KDPM2DiscreteScheduler
The KDPM2DiscreteScheduler is inspired by the Elucidating the Design Space of Diffusion-Based Generative Models paper, and the scheduler is ported from and created by Katherine Crowson.
The original codebase can be found at crowsonkb/k-diffusion.
KDPM2DiscreteScheduler
class diffusers.KDPM2DiscreteScheduler
< source >( num_train_timesteps: int = 1000 beta_start: float = 0.00085 beta_end: float = 0.012 beta_schedule: str = 'linear' trained_betas: Union = None use_karras_sigmas: Optional = False prediction_type: str = 'epsilon' timestep_spacing: str = 'linspace' steps_offset: int = 0 )
Parameters
- num_train_timesteps (
int, defaults to 1000) — The number of diffusion steps to train the model. - beta_start (
float, defaults to 0.00085) — The startingbetavalue of inference. - beta_end (
float, defaults to 0.012) — The finalbetavalue. - beta_schedule (
str, defaults to"linear") — The beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose fromlinearorscaled_linear. - trained_betas (
np.ndarray, optional) — Pass an array of betas directly to the constructor to bypassbeta_startandbeta_end. - use_karras_sigmas (
bool, optional, defaults toFalse) — Whether to use Karras sigmas for step sizes in the noise schedule during the sampling process. IfTrue, the sigmas are determined according to a sequence of noise levels {σi}. - prediction_type (
str, defaults toepsilon, optional) — Prediction type of the scheduler function; can beepsilon(predicts the noise of the diffusion process),sample(directly predicts the noisy sample) orv_prediction` (see section 2.4 of Imagen Video paper). - timestep_spacing (
str, defaults to"linspace") — The way the timesteps should be scaled. Refer to Table 2 of the Common Diffusion Noise Schedules and Sample Steps are Flawed for more information. - steps_offset (
int, defaults to 0) — An offset added to the inference steps, as required by some model families.
KDPM2DiscreteScheduler is inspired by the DPMSolver2 and Algorithm 2 from the Elucidating the Design Space of Diffusion-Based Generative Models paper.
This model inherits from SchedulerMixin and ConfigMixin. Check the superclass documentation for the generic methods the library implements for all schedulers such as loading and saving.
scale_model_input
< source >( sample: FloatTensor timestep: Union ) → torch.FloatTensor
Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep.
set_begin_index
< source >( begin_index: int = 0 )
Sets the begin index for the scheduler. This function should be run from pipeline before the inference.
set_timesteps
< source >( num_inference_steps: int device: Union = None num_train_timesteps: Optional = None )
Sets the discrete timesteps used for the diffusion chain (to be run before inference).
step
< source >( model_output: Union timestep: Union sample: Union return_dict: bool = True ) → SchedulerOutput or tuple
Parameters
- model_output (
torch.FloatTensor) — The direct output from learned diffusion model. - timestep (
float) — The current discrete timestep in the diffusion chain. - sample (
torch.FloatTensor) — A current instance of a sample created by the diffusion process. - return_dict (
bool) — Whether or not to return a SchedulerOutput or tuple.
Returns
SchedulerOutput or tuple
If return_dict is True, SchedulerOutput is returned, otherwise a
tuple is returned where the first element is the sample tensor.
Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion process from the learned model outputs (most often the predicted noise).
SchedulerOutput
class diffusers.schedulers.scheduling_utils.SchedulerOutput
< source >( prev_sample: FloatTensor )
Base class for the output of a scheduler’s step function.