Diffusers documentation
LMSDiscreteScheduler
You are viewing main version, which requires installation from source. If you'd like
regular pip install, checkout the latest stable version (v0.39.0).
LMSDiscreteScheduler
LMSDiscreteScheduler is a linear multistep scheduler for discrete beta schedules. The scheduler is ported from and created by Katherine Crowson, and the original implementation can be found at crowsonkb/k-diffusion.
LMSDiscreteScheduler
LMSDiscreteSchedulerOutput
class diffusers.schedulers.scheduling_lms_discrete.LMSDiscreteSchedulerOutput
< source >( prev_sample: Tensorpred_original_sample: typing.Optional[torch.Tensor] = None )
Parameters
- prev_sample (
torch.Tensorof shape(batch_size, num_channels, height, width)for images) — Computed sample(x_{t-1})of previous timestep.prev_sampleshould be used as next model input in the denoising loop. - pred_original_sample (
torch.Tensorof 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_samplecan be used to preview progress or for guidance.
Output class for the scheduler’s step function output.