modelzoo.vision.pytorch.dit.samplers.DDIMSampler.DDIMSamplerOutput#

class modelzoo.vision.pytorch.dit.samplers.DDIMSampler.DDIMSamplerOutput[source]#

Bases: object

Output class for the scheduler’s step function output.

Parameters
  • prev_sample (torch.FloatTensor of shape (batch_size, num_channels, height, width) for images) – Computed sample (x_{t-1}) of previous timestep. prev_sample should be used as next model input in the denoising loop.

  • pred_original_sample (torch.FloatTensor of shape (batch_size, num_channels, height, width) for images) – The predicted denoised sample (x_{0}) based on the model output from the current timestep. pred_original_sample can be used to preview progress or for guidance.

Methods

Attributes

pred_original_sample

prev_sample

__init__(prev_sample: torch.FloatTensor, pred_original_sample: Optional[torch.FloatTensor] = None) None#