmation now. Thanks guys
<!-- gh-comment-id:3712497137 -->
@Classic298 commented on GitHub (Jan 5, 2026):
should be addressed in dev, though, confirmation needed here @tomasloksa CC everyone else
PLEASE test it. New version soon - need confirmation now. Thanks guys
@Classic298 Checked the dev branch and now it works for me. Guess I did it wrong when running locally, sorry.
<!-- gh-comment-id:3717758911 -->
@tomasloksa commented on GitHub (Jan 7, 2026):
@Classic298 Checked the dev branch and now it works for me. Guess I did it wrong when running locally, sorry.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @tomasloksa on GitHub (Dec 29, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20237
Check Existing Issues
Installation Method
Docker
Open WebUI Version
v0.6.43
Ollama Version (if applicable)
No response
Operating System
azure container app
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
When I upload an image, turn on the image feature and provide instructions, I expect the original image to be edited. It worked like this in v 0.6.41!
Actual Behavior
The image produced is always a random one, that has nothing to do with the original. With further prompts i can edit the generated image perfectly, but the original - first image is always ignored.
Steps to Reproduce
Logs & Screenshots
Additional Information
No response
@owui-terminator[bot] commented on GitHub (Dec 29, 2025):
🔍 Similar Issues Found
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
#18995 issue: image generation and edition doesn’t work on temporary chats
by futureshield • Nov 06, 2025 •
bug#20019 issue:
by j63440490 • Dec 17, 2025 •
bug#19777 issue:
by Yaute7 • Dec 05, 2025 •
bug#20092 issue:
by VideoRyan • Dec 22, 2025 •
bug#20091 issue: image is regarded as binary in temp chat
by funnycups • Dec 22, 2025 •
bugShow 5 more related issues
#19711 issue: Editing function for models broken
by skleffmann • Dec 03, 2025 •
bug#19187 issue: Image generation menu gone.
by calebrio02 • Nov 14, 2025 •
bug#19481 issue: admin panel not working
by kybeq • Nov 25, 2025 •
bug#19563 issue:
by naruto7g • Nov 28, 2025 •
bug#19215 issue:Server Failed opening Admin > Settings > Images Panel
by fordinator • Nov 16, 2025 •
bug💡 Tips:
This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
@Classic298 commented on GitHub (Dec 29, 2025):
thanks for the report, will investigate
@Classic298 commented on GitHub (Dec 29, 2025):
@tomasloksa
https://github.com/open-webui/open-webui/pull/20239
please test this PR
@tomasloksa commented on GitHub (Dec 30, 2025):
@Classic298 Not sure if I'm doing something wrong, but it's still not working for me.
I pulled your fork, switched to the image-fix branch and then did a
docker compose up. I set everything up - openai key, gemini image api with create and edit image and it still behaves in the same way - generates the first image and only after that edits can be made.@Ithanil commented on GitHub (Dec 30, 2025):
You would have to build a Docker image from his fork first and then reference that image in your compose file.
@formytech commented on GitHub (Dec 31, 2025):
It does the same thing to me and I've noticed that the issue is it never sends it to the edit endpoint it it sends everything to generate regardless I don't know why it broke that but it did But if I knew any other way to fix it myself I would because database won't go backwards so I'd start over but I did it on one copy just to use it and just exported the settings but I got to wait for them to fix it to use the other copy Unless there's a way somewhere in there we ourselves that I can fix this issue but if you look hard enough it's sending everything to generate it's not sending the edits to edit an URI regardless of the back end
@maglat commented on GitHub (Jan 4, 2026):
There is a pull request already with the fix
https://github.com/open-webui/open-webui/pull/20239
@Classic298 commented on GitHub (Jan 5, 2026):
should be addressed in dev, though, confirmation needed here @tomasloksa CC everyone else
PLEASE test it. New version soon - need confirmation now. Thanks guys
@tomasloksa commented on GitHub (Jan 7, 2026):
@Classic298 Checked the dev branch and now it works for me. Guess I did it wrong when running locally, sorry.