DPMSolverSinglestepScheduler

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 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.

mindone.diffusers.DPMSolverSinglestepScheduler

Bases: SchedulerMixin, ConfigMixin

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.

PARAMETER	DESCRIPTION
num_train_timesteps	The number of diffusion steps to train the model. TYPE: `int`, defaults to 1000 DEFAULT: 1000
beta_start	The starting beta value of inference. TYPE: `float`, defaults to 0.0001 DEFAULT: 0.0001
beta_end	The final beta value. TYPE: `float`, defaults to 0.02 DEFAULT: 0.02
beta_schedule	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. TYPE: `str`, defaults to `"linear"` DEFAULT: 'linear'
trained_betas	Pass an array of betas directly to the constructor to bypass beta_start and beta_end. TYPE: `np.ndarray`, *optional* DEFAULT: None
solver_order	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. TYPE: `int`, defaults to 2 DEFAULT: 2
prediction_type	Prediction type of the scheduler function; can be epsilon (predicts the noise of the diffusion process), sample (directly predicts the noisy sample) orv_prediction` (see section 2.4 of Imagen Video paper). TYPE: `str`, defaults to `epsilon`, *optional* DEFAULT: 'epsilon'
thresholding	Whether to use the "dynamic thresholding" method. This is unsuitable for latent-space diffusion models such as Stable Diffusion. TYPE: `bool`, defaults to `False` DEFAULT: False
dynamic_thresholding_ratio	The ratio for the dynamic thresholding method. Valid only when thresholding=True. TYPE: `float`, defaults to 0.995 DEFAULT: 0.995
sample_max_value	The threshold value for dynamic thresholding. Valid only when thresholding=True and algorithm_type="dpmsolver++". TYPE: `float`, defaults to 1.0 DEFAULT: 1.0
algorithm_type	Algorithm type for the solver; can be dpmsolver or dpmsolver++. The dpmsolver type implements the algorithms in the DPMSolver paper, and the dpmsolver++ type implements the algorithms in the DPMSolver++ paper. It is recommended to use dpmsolver++ or sde-dpmsolver++ with solver_order=2 for guided sampling like in Stable Diffusion. TYPE: `str`, defaults to `dpmsolver++` DEFAULT: 'dpmsolver++'
solver_type	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. TYPE: `str`, defaults to `midpoint` DEFAULT: 'midpoint'
lower_order_final	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. TYPE: `bool`, defaults to `True` DEFAULT: False
use_karras_sigmas	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 {σi}. TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False
final_sigmas_type	The final sigma 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. If zero, the final sigma is set to 0. TYPE: `str`, *optional*, defaults to `"zero"` DEFAULT: 'zero'
lambda_min_clipped	Clipping threshold for the minimum value of lambda(t) for numerical stability. This is critical for the cosine (squaredcos_cap_v2) noise schedule. TYPE: `float`, defaults to `-inf` DEFAULT: -float('inf')
variance_type	Set to "learned" or "learned_range" for diffusion models that predict variance. If set, the model's output contains the predicted Gaussian variance. TYPE: `str`, *optional* DEFAULT: None

Source code in mindone/diffusers/schedulers/scheduling_dpmsolver_singlestep.py

class DPMSolverSinglestepScheduler(SchedulerMixin, ConfigMixin):
    """
    `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.

    Args:
        num_train_timesteps (`int`, defaults to 1000):
            The number of diffusion steps to train the model.
        beta_start (`float`, defaults to 0.0001):
            The starting `beta` value of inference.
        beta_end (`float`, defaults to 0.02):
            The final `beta` 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 from
            `linear`, `scaled_linear`, or `squaredcos_cap_v2`.
        trained_betas (`np.ndarray`, *optional*):
            Pass an array of betas directly to the constructor to bypass `beta_start` and `beta_end`.
        solver_order (`int`, defaults to 2):
            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*):
            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 [Imagen
            Video](https://imagen.research.google/video/paper.pdf) paper).
        thresholding (`bool`, defaults to `False`):
            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 when `thresholding=True`.
        sample_max_value (`float`, defaults to 1.0):
            The threshold value for dynamic thresholding. Valid only when `thresholding=True` and
            `algorithm_type="dpmsolver++"`.
        algorithm_type (`str`, defaults to `dpmsolver++`):
            Algorithm type for the solver; can be `dpmsolver` or `dpmsolver++`. The `dpmsolver` type implements the
            algorithms in the [DPMSolver](https://huggingface.co/papers/2206.00927) paper, and the `dpmsolver++` type
            implements the algorithms in the [DPMSolver++](https://huggingface.co/papers/2211.01095) 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`):
            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`):
            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`):
            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 {σi}.
        final_sigmas_type (`str`, *optional*, defaults to `"zero"`):
            The final `sigma` 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. If `zero`, the final sigma is set to 0.
        lambda_min_clipped (`float`, defaults to `-inf`):
            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*):
            Set to "learned" or "learned_range" for diffusion models that predict variance. If set, the model's output
            contains the predicted Gaussian variance.
    """

    _compatibles = [e.name for e in KarrasDiffusionSchedulers]
    order = 1

    @register_to_config
    def __init__(
        self,
        num_train_timesteps: int = 1000,
        beta_start: float = 0.0001,
        beta_end: float = 0.02,
        beta_schedule: str = "linear",
        trained_betas: Optional[np.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 = False,
        use_karras_sigmas: Optional[bool] = False,
        final_sigmas_type: Optional[str] = "zero",  # "zero", "sigma_min"
        lambda_min_clipped: float = -float("inf"),
        variance_type: Optional[str] = None,
    ):
        if algorithm_type == "dpmsolver":
            deprecation_message = (
                "algorithm_type `dpmsolver` is deprecated and will be removed in a future version. "
                "Choose from `dpmsolver++` or `sde-dpmsolver++` instead"
            )
            deprecate("algorithm_types=dpmsolver", "1.0.0", deprecation_message)

        if trained_betas is not None:
            self.betas = ms.tensor(trained_betas, dtype=ms.float32)
        elif beta_schedule == "linear":
            self.betas = ms.tensor(np.linspace(beta_start, beta_end, num_train_timesteps), dtype=ms.float32)
        elif beta_schedule == "scaled_linear":
            # this schedule is very specific to the latent diffusion model.
            self.betas = (
                ms.tensor(np.linspace(beta_start**0.5, beta_end**0.5, num_train_timesteps), dtype=ms.float32) ** 2
            )
        elif beta_schedule == "squaredcos_cap_v2":
            # Glide cosine schedule
            self.betas = betas_for_alpha_bar(num_train_timesteps)
        else:
            raise NotImplementedError(f"{beta_schedule} is not implemented for {self.__class__}")

        self.alphas = 1.0 - self.betas
        self.alphas_cumprod = ops.cumprod(self.alphas, dim=0)
        # Currently we only support VP-type noise schedule
        self.alpha_t = ops.sqrt(self.alphas_cumprod)
        self.sigma_t = ops.sqrt(1 - self.alphas_cumprod)
        self.lambda_t = ops.log(self.alpha_t) - ops.log(self.sigma_t)
        self.sigmas = ((1 - self.alphas_cumprod) / self.alphas_cumprod) ** 0.5

        # standard deviation of the initial noise distribution
        self.init_noise_sigma = 1.0

        # settings for DPM-Solver
        if algorithm_type not in ["dpmsolver", "dpmsolver++", "sde-dpmsolver++"]:
            if algorithm_type == "deis":
                self.register_to_config(algorithm_type="dpmsolver++")
            else:
                raise NotImplementedError(f"{algorithm_type} is not implemented for {self.__class__}")
        if solver_type not in ["midpoint", "heun"]:
            if solver_type in ["logrho", "bh1", "bh2"]:
                self.register_to_config(solver_type="midpoint")
            else:
                raise NotImplementedError(f"{solver_type} is not implemented for {self.__class__}")

        if algorithm_type not in ["dpmsolver++", "sde-dpmsolver++"] and final_sigmas_type == "zero":
            raise ValueError(
                f"`final_sigmas_type` {final_sigmas_type} is not supported for `algorithm_type` {algorithm_type}. Please chooose `sigma_min` instead."
            )

        # setable values
        self.num_inference_steps = None
        timesteps = np.linspace(0, num_train_timesteps - 1, num_train_timesteps, dtype=np.float32)[::-1].copy()
        self.timesteps = ms.Tensor(timesteps)
        self.model_outputs = [None] * solver_order
        self.sample = None
        self.order_list = self.get_order_list(num_train_timesteps)
        self._step_index = None
        self._begin_index = None

    def get_order_list(self, num_inference_steps: int) -> List[int]:
        """
        Computes the solver order at each time step.

        Args:
            num_inference_steps (`int`):
                The number of diffusion steps used when generating samples with a pre-trained model.
        """
        steps = num_inference_steps
        order = self.config.solver_order
        if order > 3:
            raise ValueError("Order > 3 is not supported by this scheduler")
        if self.config.lower_order_final:
            if order == 3:
                if steps % 3 == 0:
                    orders = [1, 2, 3] * (steps // 3 - 1) + [1, 2] + [1]
                elif steps % 3 == 1:
                    orders = [1, 2, 3] * (steps // 3) + [1]
                else:
                    orders = [1, 2, 3] * (steps // 3) + [1, 2]
            elif order == 2:
                if steps % 2 == 0:
                    orders = [1, 2] * (steps // 2 - 1) + [1, 1]
                else:
                    orders = [1, 2] * (steps // 2) + [1]
            elif order == 1:
                orders = [1] * steps
        else:
            if order == 3:
                orders = [1, 2, 3] * (steps // 3)
            elif order == 2:
                orders = [1, 2] * (steps // 2)
            elif order == 1:
                orders = [1] * steps
        return orders

    @property
    def step_index(self):
        """
        The index counter for current timestep. It will increase 1 after each scheduler step.
        """
        return self._step_index

    @property
    def begin_index(self):
        """
        The index for the first timestep. It should be set from pipeline with `set_begin_index` method.
        """
        return self._begin_index

    # Copied from diffusers.schedulers.scheduling_dpmsolver_multistep.DPMSolverMultistepScheduler.set_begin_index
    def set_begin_index(self, begin_index: int = 0):
        """
        Sets the begin index for the scheduler. This function should be run from pipeline before the inference.

        Args:
            begin_index (`int`):
                The begin index for the scheduler.
        """
        self._begin_index = begin_index

    def set_timesteps(self, num_inference_steps: int = None, timesteps: Optional[List[int]] = None):
        """
        Sets the discrete timesteps used for the diffusion chain (to be run before inference).

        Args:
            num_inference_steps (`int`):
                The number of diffusion steps used when generating samples with a pre-trained model.
            timesteps (`List[int]`, *optional*):
                Custom timesteps used to support arbitrary spacing between timesteps. If `None`, then the default
                timestep spacing strategy of equal spacing between timesteps schedule is used. If `timesteps` is
                passed, `num_inference_steps` must be `None`.
        """
        if num_inference_steps is None and timesteps is None:
            raise ValueError("Must pass exactly one of  `num_inference_steps` or `timesteps`.")
        if num_inference_steps is not None and timesteps is not None:
            raise ValueError("Must pass exactly one of  `num_inference_steps` or `timesteps`.")
        if timesteps is not None and self.config.use_karras_sigmas:
            raise ValueError("Cannot use `timesteps` when `config.use_karras_sigmas=True`.")

        num_inference_steps = num_inference_steps or len(timesteps)
        self.num_inference_steps = num_inference_steps

        if timesteps is not None:
            timesteps = np.array(timesteps).astype(np.int64)
        else:
            # Clipping the minimum of all lambda(t) for numerical stability.
            # This is critical for cosine (squaredcos_cap_v2) noise schedule.
            clipped_idx = np.searchsorted(ops.flip(self.lambda_t, [0]).asnumpy(), self.config.lambda_min_clipped)
            timesteps = (
                np.linspace(0, self.config.num_train_timesteps - 1 - clipped_idx, num_inference_steps + 1)
                .round()[::-1][:-1]
                .copy()
                .astype(np.int64)
            )

        sigmas = (((1 - self.alphas_cumprod) / self.alphas_cumprod) ** 0.5).asnumpy()
        if self.config.use_karras_sigmas:
            log_sigmas = np.log(sigmas)
            sigmas = np.flip(sigmas).copy()
            sigmas = self._convert_to_karras(in_sigmas=sigmas, num_inference_steps=num_inference_steps)
            timesteps = np.array([self._sigma_to_t(sigma, log_sigmas) for sigma in sigmas]).round()
        else:
            sigmas = np.interp(timesteps, np.arange(0, len(sigmas)), sigmas)

        if self.config.final_sigmas_type == "sigma_min":
            sigma_last = ((1 - self.alphas_cumprod[0]) / self.alphas_cumprod[0]) ** 0.5
        elif self.config.final_sigmas_type == "zero":
            sigma_last = 0
        else:
            raise ValueError(
                f" `final_sigmas_type` must be one of `sigma_min` or `zero`, but got {self.config.final_sigmas_type}"
            )
        sigmas = np.concatenate([sigmas, [sigma_last]]).astype(np.float32)

        self.sigmas = ms.Tensor(sigmas)

        self.timesteps = ms.tensor(timesteps, dtype=ms.int64)
        self.model_outputs = [None] * self.config.solver_order
        self.sample = None

        if not self.config.lower_order_final and num_inference_steps % self.config.solver_order != 0:
            logger.warning(
                "Changing scheduler {self.config} to have `lower_order_final` set to True to handle uneven amount of inference steps. "
                "Please make sure to always use an even number of `num_inference steps when using `lower_order_final=False`."
            )
            self.register_to_config(lower_order_final=True)

        if not self.config.lower_order_final and self.config.final_sigmas_type == "zero":
            logger.warning(
                " `last_sigmas_type='zero'` is not supported for `lower_order_final=False`. "
                "Changing scheduler {self.config} to have `lower_order_final` set to True."
            )
            self.register_to_config(lower_order_final=True)

        self.order_list = self.get_order_list(num_inference_steps)

        # add an index counter for schedulers that allow duplicated timesteps
        self._step_index = None
        self._begin_index = None

    # Copied from diffusers.schedulers.scheduling_ddpm.DDPMScheduler._threshold_sample
    def _threshold_sample(self, sample: ms.Tensor) -> ms.Tensor:
        """
        "Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the
        prediction of x_0 at timestep t), and if s > 1, then we threshold xt0 to the range [-s, s] and then divide by
        s. Dynamic thresholding pushes saturated pixels (those near -1 and 1) inwards, thereby actively preventing
        pixels from saturation at each step. We find that dynamic thresholding results in significantly better
        photorealism as well as better image-text alignment, especially when using very large guidance weights."

        https://arxiv.org/abs/2205.11487
        """
        dtype = sample.dtype
        batch_size, channels, *remaining_dims = sample.shape

        if dtype not in (ms.float32, ms.float64):
            sample = sample.float()  # upcast for quantile calculation, and clamp not implemented for cpu half

        # Flatten sample for doing quantile calculation along each image
        sample = sample.reshape(batch_size, channels * np.prod(remaining_dims).item())

        abs_sample = sample.abs()  # "a certain percentile absolute pixel value"

        s = ms.Tensor.from_numpy(np.quantile(abs_sample.asnumpy(), self.config.dynamic_thresholding_ratio, axis=1))
        s = ops.clamp(
            s, min=1, max=self.config.sample_max_value
        )  # When clamped to min=1, equivalent to standard clipping to [-1, 1]
        s = s.unsqueeze(1)  # (batch_size, 1) because clamp will broadcast along dim=0
        sample = ops.clamp(sample, -s, s) / s  # "we threshold xt0 to the range [-s, s] and then divide by s"

        sample = sample.reshape(batch_size, channels, *remaining_dims)
        sample = sample.to(dtype)

        return sample

    # Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler._sigma_to_t
    def _sigma_to_t(self, sigma, log_sigmas):
        # get log sigma
        log_sigma = np.log(np.maximum(sigma, 1e-10))

        # get distribution
        dists = log_sigma - log_sigmas[:, np.newaxis]

        # get sigmas range
        low_idx = np.cumsum((dists >= 0), axis=0).argmax(axis=0).clip(max=log_sigmas.shape[0] - 2)
        high_idx = low_idx + 1

        low = log_sigmas[low_idx]
        high = log_sigmas[high_idx]

        # interpolate sigmas
        w = (low - log_sigma) / (low - high)
        w = np.clip(w, 0, 1)

        # transform interpolation to time range
        t = (1 - w) * low_idx + w * high_idx
        t = t.reshape(sigma.shape)
        return t

    # Copied from diffusers.schedulers.scheduling_dpmsolver_multistep.DPMSolverMultistepScheduler._sigma_to_alpha_sigma_t
    def _sigma_to_alpha_sigma_t(self, sigma):
        alpha_t = 1 / ((sigma**2 + 1) ** 0.5)
        sigma_t = sigma * alpha_t

        return alpha_t, sigma_t

    # Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler._convert_to_karras
    def _convert_to_karras(self, in_sigmas: ms.Tensor, num_inference_steps) -> ms.Tensor:
        """Constructs the noise schedule of Karras et al. (2022)."""

        # Hack to make sure that other schedulers which copy this function don't break
        # TODO: Add this logic to the other schedulers
        if hasattr(self.config, "sigma_min"):
            sigma_min = self.config.sigma_min
        else:
            sigma_min = None

        if hasattr(self.config, "sigma_max"):
            sigma_max = self.config.sigma_max
        else:
            sigma_max = None

        sigma_min = sigma_min if sigma_min is not None else in_sigmas[-1].item()
        sigma_max = sigma_max if sigma_max is not None else in_sigmas[0].item()

        rho = 7.0  # 7.0 is the value used in the paper
        ramp = np.linspace(0, 1, num_inference_steps)
        min_inv_rho = sigma_min ** (1 / rho)
        max_inv_rho = sigma_max ** (1 / rho)
        sigmas = (max_inv_rho + ramp * (min_inv_rho - max_inv_rho)) ** rho
        return sigmas

    def convert_model_output(
        self,
        model_output: ms.Tensor,
        *args,
        sample: ms.Tensor = None,
        **kwargs,
    ) -> ms.Tensor:
        """
        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.

        <Tip>

        The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both noise
        prediction and data prediction models.

        </Tip>

        Args:
            model_output (`ms.Tensor`):
                The direct output from the learned diffusion model.
            sample (`ms.Tensor`):
                A current instance of a sample created by the diffusion process.

        Returns:
            `ms.Tensor`:
                The converted model output.
        """
        timestep = args[0] if len(args) > 0 else kwargs.pop("timestep", None)
        sigmas = self.sigmas.to(dtype=sample.dtype)
        if sample is None:
            if len(args) > 1:
                sample = args[1]
            else:
                raise ValueError("missing `sample` as a required keyward argument")
        if timestep is not None:
            deprecate(
                "timesteps",
                "1.0.0",
                "Passing `timesteps` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
            )
        # DPM-Solver++ needs to solve an integral of the data prediction model.
        if self.config.algorithm_type in ["dpmsolver++", "sde-dpmsolver++"]:
            if self.config.prediction_type == "epsilon":
                # DPM-Solver and DPM-Solver++ only need the "mean" output.
                if self.config.variance_type in ["learned", "learned_range"]:
                    model_output = model_output[:, :3]
                sigma = sigmas[self.step_index]
                alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma)
                x0_pred = (sample - sigma_t * model_output) / alpha_t
            elif self.config.prediction_type == "sample":
                x0_pred = model_output
            elif self.config.prediction_type == "v_prediction":
                sigma = sigmas[self.step_index]
                alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma)
                x0_pred = alpha_t * sample - sigma_t * model_output
            else:
                raise ValueError(
                    f"prediction_type given as {self.config.prediction_type} must be one of `epsilon`, `sample`, or"
                    " `v_prediction` for the DPMSolverSinglestepScheduler."
                )

            if self.config.thresholding:
                x0_pred = self._threshold_sample(x0_pred)

            return x0_pred

        # DPM-Solver needs to solve an integral of the noise prediction model.
        elif self.config.algorithm_type == "dpmsolver":
            if self.config.prediction_type == "epsilon":
                # DPM-Solver and DPM-Solver++ only need the "mean" output.
                if self.config.variance_type in ["learned", "learned_range"]:
                    epsilon = model_output[:, :3]
                else:
                    epsilon = model_output
            elif self.config.prediction_type == "sample":
                sigma = sigmas[self.step_index]
                alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma)
                epsilon = (sample - alpha_t * model_output) / sigma_t
            elif self.config.prediction_type == "v_prediction":
                sigma = sigmas[self.step_index]
                alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma)
                epsilon = alpha_t * model_output + sigma_t * sample
            else:
                raise ValueError(
                    f"prediction_type given as {self.config.prediction_type} must be one of `epsilon`, `sample`, or"
                    " `v_prediction` for the DPMSolverSinglestepScheduler."
                )

            if self.config.thresholding:
                alpha_t, sigma_t = self.alpha_t[timestep], self.sigma_t[timestep]
                x0_pred = (sample - sigma_t * epsilon) / alpha_t
                x0_pred = self._threshold_sample(x0_pred)
                epsilon = (sample - alpha_t * x0_pred) / sigma_t

            return epsilon

    def dpm_solver_first_order_update(
        self,
        model_output: ms.Tensor,
        *args,
        sample: ms.Tensor = None,
        noise: Optional[ms.Tensor] = None,
        **kwargs,
    ) -> ms.Tensor:
        """
        One step for the first-order DPMSolver (equivalent to DDIM).

        Args:
            model_output (`ms.Tensor`):
                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 (`ms.Tensor`):
                A current instance of a sample created by the diffusion process.

        Returns:
            `ms.Tensor`:
                The sample tensor at the previous timestep.
        """
        timestep = args[0] if len(args) > 0 else kwargs.pop("timestep", None)
        prev_timestep = args[1] if len(args) > 1 else kwargs.pop("prev_timestep", None)
        sigmas = self.sigmas.to(dtype=sample.dtype)
        if sample is None:
            if len(args) > 2:
                sample = args[2]
            else:
                raise ValueError(" missing `sample` as a required keyward argument")
        if timestep is not None:
            deprecate(
                "timesteps",
                "1.0.0",
                "Passing `timesteps` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
            )

        if prev_timestep is not None:
            deprecate(
                "prev_timestep",
                "1.0.0",
                "Passing `prev_timestep` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
            )
        sigma_t, sigma_s = sigmas[self.step_index + 1], sigmas[self.step_index]
        alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma_t)
        alpha_s, sigma_s = self._sigma_to_alpha_sigma_t(sigma_s)
        lambda_t = ops.log(alpha_t) - ops.log(sigma_t)
        lambda_s = ops.log(alpha_s) - ops.log(sigma_s)
        h = lambda_t - lambda_s
        if self.config.algorithm_type == "dpmsolver++":
            x_t = (sigma_t / sigma_s) * sample - (alpha_t * (ops.exp(-h) - 1.0)) * model_output
        elif self.config.algorithm_type == "dpmsolver":
            x_t = (alpha_t / alpha_s) * sample - (sigma_t * (ops.exp(h) - 1.0)) * model_output
        elif self.config.algorithm_type == "sde-dpmsolver++":
            assert noise is not None
            x_t = (
                (sigma_t / sigma_s * ops.exp(-h)) * sample
                + (alpha_t * (1 - ops.exp(-2.0 * h))) * model_output
                + sigma_t * ops.sqrt(1.0 - ops.exp(-2 * h)) * noise
            )
        return x_t

    def singlestep_dpm_solver_second_order_update(
        self,
        model_output_list: List[ms.Tensor],
        *args,
        sample: ms.Tensor = None,
        noise: Optional[ms.Tensor] = None,
        **kwargs,
    ) -> ms.Tensor:
        """
        One step for the second-order singlestep DPMSolver that computes the solution at time `prev_timestep` from the
        time `timestep_list[-2]`.

        Args:
            model_output_list (`List[ms.Tensor]`):
                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 (`ms.Tensor`):
                A current instance of a sample created by the diffusion process.

        Returns:
            `ms.Tensor`:
                The sample tensor at the previous timestep.
        """
        timestep_list = args[0] if len(args) > 0 else kwargs.pop("timestep_list", None)
        prev_timestep = args[1] if len(args) > 1 else kwargs.pop("prev_timestep", None)
        sigmas = self.sigmas.to(dtype=sample.dtype)
        if sample is None:
            if len(args) > 2:
                sample = args[2]
            else:
                raise ValueError(" missing `sample` as a required keyward argument")
        if timestep_list is not None:
            deprecate(
                "timestep_list",
                "1.0.0",
                "Passing `timestep_list` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
            )

        if prev_timestep is not None:
            deprecate(
                "prev_timestep",
                "1.0.0",
                "Passing `prev_timestep` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
            )
        sigma_t, sigma_s0, sigma_s1 = (
            sigmas[self.step_index + 1],
            sigmas[self.step_index],
            sigmas[self.step_index - 1],
        )

        alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma_t)
        alpha_s0, sigma_s0 = self._sigma_to_alpha_sigma_t(sigma_s0)
        alpha_s1, sigma_s1 = self._sigma_to_alpha_sigma_t(sigma_s1)

        lambda_t = ops.log(alpha_t) - ops.log(sigma_t)
        lambda_s0 = ops.log(alpha_s0) - ops.log(sigma_s0)
        lambda_s1 = ops.log(alpha_s1) - ops.log(sigma_s1)

        m0, m1 = model_output_list[-1], model_output_list[-2]

        h, h_0 = lambda_t - lambda_s1, lambda_s0 - lambda_s1
        r0 = h_0 / h
        D0, D1 = m1, (1.0 / r0) * (m0 - m1)
        if self.config.algorithm_type == "dpmsolver++":
            # See https://arxiv.org/abs/2211.01095 for detailed derivations
            if self.config.solver_type == "midpoint":
                x_t = (
                    (sigma_t / sigma_s1) * sample
                    - (alpha_t * (ops.exp(-h) - 1.0)) * D0
                    - 0.5 * (alpha_t * (ops.exp(-h) - 1.0)) * D1
                )
            elif self.config.solver_type == "heun":
                x_t = (
                    (sigma_t / sigma_s1) * sample
                    - (alpha_t * (ops.exp(-h) - 1.0)) * D0
                    + (alpha_t * ((ops.exp(-h) - 1.0) / h + 1.0)) * D1
                )
        elif self.config.algorithm_type == "dpmsolver":
            # See https://arxiv.org/abs/2206.00927 for detailed derivations
            if self.config.solver_type == "midpoint":
                x_t = (
                    (alpha_t / alpha_s1) * sample
                    - (sigma_t * (ops.exp(h) - 1.0)) * D0
                    - 0.5 * (sigma_t * (ops.exp(h) - 1.0)) * D1
                )
            elif self.config.solver_type == "heun":
                x_t = (
                    (alpha_t / alpha_s1) * sample
                    - (sigma_t * (ops.exp(h) - 1.0)) * D0
                    - (sigma_t * ((ops.exp(h) - 1.0) / h - 1.0)) * D1
                )
        elif self.config.algorithm_type == "sde-dpmsolver++":
            assert noise is not None
            if self.config.solver_type == "midpoint":
                x_t = (
                    (sigma_t / sigma_s1 * ops.exp(-h)) * sample
                    + (alpha_t * (1 - ops.exp(-2.0 * h))) * D0
                    + 0.5 * (alpha_t * (1 - ops.exp(-2.0 * h))) * D1
                    + sigma_t * ops.sqrt(1.0 - ops.exp(-2 * h)) * noise
                )
            elif self.config.solver_type == "heun":
                x_t = (
                    (sigma_t / sigma_s1 * ops.exp(-h)) * sample
                    + (alpha_t * (1 - ops.exp(-2.0 * h))) * D0
                    + (alpha_t * ((1.0 - ops.exp(-2.0 * h)) / (-2.0 * h) + 1.0)) * D1
                    + sigma_t * ops.sqrt(1.0 - ops.exp(-2 * h)) * noise
                )
        return x_t

    def singlestep_dpm_solver_third_order_update(
        self,
        model_output_list: List[ms.Tensor],
        *args,
        sample: ms.Tensor = None,
        **kwargs,
    ) -> ms.Tensor:
        """
        One step for the third-order singlestep DPMSolver that computes the solution at time `prev_timestep` from the
        time `timestep_list[-3]`.

        Args:
            model_output_list (`List[ms.Tensor]`):
                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 (`ms.Tensor`):
                A current instance of a sample created by diffusion process.

        Returns:
            `ms.Tensor`:
                The sample tensor at the previous timestep.
        """

        timestep_list = args[0] if len(args) > 0 else kwargs.pop("timestep_list", None)
        prev_timestep = args[1] if len(args) > 1 else kwargs.pop("prev_timestep", None)
        sigmas = self.sigmas.to(dtype=sample.dtype)
        if sample is None:
            if len(args) > 2:
                sample = args[2]
            else:
                raise ValueError(" missing`sample` as a required keyward argument")
        if timestep_list is not None:
            deprecate(
                "timestep_list",
                "1.0.0",
                "Passing `timestep_list` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
            )

        if prev_timestep is not None:
            deprecate(
                "prev_timestep",
                "1.0.0",
                "Passing `prev_timestep` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
            )

        sigma_t, sigma_s0, sigma_s1, sigma_s2 = (
            sigmas[self.step_index + 1],
            sigmas[self.step_index],
            sigmas[self.step_index - 1],
            sigmas[self.step_index - 2],
        )

        alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma_t)
        alpha_s0, sigma_s0 = self._sigma_to_alpha_sigma_t(sigma_s0)
        alpha_s1, sigma_s1 = self._sigma_to_alpha_sigma_t(sigma_s1)
        alpha_s2, sigma_s2 = self._sigma_to_alpha_sigma_t(sigma_s2)

        lambda_t = ops.log(alpha_t) - ops.log(sigma_t)
        lambda_s0 = ops.log(alpha_s0) - ops.log(sigma_s0)
        lambda_s1 = ops.log(alpha_s1) - ops.log(sigma_s1)
        lambda_s2 = ops.log(alpha_s2) - ops.log(sigma_s2)

        m0, m1, m2 = model_output_list[-1], model_output_list[-2], model_output_list[-3]

        h, h_0, h_1 = lambda_t - lambda_s2, lambda_s0 - lambda_s2, lambda_s1 - lambda_s2
        r0, r1 = h_0 / h, h_1 / h
        D0 = m2
        D1_0, D1_1 = (1.0 / r1) * (m1 - m2), (1.0 / r0) * (m0 - m2)
        D1 = (r0 * D1_0 - r1 * D1_1) / (r0 - r1)
        D2 = 2.0 * (D1_1 - D1_0) / (r0 - r1)
        if self.config.algorithm_type == "dpmsolver++":
            # See https://arxiv.org/abs/2206.00927 for detailed derivations
            if self.config.solver_type == "midpoint":
                x_t = (
                    (sigma_t / sigma_s2) * sample
                    - (alpha_t * (ops.exp(-h) - 1.0)) * D0
                    + (alpha_t * ((ops.exp(-h) - 1.0) / h + 1.0)) * D1_1
                )
            elif self.config.solver_type == "heun":
                x_t = (
                    (sigma_t / sigma_s2) * sample
                    - (alpha_t * (ops.exp(-h) - 1.0)) * D0
                    + (alpha_t * ((ops.exp(-h) - 1.0) / h + 1.0)) * D1
                    - (alpha_t * ((ops.exp(-h) - 1.0 + h) / h**2 - 0.5)) * D2
                )
        elif self.config.algorithm_type == "dpmsolver":
            # See https://arxiv.org/abs/2206.00927 for detailed derivations
            if self.config.solver_type == "midpoint":
                x_t = (
                    (alpha_t / alpha_s2) * sample
                    - (sigma_t * (ops.exp(h) - 1.0)) * D0
                    - (sigma_t * ((ops.exp(h) - 1.0) / h - 1.0)) * D1_1
                )
            elif self.config.solver_type == "heun":
                x_t = (
                    (alpha_t / alpha_s2) * sample
                    - (sigma_t * (ops.exp(h) - 1.0)) * D0
                    - (sigma_t * ((ops.exp(h) - 1.0) / h - 1.0)) * D1
                    - (sigma_t * ((ops.exp(h) - 1.0 - h) / h**2 - 0.5)) * D2
                )
        return x_t

    def singlestep_dpm_solver_update(
        self,
        model_output_list: List[ms.Tensor],
        *args,
        sample: ms.Tensor = None,
        order: int = None,
        noise: Optional[ms.Tensor] = None,
        **kwargs,
    ) -> ms.Tensor:
        """
        One step for the singlestep DPMSolver.

        Args:
            model_output_list (`List[ms.Tensor]`):
                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 (`ms.Tensor`):
                A current instance of a sample created by diffusion process.
            order (`int`):
                The solver order at this step.

        Returns:
            `ms.Tensor`:
                The sample tensor at the previous timestep.
        """
        timestep_list = args[0] if len(args) > 0 else kwargs.pop("timestep_list", None)
        prev_timestep = args[1] if len(args) > 1 else kwargs.pop("prev_timestep", None)
        if sample is None:
            if len(args) > 2:
                sample = args[2]
            else:
                raise ValueError(" missing`sample` as a required keyward argument")
        if order is None:
            if len(args) > 3:
                order = args[3]
            else:
                raise ValueError(" missing `order` as a required keyward argument")
        if timestep_list is not None:
            deprecate(
                "timestep_list",
                "1.0.0",
                "Passing `timestep_list` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
            )

        if prev_timestep is not None:
            deprecate(
                "prev_timestep",
                "1.0.0",
                "Passing `prev_timestep` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
            )

        if order == 1:
            return self.dpm_solver_first_order_update(model_output_list[-1], sample=sample, noise=noise)
        elif order == 2:
            return self.singlestep_dpm_solver_second_order_update(model_output_list, sample=sample, noise=noise)
        elif order == 3:
            return self.singlestep_dpm_solver_third_order_update(model_output_list, sample=sample)
        else:
            raise ValueError(f"Order must be 1, 2, 3, got {order}")

    # Copied from diffusers.schedulers.scheduling_dpmsolver_multistep.DPMSolverMultistepScheduler.index_for_timestep
    def index_for_timestep(self, timestep, schedule_timesteps=None):
        if schedule_timesteps is None:
            schedule_timesteps = self.timesteps

        index_candidates_num = (schedule_timesteps == timestep).sum()

        if index_candidates_num == 0:
            step_index = len(self.timesteps) - 1
        # The sigma index that is taken for the **very** first `step`
        # is always the second index (or the last index if there is only 1)
        # This way we can ensure we don't accidentally skip a sigma in
        # case we start in the middle of the denoising schedule (e.g. for image-to-image)
        else:
            if index_candidates_num > 1:
                pos = 1
            else:
                pos = 0
            step_index = int((schedule_timesteps == timestep).nonzero()[pos])

        return step_index

    # Copied from diffusers.schedulers.scheduling_dpmsolver_multistep.DPMSolverMultistepScheduler._init_step_index
    def _init_step_index(self, timestep):
        """
        Initialize the step_index counter for the scheduler.
        """

        if self.begin_index is None:
            self._step_index = self.index_for_timestep(timestep)
        else:
            self._step_index = self._begin_index

    def step(
        self,
        model_output: ms.Tensor,
        timestep: Union[int, ms.Tensor],
        sample: ms.Tensor,
        generator=None,
        return_dict: bool = False,
    ) -> Union[SchedulerOutput, Tuple]:
        """
        Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with
        the singlestep DPMSolver.

        Args:
            model_output (`ms.Tensor`):
                The direct output from learned diffusion model.
            timestep (`int`):
                The current discrete timestep in the diffusion chain.
            sample (`ms.Tensor`):
                A current instance of a sample created by the diffusion process.
            return_dict (`bool`):
                Whether or not to return a [`~schedulers.scheduling_utils.SchedulerOutput`] or `tuple`.

        Returns:
            [`~schedulers.scheduling_utils.SchedulerOutput`] or `tuple`:
                If return_dict is `True`, [`~schedulers.scheduling_utils.SchedulerOutput`] is returned, otherwise a
                tuple is returned where the first element is the sample tensor.

        """
        if self.num_inference_steps is None:
            raise ValueError(
                "Number of inference steps is 'None', you need to run 'set_timesteps' after creating the scheduler"
            )

        if self.step_index is None:
            self._init_step_index(timestep)

        model_output = self.convert_model_output(model_output, sample=sample)
        for i in range(self.config.solver_order - 1):
            self.model_outputs[i] = self.model_outputs[i + 1]
        self.model_outputs[-1] = model_output

        if self.config.algorithm_type == "sde-dpmsolver++":
            noise = randn_tensor(model_output.shape, generator=generator, dtype=model_output.dtype)
        else:
            noise = None

        order = self.order_list[self.step_index]

        #  For img2img denoising might start with order>1 which is not possible
        #  In this case make sure that the first two steps are both order=1
        while self.model_outputs[-order] is None:
            order -= 1

        # For single-step solvers, we use the initial value at each time with order = 1.
        if order == 1:
            self.sample = sample

        prev_sample = self.singlestep_dpm_solver_update(
            self.model_outputs, sample=self.sample, order=order, noise=noise
        )

        # upon completion increase step index by one, noise=noise
        self._step_index += 1

        if not return_dict:
            return (prev_sample,)

        return SchedulerOutput(prev_sample=prev_sample)

    def scale_model_input(self, sample: ms.Tensor, *args, **kwargs) -> ms.Tensor:
        """
        Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
        current timestep.

        Args:
            sample (`ms.Tensor`):
                The input sample.

        Returns:
            `ms.Tensor`:
                A scaled input sample.
        """
        return sample

    # Copied from diffusers.schedulers.scheduling_dpmsolver_multistep.DPMSolverMultistepScheduler.add_noise
    def add_noise(
        self,
        original_samples: ms.Tensor,
        noise: ms.Tensor,
        timesteps: ms.Tensor,
    ) -> ms.Tensor:
        broadcast_shape = original_samples.shape
        # Make sure sigmas and timesteps have the same device and dtype as original_samples
        sigmas = self.sigmas.to(dtype=original_samples.dtype)
        schedule_timesteps = self.timesteps

        # begin_index is None when the scheduler is used for training or pipeline does not implement set_begin_index
        if self.begin_index is None:
            step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
        elif self.step_index is not None:
            # add_noise is called after first denoising step (for inpainting)
            step_indices = [self.step_index] * timesteps.shape[0]
        else:
            # add noise is called before first denoising step to create initial latent(img2img)
            step_indices = [self.begin_index] * timesteps.shape[0]

        sigma = sigmas[step_indices].flatten()
        # while len(sigma.shape) < len(original_samples.shape):
        #     sigma = sigma.unsqueeze(-1)
        sigma = ops.reshape(sigma, (timesteps.shape[0],) + (1,) * (len(broadcast_shape) - 1))

        alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma)
        noisy_samples = alpha_t * original_samples + sigma_t * noise
        return noisy_samples

    def __len__(self):
        return self.config.num_train_timesteps

mindone.diffusers.DPMSolverSinglestepScheduler.begin_index property

The index for the first timestep. It should be set from pipeline with set_begin_index method.

mindone.diffusers.DPMSolverSinglestepScheduler.step_index property

The index counter for current timestep. It will increase 1 after each scheduler step.

mindone.diffusers.DPMSolverSinglestepScheduler.convert_model_output(model_output, *args, sample=None, **kwargs)

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.

PARAMETER	DESCRIPTION
model_output	The direct output from the learned diffusion model. TYPE: `ms.Tensor`
sample	A current instance of a sample created by the diffusion process. TYPE: `ms.Tensor` DEFAULT: None

RETURNS	DESCRIPTION
Tensor	ms.Tensor: The converted model output.

Source code in mindone/diffusers/schedulers/scheduling_dpmsolver_singlestep.py

def convert_model_output(
    self,
    model_output: ms.Tensor,
    *args,
    sample: ms.Tensor = None,
    **kwargs,
) -> ms.Tensor:
    """
    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.

    <Tip>

    The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both noise
    prediction and data prediction models.

    </Tip>

    Args:
        model_output (`ms.Tensor`):
            The direct output from the learned diffusion model.
        sample (`ms.Tensor`):
            A current instance of a sample created by the diffusion process.

    Returns:
        `ms.Tensor`:
            The converted model output.
    """
    timestep = args[0] if len(args) > 0 else kwargs.pop("timestep", None)
    sigmas = self.sigmas.to(dtype=sample.dtype)
    if sample is None:
        if len(args) > 1:
            sample = args[1]
        else:
            raise ValueError("missing `sample` as a required keyward argument")
    if timestep is not None:
        deprecate(
            "timesteps",
            "1.0.0",
            "Passing `timesteps` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
        )
    # DPM-Solver++ needs to solve an integral of the data prediction model.
    if self.config.algorithm_type in ["dpmsolver++", "sde-dpmsolver++"]:
        if self.config.prediction_type == "epsilon":
            # DPM-Solver and DPM-Solver++ only need the "mean" output.
            if self.config.variance_type in ["learned", "learned_range"]:
                model_output = model_output[:, :3]
            sigma = sigmas[self.step_index]
            alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma)
            x0_pred = (sample - sigma_t * model_output) / alpha_t
        elif self.config.prediction_type == "sample":
            x0_pred = model_output
        elif self.config.prediction_type == "v_prediction":
            sigma = sigmas[self.step_index]
            alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma)
            x0_pred = alpha_t * sample - sigma_t * model_output
        else:
            raise ValueError(
                f"prediction_type given as {self.config.prediction_type} must be one of `epsilon`, `sample`, or"
                " `v_prediction` for the DPMSolverSinglestepScheduler."
            )

        if self.config.thresholding:
            x0_pred = self._threshold_sample(x0_pred)

        return x0_pred

    # DPM-Solver needs to solve an integral of the noise prediction model.
    elif self.config.algorithm_type == "dpmsolver":
        if self.config.prediction_type == "epsilon":
            # DPM-Solver and DPM-Solver++ only need the "mean" output.
            if self.config.variance_type in ["learned", "learned_range"]:
                epsilon = model_output[:, :3]
            else:
                epsilon = model_output
        elif self.config.prediction_type == "sample":
            sigma = sigmas[self.step_index]
            alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma)
            epsilon = (sample - alpha_t * model_output) / sigma_t
        elif self.config.prediction_type == "v_prediction":
            sigma = sigmas[self.step_index]
            alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma)
            epsilon = alpha_t * model_output + sigma_t * sample
        else:
            raise ValueError(
                f"prediction_type given as {self.config.prediction_type} must be one of `epsilon`, `sample`, or"
                " `v_prediction` for the DPMSolverSinglestepScheduler."
            )

        if self.config.thresholding:
            alpha_t, sigma_t = self.alpha_t[timestep], self.sigma_t[timestep]
            x0_pred = (sample - sigma_t * epsilon) / alpha_t
            x0_pred = self._threshold_sample(x0_pred)
            epsilon = (sample - alpha_t * x0_pred) / sigma_t

        return epsilon

mindone.diffusers.DPMSolverSinglestepScheduler.dpm_solver_first_order_update(model_output, *args, sample=None, noise=None, **kwargs)

One step for the first-order DPMSolver (equivalent to DDIM).

PARAMETER	DESCRIPTION
model_output	The direct output from the learned diffusion model. TYPE: `ms.Tensor`
timestep	The current discrete timestep in the diffusion chain. TYPE: `int`
prev_timestep	The previous discrete timestep in the diffusion chain. TYPE: `int`
sample	A current instance of a sample created by the diffusion process. TYPE: `ms.Tensor` DEFAULT: None

RETURNS	DESCRIPTION
Tensor	ms.Tensor: The sample tensor at the previous timestep.

Source code in mindone/diffusers/schedulers/scheduling_dpmsolver_singlestep.py

def dpm_solver_first_order_update(
    self,
    model_output: ms.Tensor,
    *args,
    sample: ms.Tensor = None,
    noise: Optional[ms.Tensor] = None,
    **kwargs,
) -> ms.Tensor:
    """
    One step for the first-order DPMSolver (equivalent to DDIM).

    Args:
        model_output (`ms.Tensor`):
            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 (`ms.Tensor`):
            A current instance of a sample created by the diffusion process.

    Returns:
        `ms.Tensor`:
            The sample tensor at the previous timestep.
    """
    timestep = args[0] if len(args) > 0 else kwargs.pop("timestep", None)
    prev_timestep = args[1] if len(args) > 1 else kwargs.pop("prev_timestep", None)
    sigmas = self.sigmas.to(dtype=sample.dtype)
    if sample is None:
        if len(args) > 2:
            sample = args[2]
        else:
            raise ValueError(" missing `sample` as a required keyward argument")
    if timestep is not None:
        deprecate(
            "timesteps",
            "1.0.0",
            "Passing `timesteps` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
        )

    if prev_timestep is not None:
        deprecate(
            "prev_timestep",
            "1.0.0",
            "Passing `prev_timestep` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
        )
    sigma_t, sigma_s = sigmas[self.step_index + 1], sigmas[self.step_index]
    alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma_t)
    alpha_s, sigma_s = self._sigma_to_alpha_sigma_t(sigma_s)
    lambda_t = ops.log(alpha_t) - ops.log(sigma_t)
    lambda_s = ops.log(alpha_s) - ops.log(sigma_s)
    h = lambda_t - lambda_s
    if self.config.algorithm_type == "dpmsolver++":
        x_t = (sigma_t / sigma_s) * sample - (alpha_t * (ops.exp(-h) - 1.0)) * model_output
    elif self.config.algorithm_type == "dpmsolver":
        x_t = (alpha_t / alpha_s) * sample - (sigma_t * (ops.exp(h) - 1.0)) * model_output
    elif self.config.algorithm_type == "sde-dpmsolver++":
        assert noise is not None
        x_t = (
            (sigma_t / sigma_s * ops.exp(-h)) * sample
            + (alpha_t * (1 - ops.exp(-2.0 * h))) * model_output
            + sigma_t * ops.sqrt(1.0 - ops.exp(-2 * h)) * noise
        )
    return x_t

mindone.diffusers.DPMSolverSinglestepScheduler.get_order_list(num_inference_steps)

Computes the solver order at each time step.

PARAMETER	DESCRIPTION
num_inference_steps	The number of diffusion steps used when generating samples with a pre-trained model. TYPE: `int`

Source code in mindone/diffusers/schedulers/scheduling_dpmsolver_singlestep.py

def get_order_list(self, num_inference_steps: int) -> List[int]:
    """
    Computes the solver order at each time step.

    Args:
        num_inference_steps (`int`):
            The number of diffusion steps used when generating samples with a pre-trained model.
    """
    steps = num_inference_steps
    order = self.config.solver_order
    if order > 3:
        raise ValueError("Order > 3 is not supported by this scheduler")
    if self.config.lower_order_final:
        if order == 3:
            if steps % 3 == 0:
                orders = [1, 2, 3] * (steps // 3 - 1) + [1, 2] + [1]
            elif steps % 3 == 1:
                orders = [1, 2, 3] * (steps // 3) + [1]
            else:
                orders = [1, 2, 3] * (steps // 3) + [1, 2]
        elif order == 2:
            if steps % 2 == 0:
                orders = [1, 2] * (steps // 2 - 1) + [1, 1]
            else:
                orders = [1, 2] * (steps // 2) + [1]
        elif order == 1:
            orders = [1] * steps
    else:
        if order == 3:
            orders = [1, 2, 3] * (steps // 3)
        elif order == 2:
            orders = [1, 2] * (steps // 2)
        elif order == 1:
            orders = [1] * steps
    return orders

mindone.diffusers.DPMSolverSinglestepScheduler.scale_model_input(sample, *args, **kwargs)

Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep.

PARAMETER	DESCRIPTION
sample	The input sample. TYPE: `ms.Tensor`

RETURNS	DESCRIPTION
Tensor	ms.Tensor: A scaled input sample.

Source code in mindone/diffusers/schedulers/scheduling_dpmsolver_singlestep.py

def scale_model_input(self, sample: ms.Tensor, *args, **kwargs) -> ms.Tensor:
    """
    Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
    current timestep.

    Args:
        sample (`ms.Tensor`):
            The input sample.

    Returns:
        `ms.Tensor`:
            A scaled input sample.
    """
    return sample

mindone.diffusers.DPMSolverSinglestepScheduler.set_begin_index(begin_index=0)

Sets the begin index for the scheduler. This function should be run from pipeline before the inference.

PARAMETER	DESCRIPTION
begin_index	The begin index for the scheduler. TYPE: `int` DEFAULT: 0

Source code in mindone/diffusers/schedulers/scheduling_dpmsolver_singlestep.py

def set_begin_index(self, begin_index: int = 0):
    """
    Sets the begin index for the scheduler. This function should be run from pipeline before the inference.

    Args:
        begin_index (`int`):
            The begin index for the scheduler.
    """
    self._begin_index = begin_index

mindone.diffusers.DPMSolverSinglestepScheduler.set_timesteps(num_inference_steps=None, timesteps=None)

Sets the discrete timesteps used for the diffusion chain (to be run before inference).

PARAMETER	DESCRIPTION
num_inference_steps	The number of diffusion steps used when generating samples with a pre-trained model. TYPE: `int` DEFAULT: None
timesteps	Custom timesteps used to support arbitrary spacing between timesteps. If None, then the default timestep spacing strategy of equal spacing between timesteps schedule is used. If timesteps is passed, num_inference_steps must be None. TYPE: `List[int]`, *optional* DEFAULT: None

Source code in mindone/diffusers/schedulers/scheduling_dpmsolver_singlestep.py

def set_timesteps(self, num_inference_steps: int = None, timesteps: Optional[List[int]] = None):
    """
    Sets the discrete timesteps used for the diffusion chain (to be run before inference).

    Args:
        num_inference_steps (`int`):
            The number of diffusion steps used when generating samples with a pre-trained model.
        timesteps (`List[int]`, *optional*):
            Custom timesteps used to support arbitrary spacing between timesteps. If `None`, then the default
            timestep spacing strategy of equal spacing between timesteps schedule is used. If `timesteps` is
            passed, `num_inference_steps` must be `None`.
    """
    if num_inference_steps is None and timesteps is None:
        raise ValueError("Must pass exactly one of  `num_inference_steps` or `timesteps`.")
    if num_inference_steps is not None and timesteps is not None:
        raise ValueError("Must pass exactly one of  `num_inference_steps` or `timesteps`.")
    if timesteps is not None and self.config.use_karras_sigmas:
        raise ValueError("Cannot use `timesteps` when `config.use_karras_sigmas=True`.")

    num_inference_steps = num_inference_steps or len(timesteps)
    self.num_inference_steps = num_inference_steps

    if timesteps is not None:
        timesteps = np.array(timesteps).astype(np.int64)
    else:
        # Clipping the minimum of all lambda(t) for numerical stability.
        # This is critical for cosine (squaredcos_cap_v2) noise schedule.
        clipped_idx = np.searchsorted(ops.flip(self.lambda_t, [0]).asnumpy(), self.config.lambda_min_clipped)
        timesteps = (
            np.linspace(0, self.config.num_train_timesteps - 1 - clipped_idx, num_inference_steps + 1)
            .round()[::-1][:-1]
            .copy()
            .astype(np.int64)
        )

    sigmas = (((1 - self.alphas_cumprod) / self.alphas_cumprod) ** 0.5).asnumpy()
    if self.config.use_karras_sigmas:
        log_sigmas = np.log(sigmas)
        sigmas = np.flip(sigmas).copy()
        sigmas = self._convert_to_karras(in_sigmas=sigmas, num_inference_steps=num_inference_steps)
        timesteps = np.array([self._sigma_to_t(sigma, log_sigmas) for sigma in sigmas]).round()
    else:
        sigmas = np.interp(timesteps, np.arange(0, len(sigmas)), sigmas)

    if self.config.final_sigmas_type == "sigma_min":
        sigma_last = ((1 - self.alphas_cumprod[0]) / self.alphas_cumprod[0]) ** 0.5
    elif self.config.final_sigmas_type == "zero":
        sigma_last = 0
    else:
        raise ValueError(
            f" `final_sigmas_type` must be one of `sigma_min` or `zero`, but got {self.config.final_sigmas_type}"
        )
    sigmas = np.concatenate([sigmas, [sigma_last]]).astype(np.float32)

    self.sigmas = ms.Tensor(sigmas)

    self.timesteps = ms.tensor(timesteps, dtype=ms.int64)
    self.model_outputs = [None] * self.config.solver_order
    self.sample = None

    if not self.config.lower_order_final and num_inference_steps % self.config.solver_order != 0:
        logger.warning(
            "Changing scheduler {self.config} to have `lower_order_final` set to True to handle uneven amount of inference steps. "
            "Please make sure to always use an even number of `num_inference steps when using `lower_order_final=False`."
        )
        self.register_to_config(lower_order_final=True)

    if not self.config.lower_order_final and self.config.final_sigmas_type == "zero":
        logger.warning(
            " `last_sigmas_type='zero'` is not supported for `lower_order_final=False`. "
            "Changing scheduler {self.config} to have `lower_order_final` set to True."
        )
        self.register_to_config(lower_order_final=True)

    self.order_list = self.get_order_list(num_inference_steps)

    # add an index counter for schedulers that allow duplicated timesteps
    self._step_index = None
    self._begin_index = None

mindone.diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_second_order_update(model_output_list, *args, sample=None, noise=None, **kwargs)

One step for the second-order singlestep DPMSolver that computes the solution at time prev_timestep from the time timestep_list[-2].

PARAMETER	DESCRIPTION
model_output_list	The direct outputs from learned diffusion model at current and latter timesteps. TYPE: `List[ms.Tensor]`
timestep	The current and latter discrete timestep in the diffusion chain. TYPE: `int`
prev_timestep	The previous discrete timestep in the diffusion chain. TYPE: `int`
sample	A current instance of a sample created by the diffusion process. TYPE: `ms.Tensor` DEFAULT: None

RETURNS	DESCRIPTION
Tensor	ms.Tensor: The sample tensor at the previous timestep.

Source code in mindone/diffusers/schedulers/scheduling_dpmsolver_singlestep.py

def singlestep_dpm_solver_second_order_update(
    self,
    model_output_list: List[ms.Tensor],
    *args,
    sample: ms.Tensor = None,
    noise: Optional[ms.Tensor] = None,
    **kwargs,
) -> ms.Tensor:
    """
    One step for the second-order singlestep DPMSolver that computes the solution at time `prev_timestep` from the
    time `timestep_list[-2]`.

    Args:
        model_output_list (`List[ms.Tensor]`):
            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 (`ms.Tensor`):
            A current instance of a sample created by the diffusion process.

    Returns:
        `ms.Tensor`:
            The sample tensor at the previous timestep.
    """
    timestep_list = args[0] if len(args) > 0 else kwargs.pop("timestep_list", None)
    prev_timestep = args[1] if len(args) > 1 else kwargs.pop("prev_timestep", None)
    sigmas = self.sigmas.to(dtype=sample.dtype)
    if sample is None:
        if len(args) > 2:
            sample = args[2]
        else:
            raise ValueError(" missing `sample` as a required keyward argument")
    if timestep_list is not None:
        deprecate(
            "timestep_list",
            "1.0.0",
            "Passing `timestep_list` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
        )

    if prev_timestep is not None:
        deprecate(
            "prev_timestep",
            "1.0.0",
            "Passing `prev_timestep` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
        )
    sigma_t, sigma_s0, sigma_s1 = (
        sigmas[self.step_index + 1],
        sigmas[self.step_index],
        sigmas[self.step_index - 1],
    )

    alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma_t)
    alpha_s0, sigma_s0 = self._sigma_to_alpha_sigma_t(sigma_s0)
    alpha_s1, sigma_s1 = self._sigma_to_alpha_sigma_t(sigma_s1)

    lambda_t = ops.log(alpha_t) - ops.log(sigma_t)
    lambda_s0 = ops.log(alpha_s0) - ops.log(sigma_s0)
    lambda_s1 = ops.log(alpha_s1) - ops.log(sigma_s1)

    m0, m1 = model_output_list[-1], model_output_list[-2]

    h, h_0 = lambda_t - lambda_s1, lambda_s0 - lambda_s1
    r0 = h_0 / h
    D0, D1 = m1, (1.0 / r0) * (m0 - m1)
    if self.config.algorithm_type == "dpmsolver++":
        # See https://arxiv.org/abs/2211.01095 for detailed derivations
        if self.config.solver_type == "midpoint":
            x_t = (
                (sigma_t / sigma_s1) * sample
                - (alpha_t * (ops.exp(-h) - 1.0)) * D0
                - 0.5 * (alpha_t * (ops.exp(-h) - 1.0)) * D1
            )
        elif self.config.solver_type == "heun":
            x_t = (
                (sigma_t / sigma_s1) * sample
                - (alpha_t * (ops.exp(-h) - 1.0)) * D0
                + (alpha_t * ((ops.exp(-h) - 1.0) / h + 1.0)) * D1
            )
    elif self.config.algorithm_type == "dpmsolver":
        # See https://arxiv.org/abs/2206.00927 for detailed derivations
        if self.config.solver_type == "midpoint":
            x_t = (
                (alpha_t / alpha_s1) * sample
                - (sigma_t * (ops.exp(h) - 1.0)) * D0
                - 0.5 * (sigma_t * (ops.exp(h) - 1.0)) * D1
            )
        elif self.config.solver_type == "heun":
            x_t = (
                (alpha_t / alpha_s1) * sample
                - (sigma_t * (ops.exp(h) - 1.0)) * D0
                - (sigma_t * ((ops.exp(h) - 1.0) / h - 1.0)) * D1
            )
    elif self.config.algorithm_type == "sde-dpmsolver++":
        assert noise is not None
        if self.config.solver_type == "midpoint":
            x_t = (
                (sigma_t / sigma_s1 * ops.exp(-h)) * sample
                + (alpha_t * (1 - ops.exp(-2.0 * h))) * D0
                + 0.5 * (alpha_t * (1 - ops.exp(-2.0 * h))) * D1
                + sigma_t * ops.sqrt(1.0 - ops.exp(-2 * h)) * noise
            )
        elif self.config.solver_type == "heun":
            x_t = (
                (sigma_t / sigma_s1 * ops.exp(-h)) * sample
                + (alpha_t * (1 - ops.exp(-2.0 * h))) * D0
                + (alpha_t * ((1.0 - ops.exp(-2.0 * h)) / (-2.0 * h) + 1.0)) * D1
                + sigma_t * ops.sqrt(1.0 - ops.exp(-2 * h)) * noise
            )
    return x_t

mindone.diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_third_order_update(model_output_list, *args, sample=None, **kwargs)

One step for the third-order singlestep DPMSolver that computes the solution at time prev_timestep from the time timestep_list[-3].

PARAMETER	DESCRIPTION
model_output_list	The direct outputs from learned diffusion model at current and latter timesteps. TYPE: `List[ms.Tensor]`
timestep	The current and latter discrete timestep in the diffusion chain. TYPE: `int`
prev_timestep	The previous discrete timestep in the diffusion chain. TYPE: `int`
sample	A current instance of a sample created by diffusion process. TYPE: `ms.Tensor` DEFAULT: None

RETURNS	DESCRIPTION
Tensor	ms.Tensor: The sample tensor at the previous timestep.

Source code in mindone/diffusers/schedulers/scheduling_dpmsolver_singlestep.py

def singlestep_dpm_solver_third_order_update(
    self,
    model_output_list: List[ms.Tensor],
    *args,
    sample: ms.Tensor = None,
    **kwargs,
) -> ms.Tensor:
    """
    One step for the third-order singlestep DPMSolver that computes the solution at time `prev_timestep` from the
    time `timestep_list[-3]`.

    Args:
        model_output_list (`List[ms.Tensor]`):
            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 (`ms.Tensor`):
            A current instance of a sample created by diffusion process.

    Returns:
        `ms.Tensor`:
            The sample tensor at the previous timestep.
    """

    timestep_list = args[0] if len(args) > 0 else kwargs.pop("timestep_list", None)
    prev_timestep = args[1] if len(args) > 1 else kwargs.pop("prev_timestep", None)
    sigmas = self.sigmas.to(dtype=sample.dtype)
    if sample is None:
        if len(args) > 2:
            sample = args[2]
        else:
            raise ValueError(" missing`sample` as a required keyward argument")
    if timestep_list is not None:
        deprecate(
            "timestep_list",
            "1.0.0",
            "Passing `timestep_list` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
        )

    if prev_timestep is not None:
        deprecate(
            "prev_timestep",
            "1.0.0",
            "Passing `prev_timestep` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
        )

    sigma_t, sigma_s0, sigma_s1, sigma_s2 = (
        sigmas[self.step_index + 1],
        sigmas[self.step_index],
        sigmas[self.step_index - 1],
        sigmas[self.step_index - 2],
    )

    alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma_t)
    alpha_s0, sigma_s0 = self._sigma_to_alpha_sigma_t(sigma_s0)
    alpha_s1, sigma_s1 = self._sigma_to_alpha_sigma_t(sigma_s1)
    alpha_s2, sigma_s2 = self._sigma_to_alpha_sigma_t(sigma_s2)

    lambda_t = ops.log(alpha_t) - ops.log(sigma_t)
    lambda_s0 = ops.log(alpha_s0) - ops.log(sigma_s0)
    lambda_s1 = ops.log(alpha_s1) - ops.log(sigma_s1)
    lambda_s2 = ops.log(alpha_s2) - ops.log(sigma_s2)

    m0, m1, m2 = model_output_list[-1], model_output_list[-2], model_output_list[-3]

    h, h_0, h_1 = lambda_t - lambda_s2, lambda_s0 - lambda_s2, lambda_s1 - lambda_s2
    r0, r1 = h_0 / h, h_1 / h
    D0 = m2
    D1_0, D1_1 = (1.0 / r1) * (m1 - m2), (1.0 / r0) * (m0 - m2)
    D1 = (r0 * D1_0 - r1 * D1_1) / (r0 - r1)
    D2 = 2.0 * (D1_1 - D1_0) / (r0 - r1)
    if self.config.algorithm_type == "dpmsolver++":
        # See https://arxiv.org/abs/2206.00927 for detailed derivations
        if self.config.solver_type == "midpoint":
            x_t = (
                (sigma_t / sigma_s2) * sample
                - (alpha_t * (ops.exp(-h) - 1.0)) * D0
                + (alpha_t * ((ops.exp(-h) - 1.0) / h + 1.0)) * D1_1
            )
        elif self.config.solver_type == "heun":
            x_t = (
                (sigma_t / sigma_s2) * sample
                - (alpha_t * (ops.exp(-h) - 1.0)) * D0
                + (alpha_t * ((ops.exp(-h) - 1.0) / h + 1.0)) * D1
                - (alpha_t * ((ops.exp(-h) - 1.0 + h) / h**2 - 0.5)) * D2
            )
    elif self.config.algorithm_type == "dpmsolver":
        # See https://arxiv.org/abs/2206.00927 for detailed derivations
        if self.config.solver_type == "midpoint":
            x_t = (
                (alpha_t / alpha_s2) * sample
                - (sigma_t * (ops.exp(h) - 1.0)) * D0
                - (sigma_t * ((ops.exp(h) - 1.0) / h - 1.0)) * D1_1
            )
        elif self.config.solver_type == "heun":
            x_t = (
                (alpha_t / alpha_s2) * sample
                - (sigma_t * (ops.exp(h) - 1.0)) * D0
                - (sigma_t * ((ops.exp(h) - 1.0) / h - 1.0)) * D1
                - (sigma_t * ((ops.exp(h) - 1.0 - h) / h**2 - 0.5)) * D2
            )
    return x_t

mindone.diffusers.DPMSolverSinglestepScheduler.singlestep_dpm_solver_update(model_output_list, *args, sample=None, order=None, noise=None, **kwargs)

One step for the singlestep DPMSolver.

PARAMETER	DESCRIPTION
model_output_list	The direct outputs from learned diffusion model at current and latter timesteps. TYPE: `List[ms.Tensor]`
timestep	The current and latter discrete timestep in the diffusion chain. TYPE: `int`
prev_timestep	The previous discrete timestep in the diffusion chain. TYPE: `int`
sample	A current instance of a sample created by diffusion process. TYPE: `ms.Tensor` DEFAULT: None
order	The solver order at this step. TYPE: `int` DEFAULT: None

RETURNS	DESCRIPTION
Tensor	ms.Tensor: The sample tensor at the previous timestep.

Source code in mindone/diffusers/schedulers/scheduling_dpmsolver_singlestep.py

def singlestep_dpm_solver_update(
    self,
    model_output_list: List[ms.Tensor],
    *args,
    sample: ms.Tensor = None,
    order: int = None,
    noise: Optional[ms.Tensor] = None,
    **kwargs,
) -> ms.Tensor:
    """
    One step for the singlestep DPMSolver.

    Args:
        model_output_list (`List[ms.Tensor]`):
            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 (`ms.Tensor`):
            A current instance of a sample created by diffusion process.
        order (`int`):
            The solver order at this step.

    Returns:
        `ms.Tensor`:
            The sample tensor at the previous timestep.
    """
    timestep_list = args[0] if len(args) > 0 else kwargs.pop("timestep_list", None)
    prev_timestep = args[1] if len(args) > 1 else kwargs.pop("prev_timestep", None)
    if sample is None:
        if len(args) > 2:
            sample = args[2]
        else:
            raise ValueError(" missing`sample` as a required keyward argument")
    if order is None:
        if len(args) > 3:
            order = args[3]
        else:
            raise ValueError(" missing `order` as a required keyward argument")
    if timestep_list is not None:
        deprecate(
            "timestep_list",
            "1.0.0",
            "Passing `timestep_list` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
        )

    if prev_timestep is not None:
        deprecate(
            "prev_timestep",
            "1.0.0",
            "Passing `prev_timestep` is deprecated and has no effect as model output conversion is now handled via an internal counter `self.step_index`",
        )

    if order == 1:
        return self.dpm_solver_first_order_update(model_output_list[-1], sample=sample, noise=noise)
    elif order == 2:
        return self.singlestep_dpm_solver_second_order_update(model_output_list, sample=sample, noise=noise)
    elif order == 3:
        return self.singlestep_dpm_solver_third_order_update(model_output_list, sample=sample)
    else:
        raise ValueError(f"Order must be 1, 2, 3, got {order}")

mindone.diffusers.DPMSolverSinglestepScheduler.step(model_output, timestep, sample, generator=None, return_dict=False)

Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with the singlestep DPMSolver.

PARAMETER	DESCRIPTION
model_output	The direct output from learned diffusion model. TYPE: `ms.Tensor`
timestep	The current discrete timestep in the diffusion chain. TYPE: `int`
sample	A current instance of a sample created by the diffusion process. TYPE: `ms.Tensor`
return_dict	Whether or not to return a [~schedulers.scheduling_utils.SchedulerOutput] or tuple. TYPE: `bool` DEFAULT: False

RETURNS	DESCRIPTION
Union[SchedulerOutput, Tuple]	[~schedulers.scheduling_utils.SchedulerOutput] or tuple: If return_dict is True, [~schedulers.scheduling_utils.SchedulerOutput] is returned, otherwise a tuple is returned where the first element is the sample tensor.

Source code in mindone/diffusers/schedulers/scheduling_dpmsolver_singlestep.py

def step(
    self,
    model_output: ms.Tensor,
    timestep: Union[int, ms.Tensor],
    sample: ms.Tensor,
    generator=None,
    return_dict: bool = False,
) -> Union[SchedulerOutput, Tuple]:
    """
    Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with
    the singlestep DPMSolver.

    Args:
        model_output (`ms.Tensor`):
            The direct output from learned diffusion model.
        timestep (`int`):
            The current discrete timestep in the diffusion chain.
        sample (`ms.Tensor`):
            A current instance of a sample created by the diffusion process.
        return_dict (`bool`):
            Whether or not to return a [`~schedulers.scheduling_utils.SchedulerOutput`] or `tuple`.

    Returns:
        [`~schedulers.scheduling_utils.SchedulerOutput`] or `tuple`:
            If return_dict is `True`, [`~schedulers.scheduling_utils.SchedulerOutput`] is returned, otherwise a
            tuple is returned where the first element is the sample tensor.

    """
    if self.num_inference_steps is None:
        raise ValueError(
            "Number of inference steps is 'None', you need to run 'set_timesteps' after creating the scheduler"
        )

    if self.step_index is None:
        self._init_step_index(timestep)

    model_output = self.convert_model_output(model_output, sample=sample)
    for i in range(self.config.solver_order - 1):
        self.model_outputs[i] = self.model_outputs[i + 1]
    self.model_outputs[-1] = model_output

    if self.config.algorithm_type == "sde-dpmsolver++":
        noise = randn_tensor(model_output.shape, generator=generator, dtype=model_output.dtype)
    else:
        noise = None

    order = self.order_list[self.step_index]

    #  For img2img denoising might start with order>1 which is not possible
    #  In this case make sure that the first two steps are both order=1
    while self.model_outputs[-order] is None:
        order -= 1

    # For single-step solvers, we use the initial value at each time with order = 1.
    if order == 1:
        self.sample = sample

    prev_sample = self.singlestep_dpm_solver_update(
        self.model_outputs, sample=self.sample, order=order, noise=noise
    )

    # upon completion increase step index by one, noise=noise
    self._step_index += 1

    if not return_dict:
        return (prev_sample,)

    return SchedulerOutput(prev_sample=prev_sample)