EulerDiscreteScheduler
The Euler scheduler (Algorithm 2) is from the Elucidating the Design Space of Diffusion-Based Generative Models paper by Karras et al. This is a fast scheduler which can often generate good outputs in 20-30 steps. The scheduler is based on the original k-diffusion implementation by Katherine Crowson.
EulerDiscreteScheduler
class diffusers.EulerDiscreteScheduler
< source >( num_train_timesteps: int = 1000 beta_start: float = 0.0001 beta_end: float = 0.02 beta_schedule: str = 'linear' trained_betas: Union = None prediction_type: str = 'epsilon' interpolation_type: str = 'linear' use_karras_sigmas: Optional = False use_exponential_sigmas: Optional = False use_beta_sigmas: Optional = False sigma_min: Optional = None sigma_max: Optional = None timestep_spacing: str = 'linspace' timestep_type: str = 'discrete' steps_offset: int = 0 rescale_betas_zero_snr: bool = False final_sigmas_type: str = 'zero' )
Parameters
- num_train_timesteps (
int
, defaults to 1000) — The number of diffusion steps to train the model. - beta_start (
float
, defaults to 0.0001) — The startingbeta
value of inference. - beta_end (
float
, defaults to 0.02) — The finalbeta
value. - 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 fromlinear
orscaled_linear
. - trained_betas (
np.ndarray
, optional) — Pass an array of betas directly to the constructor to bypassbeta_start
andbeta_end
. - 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) or
v_prediction` (see section 2.4 of Imagen Video paper). - interpolation_type(
str
, defaults to"linear"
, optional) — The interpolation type to compute intermediate sigmas for the scheduler denoising steps. Should be on of"linear"
or"log_linear"
. - 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}. - use_exponential_sigmas (
bool
, optional, defaults toFalse
) — Whether to use exponential sigmas for step sizes in the noise schedule during the sampling process. - use_beta_sigmas (
bool
, optional, defaults toFalse
) — Whether to use beta sigmas for step sizes in the noise schedule during the sampling process. Refer to Beta Sampling is All You Need for more information. - 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. - rescale_betas_zero_snr (
bool
, defaults toFalse
) — Whether to rescale the betas to have zero terminal SNR. This enables the model to generate very bright and dark samples instead of limiting it to samples with medium brightness. Loosely related to--offset_noise
. - final_sigmas_type (
str
, defaults to"zero"
) — The finalsigma
value for the noise schedule during the sampling process. If"sigma_min"
, the final sigma is the same as the last sigma in the training schedule. Ifzero
, the final sigma is set to 0.
Euler scheduler.
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: Tensor timestep: Union ) → torch.Tensor
Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
current timestep. Scales the denoising model input by (sigma**2 + 1) ** 0.5
to match the Euler algorithm.
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 = None device: Union = None timesteps: Optional = None sigmas: Optional = None )
Parameters
- num_inference_steps (
int
) — The number of diffusion steps used when generating samples with a pre-trained model. - device (
str
ortorch.device
, optional) — The device to which the timesteps should be moved to. IfNone
, the timesteps are not moved. - timesteps (
List[int]
, optional) — Custom timesteps used to support arbitrary timesteps schedule. IfNone
, timesteps will be generated based on thetimestep_spacing
attribute. Iftimesteps
is passed,num_inference_steps
andsigmas
must beNone
, andtimestep_spacing
attribute will be ignored. - sigmas (
List[float]
, optional) — Custom sigmas used to support arbitrary timesteps schedule schedule. IfNone
, timesteps and sigmas will be generated based on the relevant scheduler attributes. Ifsigmas
is passed,num_inference_steps
andtimesteps
must beNone
, and the timesteps will be generated based on the custom sigmas schedule.
Sets the discrete timesteps used for the diffusion chain (to be run before inference).
step
< source >( model_output: Tensor timestep: Union sample: Tensor s_churn: float = 0.0 s_tmin: float = 0.0 s_tmax: float = inf s_noise: float = 1.0 generator: Optional = None return_dict: bool = True ) → EulerDiscreteSchedulerOutput or tuple
Parameters
- model_output (
torch.Tensor
) — The direct output from learned diffusion model. - timestep (
float
) — The current discrete timestep in the diffusion chain. - sample (
torch.Tensor
) — A current instance of a sample created by the diffusion process. - s_churn (
float
) — - s_tmin (
float
) — - s_tmax (
float
) — - s_noise (
float
, defaults to 1.0) — Scaling factor for noise added to the sample. - generator (
torch.Generator
, optional) — A random number generator. - return_dict (
bool
) — Whether or not to return a EulerDiscreteSchedulerOutput or tuple.
Returns
EulerDiscreteSchedulerOutput or tuple
If return_dict is True
, EulerDiscreteSchedulerOutput 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).
EulerDiscreteSchedulerOutput
class diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteSchedulerOutput
< source >( prev_sample: Tensor pred_original_sample: Optional = None )
Parameters
- prev_sample (
torch.Tensor
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.Tensor
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.
Output class for the scheduler’s step
function output.