[enhancement]: GLIGEN

### Is there an existing issue for this?

- [X] I have searched the existing issues

### Contact Details

_No response_

### What should this feature add?

For better control over the image generation, [GLIGEN](https://github.com/gligen/GLIGEN) could be added to text2image. There exists a GUI concept for comfyui called [gligen-gui](https://github.com/mut-ex/gligen-gui) that seems to offer good UX and could be used as a reference.
Adding the possibility to have finer control over object placement in image generation seems like a no brainer for a professional application and should be better than inpainting to achieve desired results.

### Alternatives

Any form of regional prompt control would be useful (e.g. as seen [here](https://github.com/hako-mikan/sd-webui-regional-prompter))

### Additional Content

_No response_