Heun scheduler inspired by Karras et. al paper
Overview
Algorithm 1 of Karras et. al. Scheduler ported from @crowsonkb’s https://github.com/crowsonkb/k-diffusion library:
All credit for making this scheduler work goes to Katherine Crowson
HeunDiscreteScheduler
class diffusers.HeunDiscreteScheduler
< source >( num_train_timesteps: int = 1000 beta_start: float = 0.00085 beta_end: float = 0.012 beta_schedule: str = 'linear' trained_betas: typing.Union[numpy.ndarray, typing.List[float], NoneType] = None prediction_type: str = 'epsilon' use_karras_sigmas: typing.Optional[bool] = False )
Parameters
-
num_train_timesteps (
int
) — number of diffusion steps used to train the model. beta_start (float
): the -
starting
beta
value of inference. beta_end (float
) — the finalbeta
value. beta_schedule (str
): the beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose fromlinear
orscaled_linear
. -
trained_betas (
np.ndarray
, optional) — option to pass an array of betas directly to the constructor to bypassbeta_start
,beta_end
etc. options to clip the variance used when adding noise to the denoised sample. Choose fromfixed_small
,fixed_small_log
,fixed_large
,fixed_large_log
,learned
orlearned_range
. -
prediction_type (
str
, defaultepsilon
, optional) — prediction type of the scheduler function, one ofepsilon
(predicting the noise of the diffusion process),sample
(directly predicting the noisy sample) or
v_prediction` (see section 2.4 https://imagen.research.google/video/paper.pdf). -
use_karras_sigmas (
bool
, optional, defaults toFalse
) — This parameter controls whether to use Karras sigmas (Karras et al. (2022) scheme) for step sizes in the noise schedule during the sampling process. If True, the sigmas will be determined according to a sequence of noise levels {σi} as defined in Equation (5) of the paper https://arxiv.org/pdf/2206.00364.pdf.
Implements Algorithm 2 (Heun steps) from Karras et al. (2022). for discrete beta schedules. Based on the original k-diffusion implementation by Katherine Crowson: https://github.com/crowsonkb/k-diffusion/blob/481677d114f6ea445aa009cf5bd7a9cdee909e47/k_diffusion/sampling.py#L90
~ConfigMixin takes care of storing all config attributes that are passed in the scheduler’s __init__
function, such as num_train_timesteps
. They can be accessed via scheduler.config.num_train_timesteps
.
SchedulerMixin provides general loading and saving functionality via the SchedulerMixin.save_pretrained() and
from_pretrained() functions.
scale_model_input
< source >(
sample: FloatTensor
timestep: typing.Union[float, torch.FloatTensor]
)
→
torch.FloatTensor
set_timesteps
< source >( num_inference_steps: int device: typing.Union[str, torch.device] = None num_train_timesteps: typing.Optional[int] = None )
Sets the timesteps used for the diffusion chain. Supporting function to be run before inference.
step
< source >(
model_output: typing.Union[torch.FloatTensor, numpy.ndarray]
timestep: typing.Union[float, torch.FloatTensor]
sample: typing.Union[torch.FloatTensor, numpy.ndarray]
return_dict: bool = True
)
→
SchedulerOutput or tuple
Parameters
- Predict the sample at the previous timestep by reversing the SDE. Core function to propagate the diffusion —
-
process from the learned model outputs (most often the predicted noise). —
model_output (
torch.FloatTensor
ornp.ndarray
): direct output from learned diffusion model. timestep (int
): current discrete timestep in the diffusion chain. sample (torch.FloatTensor
ornp.ndarray
): current instance of sample being created by diffusion process. return_dict (bool
): option for returning tuple rather than SchedulerOutput class
Returns
SchedulerOutput or tuple
SchedulerOutput if return_dict
is True, otherwise a tuple
. When
returning a tuple, the first element is the sample tensor.