Enable Volume Generation from Concrete Labelmaps in MAISI ControlNet

Is your feature request related to a problem? Please describe.
Image generation with MAISI

Describe the solution you'd like
Afaiu, currently, MAISI can "only" generate volumes conditionally on controlnet_cond. These are relative size changes of certain anatomical labels. But it cannot generate a volume from a concrete labelmap that is given.

Describe alternatives you've considered
In ControlNet's forward() method, I did not see an alternative that would allow embedding a concrete labelmap. The Diffusion Model requires embeddings from ControlNet, and cannot accept concrete labelmaps either.

Additional context
Figure 2 in the MAISI paper also seems to indicate that ControlNet can only accept "task-specific conditions", and "Diffusion Model" depends on ControlNet embeddings.

Start by reading monai/apps/generation/maisi/networks/controlnet_maisi.py, especially ControlNet's forward() method, and compare it with the MAISI paper's description of task-specific conditions. Determine how a concrete labelmap would be represented and passed through ControlNet and the diffusion model; done means volume generation accepts the supplied labelmap as a condition and the behavior is covered by appropriate tests.