I have searched the existing issues and discussions.
Problem Description
The current image generation via the Gemini API only permits Imagen 3 002, instead of having multiple models, such as Gemini-2.0-flash-exp-image-generation
Desired Solution you'd like
I would like to have the ability to have the image model be gemini-2.0-flash-exp-image-generation, since it can generate images. I would also like to have the ability to edit images, so if gemini-2.0-flash-exp-image-generation is selected, the image could be parsed to the model to edit.
Alternatives Considered
No response
Additional Context
There have been two issues about this, both have been closed and no development nor comment from anybody has been done regarding this, it is straight up not supported.
Originally created by @Sweaterdog on GitHub (Mar 30, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/12199
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
### Problem Description
The current image generation via the Gemini API only permits Imagen 3 002, instead of having multiple models, such as Gemini-2.0-flash-exp-image-generation
### Desired Solution you'd like
I would like to have the ability to have the image model be `gemini-2.0-flash-exp-image-generation`, since it can generate images. I would also like to have the ability to edit images, so if `gemini-2.0-flash-exp-image-generation` is selected, the image could be parsed to the model to edit.
### Alternatives Considered
_No response_
### Additional Context
There have been two issues about this, both have been closed and no development nor comment from anybody has been done regarding this, it is straight up not supported.
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 @Sweaterdog on GitHub (Mar 30, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/12199
Check Existing Issues
Problem Description
The current image generation via the Gemini API only permits Imagen 3 002, instead of having multiple models, such as Gemini-2.0-flash-exp-image-generation
Desired Solution you'd like
I would like to have the ability to have the image model be
gemini-2.0-flash-exp-image-generation, since it can generate images. I would also like to have the ability to edit images, so ifgemini-2.0-flash-exp-image-generationis selected, the image could be parsed to the model to edit.Alternatives Considered
No response
Additional Context
There have been two issues about this, both have been closed and no development nor comment from anybody has been done regarding this, it is straight up not supported.
@tjbck commented on GitHub (Mar 30, 2025):
PR Welcome.