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
Git Clone
Open WebUI Version
v0.7.2
Ollama Version (if applicable)
latest
Operating System
Win11
Browser (if applicable)
Edge,IOS, Zen
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
User uploads new image or reference a specific image in chat > model should focus on that image.
Actual Behavior
When user uploads new image to chat, and the model has native tool calling, it should refrence that image and do an image_edit tool call, instead, its uses older image and not the uploaded image.
Steps to Reproduce
1,Create any image in chat
2.Upload new image and ask for changes.
3.LLM will still work on first image
Logs & Screenshots
Additional Information
No response
Originally created by @iChristGit on GitHub (Jan 17, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20754
### 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
Git Clone
### Open WebUI Version
v0.7.2
### Ollama Version (if applicable)
latest
### Operating System
Win11
### Browser (if applicable)
Edge,IOS, Zen
### 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
User uploads new image or reference a specific image in chat > model should focus on that image.
### Actual Behavior
When user uploads new image to chat, and the model has native tool calling, it should refrence that image and do an image_edit tool call, instead, its uses older image and not the uploaded image.
### Steps to Reproduce
1,Create any image in chat
2.Upload new image and ask for changes.
3.LLM will still work on first image
### Logs & Screenshots
<img width="564" height="1238" alt="Image" src="https://github.com/user-attachments/assets/bbe09c22-0362-4e39-bc02-74d29b60b050" />
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-05-21 01:29:10 -05:00
@owui-terminator[bot] commented on GitHub (Jan 17, 2026):
🔍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:
#20237issue: Image editing stopped working by tomasloksa • Dec 29, 2025 • bug, confirmed issue
#20436issue: image generation cannot finish normally by lywbh • Jan 07, 2026 • bug
#20544issue: Document uploading - Docling API by n4gY1 • Jan 10, 2026 • bug
#20490issue: Unable to edit reference image by fgonzalez-glmc • Jan 08, 2026 • bug
#18995issue: image generation and edition doesn’t work on temporary chats by futureshield • Nov 06, 2025 • bug
Show 5 more related issues
#19339issue: Multiple input images for image edit and generation are passed as separate instances instead of as a list by eml-henn • Nov 21, 2025 • bug
#19701issue: knowledge can not multiple upload file by willy808 • Dec 03, 2025 • bug
#20091issue: image is regarded as binary in temp chat by funnycups • Dec 22, 2025 • bug
#19187issue: Image generation menu gone. by calebrio02 • Nov 14, 2025 • bug
#18514issue: Incorrect logic when uploading an image into a collection by chayaziv • Oct 22, 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:3763087882 -->
@owui-terminator[bot] commented on GitHub (Jan 17, 2026):
🔍 **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. [#20237](https://github.com/open-webui/open-webui/issues/20237) **issue: Image editing stopped working**
*by tomasloksa • Dec 29, 2025 • `bug`, `confirmed issue`*
2. [#20436](https://github.com/open-webui/open-webui/issues/20436) **issue: image generation cannot finish normally**
*by lywbh • Jan 07, 2026 • `bug`*
3. [#20544](https://github.com/open-webui/open-webui/issues/20544) **issue: Document uploading - Docling API**
*by n4gY1 • Jan 10, 2026 • `bug`*
4. [#20490](https://github.com/open-webui/open-webui/issues/20490) **issue: Unable to edit reference image**
*by fgonzalez-glmc • Jan 08, 2026 • `bug`*
5. [#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`*
<details>
<summary>Show 5 more related issues</summary>
6. [#19339](https://github.com/open-webui/open-webui/issues/19339) **issue: Multiple input images for image edit and generation are passed as separate instances instead of as a list**
*by eml-henn • Nov 21, 2025 • `bug`*
7. [#19701](https://github.com/open-webui/open-webui/issues/19701) **issue: knowledge can not multiple upload file**
*by willy808 • Dec 03, 2025 • `bug`*
8. [#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`*
9. [#19187](https://github.com/open-webui/open-webui/issues/19187) **issue: Image generation menu gone.**
*by calebrio02 • Nov 14, 2025 • `bug`*
10. [#18514](https://github.com/open-webui/open-webui/issues/18514) **issue: Incorrect logic when uploading an image into a collection**
*by chayaziv • Oct 22, 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.
Not sure its related to the old issues, when there is no prior images its working, the issue is happening by first generating an image and then uploading a different image
<!-- gh-comment-id:3763333466 -->
@iChristGit commented on GitHub (Jan 17, 2026):
Not sure its related to the old issues, when there is no prior images its working, the issue is happening by first generating an image and then uploading a different image
Having the same issue, it only edits images that are also generated by the AI. If I attach an image (in a fresh chat) and ask to edit it, it will just generate something new. But it's weird because it worked once when I took a picture with my phone from within the app and asked to modify that, but all the other times it also didn't work that way.
<!-- gh-comment-id:3790130951 -->
@nvdg commented on GitHub (Jan 23, 2026):
Having the same issue, it only edits images that are also generated by the AI. If I attach an image (in a fresh chat) and ask to edit it, it will just generate something new. But it's weird because it worked once when I took a picture with my phone from within the app and asked to modify that, but all the other times it also didn't work that way.
EDIT, this appears to be the issue:
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
Having the same issue, it only edits images that are also generated by the AI. If I attach an image (in a fresh chat) and ask to edit it, it will just generate something new. But it's weird because it worked once when I took a picture with my phone from within the app and asked to modify that, but all the other times it also didn't work that way.
In fresh chat, I can edit uploaded images, once even one image has been generated it wont allow image editing.
It has nothing to do with temporary chats
<!-- gh-comment-id:3794290723 -->
@iChristGit commented on GitHub (Jan 24, 2026):
> Having the same issue, it only edits images that are also generated by the AI. If I attach an image (in a fresh chat) and ask to edit it, it will just generate something new. But it's weird because it worked once when I took a picture with my phone from within the app and asked to modify that, but all the other times it also didn't work that way.
>
> EDIT, this appears to be the issue:
> 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
No this issue is different.
In fresh chat, I can edit uploaded images, once even one image has been generated it wont allow image editing.
It has nothing to do with temporary chats
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 @iChristGit on GitHub (Jan 17, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20754
Check Existing Issues
Installation Method
Git Clone
Open WebUI Version
v0.7.2
Ollama Version (if applicable)
latest
Operating System
Win11
Browser (if applicable)
Edge,IOS, Zen
Confirmation
README.md.Expected Behavior
User uploads new image or reference a specific image in chat > model should focus on that image.
Actual Behavior
When user uploads new image to chat, and the model has native tool calling, it should refrence that image and do an image_edit tool call, instead, its uses older image and not the uploaded image.
Steps to Reproduce
1,Create any image in chat
2.Upload new image and ask for changes.
3.LLM will still work on first image
Logs & Screenshots
Additional Information
No response
@owui-terminator[bot] commented on GitHub (Jan 17, 2026):
🔍 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:
#20237 issue: Image editing stopped working
by tomasloksa • Dec 29, 2025 •
bug,confirmed issue#20436 issue: image generation cannot finish normally
by lywbh • Jan 07, 2026 •
bug#20544 issue: Document uploading - Docling API
by n4gY1 • Jan 10, 2026 •
bug#20490 issue: Unable to edit reference image
by fgonzalez-glmc • Jan 08, 2026 •
bug#18995 issue: image generation and edition doesn’t work on temporary chats
by futureshield • Nov 06, 2025 •
bugShow 5 more related issues
#19339 issue: Multiple input images for image edit and generation are passed as separate instances instead of as a list
by eml-henn • Nov 21, 2025 •
bug#19701 issue: knowledge can not multiple upload file
by willy808 • Dec 03, 2025 •
bug#20091 issue: image is regarded as binary in temp chat
by funnycups • Dec 22, 2025 •
bug#19187 issue: Image generation menu gone.
by calebrio02 • Nov 14, 2025 •
bug#18514 issue: Incorrect logic when uploading an image into a collection
by chayaziv • Oct 22, 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.
@iChristGit commented on GitHub (Jan 17, 2026):
Not sure its related to the old issues, when there is no prior images its working, the issue is happening by first generating an image and then uploading a different image
@tjbck commented on GitHub (Jan 22, 2026):
@silentoplayz @micahdbak able to reproduce?
@nvdg commented on GitHub (Jan 23, 2026):
Having the same issue, it only edits images that are also generated by the AI. If I attach an image (in a fresh chat) and ask to edit it, it will just generate something new. But it's weird because it worked once when I took a picture with my phone from within the app and asked to modify that, but all the other times it also didn't work that way.
EDIT, this appears to be the issue:
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
@iChristGit commented on GitHub (Jan 24, 2026):
No this issue is different.
In fresh chat, I can edit uploaded images, once even one image has been generated it wont allow image editing.
It has nothing to do with temporary chats
@iChristGit commented on GitHub (Feb 13, 2026):
Works flawlessly on latest 0.8.0 version, closing this