DPMSolverSinglestepScheduler
译者:片刻小哥哥
项目地址:https://huggingface.apachecn.org/docs/diffusers/api/schedulers/singlestep_dpm_solver
原始地址:https://huggingface.co/docs/diffusers/api/schedulers/singlestep_dpm_solver
DPMSolverSinglestepScheduler
is a single step scheduler from
DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
and
DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
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 LuChengTHU/dpm-solver .
Tips
It is recommended to set
solver_order
to 2 for guide sampling, and
solver_order=3
for unconditional sampling.
Dynamic thresholding from Imagen (
https://huggingface.co/papers/2205.11487
) 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.
DPMSolverSinglestepScheduler
class
diffusers.
DPMSolverSinglestepScheduler
[<
source
](https://github.com/huggingface/diffusers/blob/v0.23.0/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L76)
(
num_train_timesteps
: int = 1000
beta_start
: float = 0.0001
beta_end
: float = 0.02
beta_schedule
: str = 'linear'
trained_betas
: typing.Optional[numpy.ndarray] = None
solver_order
: int = 2
prediction_type
: str = 'epsilon'
thresholding
: bool = False
dynamic_thresholding_ratio
: float = 0.995
sample_max_value
: float = 1.0
algorithm_type
: str = 'dpmsolver++'
solver_type
: str = 'midpoint'
lower_order_final
: bool = True
use_karras_sigmas
: typing.Optional[bool] = False
lambda_min_clipped
: float = -inf
variance_type
: typing.Optional[str] = None
)
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
,scaled_linear
, orsquaredcos_cap_v2
. - trained_betas
(
np.ndarray
, optional ) — Pass an array of betas directly to the constructor to bypassbeta_start
andbeta_end
. - solver_order
(
int
, defaults to 2) — The DPMSolver order which can be1
or2
or3
. It is recommended to usesolver_order=2
for guided sampling, andsolver_order=3
for unconditional sampling. - 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). - thresholding
(
bool
, defaults toFalse
) — Whether to use the “dynamic thresholding” method. This is unsuitable for latent-space diffusion models such as Stable Diffusion. - dynamic_thresholding_ratio
(
float
, defaults to 0.995) — The ratio for the dynamic thresholding method. Valid only whenthresholding=True
. - sample_max_value
(
float
, defaults to 1.0) — The threshold value for dynamic thresholding. Valid only whenthresholding=True
andalgorithm_type="dpmsolver++"
. - algorithm_type
(
str
, defaults todpmsolver++
) — Algorithm type for the solver; can bedpmsolver
,dpmsolver++
,sde-dpmsolver
orsde-dpmsolver++
. Thedpmsolver
type implements the algorithms in the DPMSolver paper, and thedpmsolver++
type implements the algorithms in the DPMSolver++ paper. It is recommended to usedpmsolver++
orsde-dpmsolver++
withsolver_order=2
for guided sampling like in Stable Diffusion. - solver_type
(
str
, defaults tomidpoint
) — Solver type for the second-order solver; can bemidpoint
orheun
. The solver type slightly affects the sample quality, especially for a small number of steps. It is recommended to usemidpoint
solvers. - lower_order_final
(
bool
, defaults toTrue
) — 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 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}. - lambda_min_clipped
(
float
, defaults to-inf
) — Clipping threshold for the minimum value oflambda(t)
for numerical stability. This is critical for the cosine (squaredcos_cap_v2
) noise schedule. - variance_type
(
str
, optional ) — Set to “learned” or “learned_range” for diffusion models that predict variance. If set, the model’s output contains the predicted Gaussian variance.
DPMSolverSinglestepScheduler
is a fast dedicated high-order solver for diffusion ODEs.
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.
convert_model_output
[<
source
](https://github.com/huggingface/diffusers/blob/v0.23.0/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L372)
(
model_output
: FloatTensor
*args
sample
: FloatTensor = None
**kwargs
)
→
export const metadata = 'undefined';
torch.FloatTensor
Parameters
- model_output
(
torch.FloatTensor
) — The direct output from the learned diffusion model. - sample
(
torch.FloatTensor
) — A current instance of a sample created by the diffusion process.
Returns
export const metadata = 'undefined';
torch.FloatTensor
export const metadata = 'undefined';
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
[<
source
](https://github.com/huggingface/diffusers/blob/v0.23.0/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L461)
(
model_output
: FloatTensor
*args
sample
: FloatTensor = None
**kwargs
)
→
export const metadata = 'undefined';
torch.FloatTensor
Parameters
- model_output
(
torch.FloatTensor
) — The direct output from the learned diffusion model. - timestep
(
int
) — The current discrete timestep in the diffusion chain. - prev_timestep
(
int
) — The previous discrete timestep in the diffusion chain. - sample
(
torch.FloatTensor
) — A current instance of a sample created by the diffusion process.
Returns
export const metadata = 'undefined';
torch.FloatTensor
export const metadata = 'undefined';
The sample tensor at the previous timestep.
One step for the first-order DPMSolver (equivalent to DDIM).
get_order_list
[<
source
](https://github.com/huggingface/diffusers/blob/v0.23.0/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L202)
(
num_inference_steps
: int
)
Parameters
- num_inference_steps
(
int
) — 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
[<
source
](https://github.com/huggingface/diffusers/blob/v0.23.0/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L857)
(
sample
: FloatTensor
*args
**kwargs
)
→
export const metadata = 'undefined';
torch.FloatTensor
Parameters
- sample
(
torch.FloatTensor
) — The input sample.
Returns
export const metadata = 'undefined';
torch.FloatTensor
export const metadata = 'undefined';
A scaled input sample.
Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep.
set_timesteps
[<
source
](https://github.com/huggingface/diffusers/blob/v0.23.0/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L243)
(
num_inference_steps
: int
device
: typing.Union[str, torch.device] = 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.
Sets the discrete timesteps used for the diffusion chain (to be run before inference).
singlestep_dpm_solver_second_order_update
[<
source
](https://github.com/huggingface/diffusers/blob/v0.23.0/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L517)
(
model_output_list
: typing.List[torch.FloatTensor]
*args
sample
: FloatTensor = None
**kwargs
)
→
export const metadata = 'undefined';
torch.FloatTensor
Parameters
- model_output_list
(
List[torch.FloatTensor]
) — The direct outputs from learned diffusion model at current and latter timesteps. - timestep
(
int
) — The current and latter discrete timestep in the diffusion chain. - prev_timestep
(
int
) — The previous discrete timestep in the diffusion chain. - sample
(
torch.FloatTensor
) — A current instance of a sample created by the diffusion process.
Returns
export const metadata = 'undefined';
torch.FloatTensor
export const metadata = 'undefined';
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
[<
source
](https://github.com/huggingface/diffusers/blob/v0.23.0/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L611)
(
model_output_list
: typing.List[torch.FloatTensor]
*args
sample
: FloatTensor = None
**kwargs
)
→
export const metadata = 'undefined';
torch.FloatTensor
Parameters
- model_output_list
(
List[torch.FloatTensor]
) — The direct outputs from learned diffusion model at current and latter timesteps. - timestep
(
int
) — The current and latter discrete timestep in the diffusion chain. - prev_timestep
(
int
) — The previous discrete timestep in the diffusion chain. - sample
(
torch.FloatTensor
) — A current instance of a sample created by diffusion process.
Returns
export const metadata = 'undefined';
torch.FloatTensor
export const metadata = 'undefined';
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
[<
source
](https://github.com/huggingface/diffusers/blob/v0.23.0/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L715)
(
model_output_list
: typing.List[torch.FloatTensor]
*args
sample
: FloatTensor = None
order
: int = None
**kwargs
)
→
export const metadata = 'undefined';
torch.FloatTensor
Parameters
- model_output_list
(
List[torch.FloatTensor]
) — The direct outputs from learned diffusion model at current and latter timesteps. - timestep
(
int
) — The current and latter discrete timestep in the diffusion chain. - prev_timestep
(
int
) — The previous discrete timestep in the diffusion chain. - sample
(
torch.FloatTensor
) — A current instance of a sample created by diffusion process. - order
(
int
) — The solver order at this step.
Returns
export const metadata = 'undefined';
torch.FloatTensor
export const metadata = 'undefined';
The sample tensor at the previous timestep.
One step for the singlestep DPMSolver.
step
[<
source
](https://github.com/huggingface/diffusers/blob/v0.23.0/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py#L796)
(
model_output
: FloatTensor
timestep
: int
sample
: FloatTensor
return_dict
: bool = True
)
→
export const metadata = 'undefined';
SchedulerOutput
or
tuple
Parameters
- model_output
(
torch.FloatTensor
) — The direct output from learned diffusion model. - timestep
(
int
) — 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 ortuple
.
Returns
export const metadata = 'undefined';
SchedulerOutput
or
tuple
export const metadata = 'undefined';
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 sample with the singlestep DPMSolver.
SchedulerOutput
class
diffusers.schedulers.scheduling_utils.
SchedulerOutput
[<
source
](https://github.com/huggingface/diffusers/blob/v0.23.0/src/diffusers/schedulers/scheduling_utils.py#L50)
(
prev_sample
: FloatTensor
)
Parameters
- prev_sample
(
torch.FloatTensor
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.
Base class for the output of a scheduler’s
step
function.