Multidiffusion (panorama pipeline) is missing segmentation inputs?

I'm looking at the multidiffusion panorama pipeline page (https://huggingface.co/docs/diffusers/en/api/pipelines/panorama). It looks like there is no way to specify the segmentation and associated prompts as in the original paper https://multidiffusion.github.io/ . If the code only has the panorama capability and not the region based generation using segmentation and prompts, then it should be extended to include the regional generation... If it does have region based generation then the documentation should be updated to show how to use it!

Start with the multidiffusion panorama pipeline documentation at the linked Hugging Face page and compare its documented capabilities with the original paper. Determine whether segmentation inputs and region-based prompts already exist; done means either documenting their usage or defining the implementation needed to add them.

Written by the indexing model from the issue text.