Generated Image is also Associated with the Edited AI Response Saved as a Copy #2957

Closed
opened 2025-11-11 15:18:26 -06:00 by GiteaMirror · 1 comment
Owner

Originally created by @Bambouzle on GitHub (Dec 8, 2024).

Originally assigned to: @tjbck on GitHub.

Bug Report

Installation Method

I am using Open-WebUI in conjunction with ollama inside a docker-compose.

Environment

  • Open WebUI Version: v0.4.8

  • Ollama (if applicable): v0.5.1

  • Operating System: Windows 11

  • Browser (if applicable): Firefox 133.0

Confirmation:

  • I have read and followed all the instructions provided in the README.md.
  • I am on 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 the exact steps to reproduce the bug in the "Steps to Reproduce" section below.

Expected Behavior:

I would expect to see no picture attached when saving an edit of the answer as copy

Actual Behavior:

The picture generated with the original response gets attached automatically to the edited copy of the answer.

Description

Bug Summary:
After generating an image based of the AI answer. Editing the AI answer then saving it as a copy attaches the original image to the edited prompt.

Reproduction Details

Steps to Reproduce:

  1. Send a prompt
  2. generate an image with the answer
  3. once the generated image is received, edit the LLM answer.
  4. Save as copy

Logs and Screenshots

Screenshots:
2024-12-08 22 51 24 001
2024-12-08 22 51 52 001
2024-12-08 22 52 00 001

Thanks for the hard work !

Originally created by @Bambouzle on GitHub (Dec 8, 2024). Originally assigned to: @tjbck on GitHub. # Bug Report ## Installation Method I am using Open-WebUI in conjunction with ollama inside a docker-compose. ## Environment - **Open WebUI Version:** v0.4.8 - **Ollama (if applicable):** v0.5.1 - **Operating System:** Windows 11 - **Browser (if applicable):** Firefox 133.0 **Confirmation:** - [x] I have read and followed all the instructions provided in the README.md. - [x] I am on the latest version of both Open WebUI and Ollama. - [ ] I have included the browser console logs. - [ ] I have included the Docker container logs. - [x] I have provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below. ## Expected Behavior: I would expect to see no picture attached when saving an edit of the answer **as copy** ## Actual Behavior: The picture generated with the original response gets attached automatically to the edited copy of the answer. ## Description **Bug Summary:** After generating an image based of the AI answer. Editing the AI answer then saving it as a copy attaches the original image to the edited prompt. ## Reproduction Details **Steps to Reproduce:** 1. Send a prompt 2. generate an image with the answer 3. once the generated image is received, edit the LLM answer. 4. Save as copy ## Logs and Screenshots **Screenshots:** ![2024-12-08 22 51 24 001](https://github.com/user-attachments/assets/3367dd62-67d6-4e98-b8e5-5e790b671e9c) ![2024-12-08 22 51 52 001](https://github.com/user-attachments/assets/53d6a04f-97e6-43db-8feb-a92c14ecd991) ![2024-12-08 22 52 00 001](https://github.com/user-attachments/assets/1afb4a74-451b-4065-8175-a5336201a060) Thanks for the hard work !
Author
Owner

@tjbck commented on GitHub (Dec 10, 2024):

Fixed on dev!

@tjbck commented on GitHub (Dec 10, 2024): Fixed on dev!
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#2957