Originally created by @liucoj on GitHub (May 5, 2025).
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
v0.6.5
Ollama Version (if applicable)
0.6.7
Operating System
macOS Sequoia 15.4.1
Browser (if applicable)
Safari, Firefox, Brave
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 listed steps to reproduce the bug in detail.
Expected Behavior
Select Gemma3 or another vision model, upload an image to the chat and prompt for an analysis
Actual Behavior
Select Gemma3 or another vision model, upload an image to the chat but an error appears:
Failed to load resource: the server responded with a status of 400 (Bad Request)
Steps to Reproduce
Select a Vision model
upload a jpg image
prompt asking something about
Logs & Screenshots
on Safari I found this entry in console:
Failed to load resource: the server responded with a status of 400 (Bad Request)
Additional Information
This issue is related only to uploading images, no problems on different kind of documents like pdfs or text files.
Using the same vision model, the same image through Ollama cli worked well.
Originally created by @liucoj on GitHub (May 5, 2025).
### 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
v0.6.5
### Ollama Version (if applicable)
0.6.7
### Operating System
macOS Sequoia 15.4.1
### Browser (if applicable)
Safari, Firefox, Brave
### 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 listed steps to reproduce the bug in detail.
### Expected Behavior
Select Gemma3 or another vision model, upload an image to the chat and prompt for an analysis
### Actual Behavior
Select Gemma3 or another vision model, upload an image to the chat but an error appears:
Failed to load resource: the server responded with a status of 400 (Bad Request)
### Steps to Reproduce
1. Select a Vision model
2. upload a jpg image
3. prompt asking something about
### Logs & Screenshots
<img width="1034" alt="Image" src="https://github.com/user-attachments/assets/a96f250d-3620-4145-9f62-ea07737921fd" />
on Safari I found this entry in console:
Failed to load resource: the server responded with a status of 400 (Bad Request)
### Additional Information
This issue is related only to uploading images, no problems on different kind of documents like pdfs or text files.
Using the same vision model, the same image through Ollama cli worked well.
GiteaMirror
added the bug label 2025-11-11 16:10:26 -06:00
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 @liucoj on GitHub (May 5, 2025).
Check Existing Issues
Installation Method
Git Clone
Open WebUI Version
v0.6.5
Ollama Version (if applicable)
0.6.7
Operating System
macOS Sequoia 15.4.1
Browser (if applicable)
Safari, Firefox, Brave
Confirmation
README.md.Expected Behavior
Select Gemma3 or another vision model, upload an image to the chat and prompt for an analysis
Actual Behavior
Select Gemma3 or another vision model, upload an image to the chat but an error appears:
Failed to load resource: the server responded with a status of 400 (Bad Request)
Steps to Reproduce
Logs & Screenshots
on Safari I found this entry in console:
Failed to load resource: the server responded with a status of 400 (Bad Request)
Additional Information
This issue is related only to uploading images, no problems on different kind of documents like pdfs or text files.
Using the same vision model, the same image through Ollama cli worked well.