DPMSolverSinglestepScheduler
Last updated
Last updated
DPMSolverSinglestepScheduler is a single step scheduler from and by Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu.
DPMSolver (and the improved version DPMSolver++) is a fast dedicated high-order solver for diffusion ODEs with convergence order guarantee. Empirically, DPMSolver sampling with only 20 steps can generate high-quality samples, and it can generate quite good samples even in 10 steps.
The original implementation can be found at .
It is recommended to set solver_order to 2 for guide sampling, and solver_order=3 for unconditional sampling.
Dynamic thresholding from Imagen () is supported, and for pixel-space diffusion models, you can set both algorithm_type="dpmsolver++" and thresholding=True to use dynamic thresholding. This thresholding method is unsuitable for latent-space diffusion models such as Stable Diffusion.
( num_train_timesteps: int = 1000beta_start: float = 0.0001beta_end: float = 0.02beta_schedule: str = 'linear'trained_betas: typing.Optional[numpy.ndarray] = Nonesolver_order: int = 2prediction_type: str = 'epsilon'thresholding: bool = Falsedynamic_thresholding_ratio: float = 0.995sample_max_value: float = 1.0algorithm_type: str = 'dpmsolver++'solver_type: str = 'midpoint'lower_order_final: bool = Trueuse_karras_sigmas: typing.Optional[bool] = Falselambda_min_clipped: float = -infvariance_type: typing.Optional[str] = None )
Parameters
num_train_timesteps (int, defaults to 1000) β The number of diffusion steps to train the model.
beta_start (float, defaults to 0.0001) β The starting beta value of inference.
beta_end (float, defaults to 0.02) β The final beta value.
beta_schedule (str, defaults to "linear") β The beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from linear, scaled_linear, or squaredcos_cap_v2.
trained_betas (np.ndarray, optional) β Pass an array of betas directly to the constructor to bypass beta_start and beta_end.
solver_order (int, defaults to 2) β The DPMSolver order which can be 1 or 2 or 3. It is recommended to use solver_order=2 for guided sampling, and solver_order=3 for unconditional sampling.
prediction_type (str, defaults to epsilon, optional) β Prediction type of the scheduler function; can be epsilon (predicts the noise of the diffusion process), sample (directly predicts the noisy sample) or v_prediction` (see section 2.4 of paper).
thresholding (bool, defaults to False) β Whether to use the βdynamic thresholdingβ method. This is unsuitable for latent-space diffusion models such as Stable Diffusion.
dynamic_thresholding_ratio (float, defaults to 0.995) β The ratio for the dynamic thresholding method. Valid only when thresholding=True.
sample_max_value (float, defaults to 1.0) β The threshold value for dynamic thresholding. Valid only when thresholding=True and algorithm_type="dpmsolver++".
algorithm_type (str, defaults to dpmsolver++) β Algorithm type for the solver; can be dpmsolver, dpmsolver++, sde-dpmsolver or sde-dpmsolver++. The dpmsolver type implements the algorithms in the paper, and the dpmsolver++ type implements the algorithms in the paper. It is recommended to use dpmsolver++ or sde-dpmsolver++ with solver_order=2 for guided sampling like in Stable Diffusion.
solver_type (str, defaults to midpoint) β Solver type for the second-order solver; can be midpoint or heun. The solver type slightly affects the sample quality, especially for a small number of steps. It is recommended to use midpoint solvers.
lower_order_final (bool, defaults to True) β Whether to use lower-order solvers in the final steps. Only valid for < 15 inference steps. This can stabilize the sampling of DPMSolver for steps < 15, especially for steps <= 10.
use_karras_sigmas (bool, optional, defaults to False) β Whether to use Karras sigmas for step sizes in the noise schedule during the sampling process. If True, the sigmas are determined according to a sequence of noise levels {Οi}.
lambda_min_clipped (float, defaults to -inf) β Clipping threshold for the minimum value of lambda(t) for numerical stability. This is critical for the cosine (squaredcos_cap_v2) noise schedule.
variance_type (str, optional) β Set to βlearnedβ or βlearned_rangeβ for diffusion models that predict variance. If set, the modelβs output contains the predicted Gaussian variance.
DPMSolverSinglestepScheduler is a fast dedicated high-order solver for diffusion ODEs.
convert_model_output
( model_output: FloatTensortimestep: intsample: FloatTensor ) β torch.FloatTensor
Parameters
model_output (torch.FloatTensor) β The direct output from the learned diffusion model.
timestep (int) β The current discrete timestep in the diffusion chain.
sample (torch.FloatTensor) β A current instance of a sample created by the diffusion process.
Returns
torch.FloatTensor
The converted model output.
Convert the model output to the corresponding type the DPMSolver/DPMSolver++ algorithm needs. DPM-Solver is designed to discretize an integral of the noise prediction model, and DPM-Solver++ is designed to discretize an integral of the data prediction model.
The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both noise prediction and data prediction models.
dpm_solver_first_order_update
( model_output: FloatTensortimestep: intprev_timestep: intsample: FloatTensor ) β torch.FloatTensor
Parameters
model_output (torch.FloatTensor) β The direct output from the learned diffusion model.
timestep (int) β The current discrete timestep in the diffusion chain.
prev_timestep (int) β The previous discrete timestep in the diffusion chain.
sample (torch.FloatTensor) β A current instance of a sample created by the diffusion process.
Returns
torch.FloatTensor
The sample tensor at the previous timestep.
One step for the first-order DPMSolver (equivalent to DDIM).
get_order_list
( num_inference_steps: int )
Parameters
num_inference_steps (int) β The number of diffusion steps used when generating samples with a pre-trained model.
Computes the solver order at each time step.
scale_model_input
( sample: FloatTensor*args**kwargs ) β torch.FloatTensor
Parameters
sample (torch.FloatTensor) β The input sample.
Returns
torch.FloatTensor
A scaled input sample.
Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep.
set_timesteps
( num_inference_steps: intdevice: typing.Union[str, torch.device] = None )
Parameters
num_inference_steps (int) β The number of diffusion steps used when generating samples with a pre-trained model.
device (str or torch.device, optional) β The device to which the timesteps should be moved to. If None, the timesteps are not moved.
Sets the discrete timesteps used for the diffusion chain (to be run before inference).
singlestep_dpm_solver_second_order_update
( model_output_list: typing.List[torch.FloatTensor]timestep_list: typing.List[int]prev_timestep: intsample: FloatTensor ) β torch.FloatTensor
Parameters
model_output_list (List[torch.FloatTensor]) β The direct outputs from learned diffusion model at current and latter timesteps.
timestep (int) β The current and latter discrete timestep in the diffusion chain.
prev_timestep (int) β The previous discrete timestep in the diffusion chain.
sample (torch.FloatTensor) β A current instance of a sample created by the diffusion process.
Returns
torch.FloatTensor
The sample tensor at the previous timestep.
One step for the second-order singlestep DPMSolver that computes the solution at time prev_timestep from the time timestep_list[-2].
singlestep_dpm_solver_third_order_update
( model_output_list: typing.List[torch.FloatTensor]timestep_list: typing.List[int]prev_timestep: intsample: FloatTensor ) β torch.FloatTensor
Parameters
model_output_list (List[torch.FloatTensor]) β The direct outputs from learned diffusion model at current and latter timesteps.
timestep (int) β The current and latter discrete timestep in the diffusion chain.
prev_timestep (int) β The previous discrete timestep in the diffusion chain.
sample (torch.FloatTensor) β A current instance of a sample created by diffusion process.
Returns
torch.FloatTensor
The sample tensor at the previous timestep.
One step for the third-order singlestep DPMSolver that computes the solution at time prev_timestep from the time timestep_list[-3].
singlestep_dpm_solver_update
( model_output_list: typing.List[torch.FloatTensor]timestep_list: typing.List[int]prev_timestep: intsample: FloatTensororder: int ) β torch.FloatTensor
Parameters
model_output_list (List[torch.FloatTensor]) β The direct outputs from learned diffusion model at current and latter timesteps.
timestep (int) β The current and latter discrete timestep in the diffusion chain.
prev_timestep (int) β The previous discrete timestep in the diffusion chain.
sample (torch.FloatTensor) β A current instance of a sample created by diffusion process.
order (int) β The solver order at this step.
Returns
torch.FloatTensor
The sample tensor at the previous timestep.
One step for the singlestep DPMSolver.
step
Parameters
model_output (torch.FloatTensor) β The direct output from learned diffusion model.
timestep (int) β The current discrete timestep in the diffusion chain.
sample (torch.FloatTensor) β A current instance of a sample created by the diffusion process.
Returns
Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with the singlestep DPMSolver.
( prev_sample: FloatTensor )
Parameters
prev_sample (torch.FloatTensor of shape (batch_size, num_channels, height, width) for images) β Computed sample (x_{t-1}) of previous timestep. prev_sample should be used as next model input in the denoising loop.
Base class for the output of a schedulerβs step function.
This model inherits from and . Check the superclass documentation for the generic methods the library implements for all schedulers such as loading and saving.
( model_output: FloatTensortimestep: intsample: FloatTensorreturn_dict: bool = True ) β or tuple
return_dict (bool) β Whether or not to return a or tuple.
or tuple
If return_dict is True, is returned, otherwise a tuple is returned where the first element is the sample tensor.