maisi unconditioned inference return noise

Hallo,

I tried longer to make the diffusion unet (rectified flow version) work but without success. the VAE performes correct and encoding and reconstruction look fine. I take all the configs from the repo so configuration as well as weights are equivalently loaded as in https://github.com/Project-MONAI/tutorials/blob/main/generation/maisi/maisi_inference_tutorial.ipynb.

Using the diffusion unet with the existing code of diffusion_model_infer.py with

from scripts.diff_model_infer import run_inference
data = run_inference(
  args,
  device,
  autoencoder,
  diffusion_unet,
  1.4,#scale_factor,
  None,#top_region_index_tensor,
  None, #bottom_region_index_tensor,
  torch.tensor([[1.5,1.5,4.0]]).to('cuda'),#spacing_tensor,
  torch.tensor([1]).to('cuda'),#modality_tensor,
  (96,96,96),#output_size,
  4,
  logger,
)

I saw that there was an issue with the architecture which was different during training and the implementation but I'm not sure if that is related.
https://github.com/Project-MONAI/MONAI/issues/7991.
Some observations I made is when I would like to just reconstruction an image and basically make one step, the recon get's extremly noise.

For any suggestion what could be the potential issue, I'm thankful.

Best,
Lukas

Iniziare con scripts/diff_model_infer.py e il MAISI inference tutorial notebook, riproducendo la ricostruzione in un passaggio che produce rumore. Confrontare l’architettura di inferenza e la configurazione caricata con l’implementazione dell’addestramento, incluse le differenze discusse in issue 7991. Il lavoro è completato quando l’inferenza o la ricostruzione non condizionata non restituisce più un output rumoroso con le impostazioni fornite.