Is your feature request related to a problem? Please describe.
The multimodal abilities of model Janus Pro 7B is not fully supported, It cannot understand pictures sent in the chat nor can it generate images according to user command.
Describe the solution you'd like
Add official support of Janus-Pro 7B to fully perform as intended
Describe alternatives you've considered
The devs have a demo made with gradio but I would like an intergrated interface for all models
Additional context
This is what it does now, which it ask me to describe the image.
This is what it should do, chatting with context is not fully necessary
Originally created by @TriDefender on GitHub (Feb 14, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/9959
**Is your feature request related to a problem? Please describe.**
The multimodal abilities of model Janus Pro 7B is not fully supported, It cannot understand pictures sent in the chat nor can it generate images according to user command.
**Describe the solution you'd like**
Add official support of Janus-Pro 7B to fully perform as intended
**Describe alternatives you've considered**
The devs have a demo made with gradio but I would like an intergrated interface for all models
**Additional context**
This is what it does now, which it ask me to describe the image.
This is what it should do, chatting with context is not fully necessary
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 @TriDefender on GitHub (Feb 14, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/9959
Is your feature request related to a problem? Please describe.
The multimodal abilities of model Janus Pro 7B is not fully supported, It cannot understand pictures sent in the chat nor can it generate images according to user command.
Describe the solution you'd like
Add official support of Janus-Pro 7B to fully perform as intended
Describe alternatives you've considered
The devs have a demo made with gradio but I would like an intergrated interface for all models
Additional context
This is what it does now, which it ask me to describe the image.
This is what it should do, chatting with context is not fully necessary