EDMEulerScheduler

The Karras formulation of the Euler scheduler (Algorithm 2) from the Elucidating the Design Space of Diffusion-Based Generative Models paper by Karras et al. This is a fast scheduler which can often generate good outputs in 20-30 steps. The scheduler is based on the original k-diffusion implementation by Katherine Crowson.

mindone.diffusers.EDMEulerScheduler

Bases: SchedulerMixin, ConfigMixin

Implements the Euler scheduler in EDM formulation as presented in Karras et al. 2022 [1].

[1] Karras, Tero, et al. "Elucidating the Design Space of Diffusion-Based Generative Models." https://arxiv.org/abs/2206.00364

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
sigma_min	Minimum noise magnitude in the sigma schedule. This was set to 0.002 in the EDM paper [1]; a reasonable range is [0, 10]. TYPE: `float`, *optional*, defaults to 0.002 DEFAULT: 0.002
sigma_max	Maximum noise magnitude in the sigma schedule. This was set to 80.0 in the EDM paper [1]; a reasonable range is [0.2, 80.0]. TYPE: `float`, *optional*, defaults to 80.0 DEFAULT: 80.0
sigma_data	The standard deviation of the data distribution. This is set to 0.5 in the EDM paper [1]. TYPE: `float`, *optional*, defaults to 0.5 DEFAULT: 0.5
sigma_schedule	Sigma schedule to compute the sigmas. By default, we the schedule introduced in the EDM paper (https://arxiv.org/abs/2206.00364). Other acceptable value is "exponential". The exponential schedule was incorporated in this model: https://huggingface.co/stabilityai/cosxl. TYPE: `str`, *optional*, defaults to `karras` DEFAULT: 'karras'
num_train_timesteps	The number of diffusion steps to train the model. TYPE: `int`, defaults to 1000 DEFAULT: 1000
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'
rho	The rho parameter used for calculating the Karras sigma schedule, which is set to 7.0 in the EDM paper [1]. TYPE: `float`, *optional*, defaults to 7.0 DEFAULT: 7.0

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

class EDMEulerScheduler(SchedulerMixin, ConfigMixin):
    """
    Implements the Euler scheduler in EDM formulation as presented in Karras et al. 2022 [1].

    [1] Karras, Tero, et al. "Elucidating the Design Space of Diffusion-Based Generative Models."
    https://arxiv.org/abs/2206.00364

    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:
        sigma_min (`float`, *optional*, defaults to 0.002):
            Minimum noise magnitude in the sigma schedule. This was set to 0.002 in the EDM paper [1]; a reasonable
            range is [0, 10].
        sigma_max (`float`, *optional*, defaults to 80.0):
            Maximum noise magnitude in the sigma schedule. This was set to 80.0 in the EDM paper [1]; a reasonable
            range is [0.2, 80.0].
        sigma_data (`float`, *optional*, defaults to 0.5):
            The standard deviation of the data distribution. This is set to 0.5 in the EDM paper [1].
        sigma_schedule (`str`, *optional*, defaults to `karras`):
            Sigma schedule to compute the `sigmas`. By default, we the schedule introduced in the EDM paper
            (https://arxiv.org/abs/2206.00364). Other acceptable value is "exponential". The exponential schedule was
            incorporated in this model: https://huggingface.co/stabilityai/cosxl.
        num_train_timesteps (`int`, defaults to 1000):
            The number of diffusion steps to train the model.
        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).
        rho (`float`, *optional*, defaults to 7.0):
            The rho parameter used for calculating the Karras sigma schedule, which is set to 7.0 in the EDM paper [1].
    """

    _compatibles = []
    order = 1

    @register_to_config
    def __init__(
        self,
        sigma_min: float = 0.002,
        sigma_max: float = 80.0,
        sigma_data: float = 0.5,
        sigma_schedule: str = "karras",
        num_train_timesteps: int = 1000,
        prediction_type: str = "epsilon",
        rho: float = 7.0,
    ):
        if sigma_schedule not in ["karras", "exponential"]:
            raise ValueError(f"Wrong value for provided for `{sigma_schedule=}`.`")

        # setable values
        self.num_inference_steps = None

        ramp = ms.tensor(np.linspace(0, 1, num_train_timesteps), ms.float32)
        if sigma_schedule == "karras":
            sigmas = self._compute_karras_sigmas(ramp)
        elif sigma_schedule == "exponential":
            sigmas = self._compute_exponential_sigmas(ramp)

        self.timesteps = self.precondition_noise(sigmas)

        self.sigmas = ops.cat([sigmas, ops.zeros(1, dtype=sigmas.dtype)])

        self.is_scale_input_called = False

        self._step_index = None
        self._begin_index = None
        self.sigma_data = self.config.sigma_data

    @property
    def init_noise_sigma(self):
        # standard deviation of the initial noise distribution
        return (self.config.sigma_max**2 + 1) ** 0.5

    @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 precondition_inputs(self, sample, sigma):
        c_in = 1 / ((sigma**2 + self.sigma_data**2) ** 0.5)
        scaled_sample = sample * c_in
        return scaled_sample

    def precondition_noise(self, sigma):
        if not isinstance(sigma, ms.Tensor):
            sigma = ms.tensor(sigma)

        c_noise = 0.25 * ops.log(sigma)

        return c_noise

    def precondition_outputs(self, sample, model_output, sigma):
        sigma_data = self.sigma_data
        c_skip = sigma_data**2 / (sigma**2 + sigma_data**2)

        if self.config.prediction_type == "epsilon":
            c_out = sigma * sigma_data / (sigma**2 + sigma_data**2) ** 0.5
        elif self.config.prediction_type == "v_prediction":
            c_out = -sigma * sigma_data / (sigma**2 + sigma_data**2) ** 0.5
        else:
            raise ValueError(f"Prediction type {self.config.prediction_type} is not supported.")

        denoised = (c_skip * sample + c_out * model_output).to(sample.dtype)

        return denoised

    def scale_model_input(self, sample: ms.Tensor, timestep: Union[float, ms.Tensor]) -> ms.Tensor:
        """
        Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
        current timestep. Scales the denoising model input by `(sigma**2 + 1) ** 0.5` to match the Euler algorithm.

        Args:
            sample (`ms.Tensor`):
                The input sample.
            timestep (`int`, *optional*):
                The current timestep in the diffusion chain.

        Returns:
            `ms.Tensor`:
                A scaled input sample.
        """
        if self.step_index is None:
            self._init_step_index(timestep)

        sigma = self.sigmas[self.step_index]
        sample = self.precondition_inputs(sample, sigma).to(sample.dtype)

        self.is_scale_input_called = True
        return sample

    def set_timesteps(self, num_inference_steps: int):
        """
        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.
        """
        self.num_inference_steps = num_inference_steps

        ramp = ms.tensor(np.linspace(0, 1, self.num_inference_steps))
        if self.config.sigma_schedule == "karras":
            sigmas = self._compute_karras_sigmas(ramp)
        elif self.config.sigma_schedule == "exponential":
            sigmas = self._compute_exponential_sigmas(ramp)

        sigmas = sigmas.to(ms.float32)
        self.timesteps = self.precondition_noise(sigmas)

        self.sigmas = ops.cat([sigmas, ops.zeros(1)])
        self._step_index = None
        self._begin_index = None

    # Taken from https://github.com/crowsonkb/k-diffusion/blob/686dbad0f39640ea25c8a8c6a6e56bb40eacefa2/k_diffusion/sampling.py#L17
    def _compute_karras_sigmas(self, ramp, sigma_min=None, sigma_max=None) -> ms.Tensor:
        """Constructs the noise schedule of Karras et al. (2022)."""
        sigma_min = sigma_min or self.config.sigma_min
        sigma_max = sigma_max or self.config.sigma_max

        rho = self.config.rho
        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 _compute_exponential_sigmas(self, ramp, sigma_min=None, sigma_max=None) -> ms.Tensor:
        """Implementation closely follows k-diffusion.

        https://github.com/crowsonkb/k-diffusion/blob/6ab5146d4a5ef63901326489f31f1d8e7dd36b48/k_diffusion/sampling.py#L26
        """
        sigma_min = sigma_min or self.config.sigma_min
        sigma_max = sigma_max or self.config.sigma_max
        sigmas = ms.tensor(np.linspace(math.log(sigma_min), math.log(sigma_max), len(ramp)).exp().flip((0,)))
        return sigmas

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

        if (schedule_timesteps == timestep).sum() > 1:
            pos = 1
        else:
            pos = 0

        # 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)
        indices = (schedule_timesteps == timestep).nonzero()

        return int(indices[pos])

    # Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler._init_step_index
    def _init_step_index(self, timestep):
        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[float, ms.Tensor],
        sample: ms.Tensor,
        s_churn: float = 0.0,
        s_tmin: float = 0.0,
        s_tmax: float = float("inf"),
        s_noise: float = 1.0,
        generator: Optional[np.random.Generator] = None,
        return_dict: bool = False,
    ) -> Union[EDMEulerSchedulerOutput, Tuple]:
        """
        Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion
        process from the learned model outputs (most often the predicted noise).

        Args:
            model_output (`ms.Tensor`):
                The direct output from learned diffusion model.
            timestep (`float`):
                The current discrete timestep in the diffusion chain.
            sample (`ms.Tensor`):
                A current instance of a sample created by the diffusion process.
            s_churn (`float`):
            s_tmin  (`float`):
            s_tmax  (`float`):
            s_noise (`float`, defaults to 1.0):
                Scaling factor for noise added to the sample.
            generator (`np.random.Generator`, *optional*):
                A random number generator.
            return_dict (`bool`):
                Whether or not to return a [`~schedulers.scheduling_euler_discrete.EDMEulerSchedulerOutput`] or tuple.

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

        if isinstance(timestep, int) or (isinstance(timestep, ms.Tensor) and timestep.dtype in [ms.int32, ms.int64]):
            raise ValueError(
                (
                    "Passing integer indices (e.g. from `enumerate(timesteps)`) as timesteps to"
                    " `EDMEulerScheduler.step()` is not supported. Make sure to pass"
                    " one of the `scheduler.timesteps` as a timestep."
                ),
            )

        if not self.is_scale_input_called:
            logger.warning(
                "The `scale_model_input` function should be called before `step` to ensure correct denoising. "
                "See `StableDiffusionPipeline` for a usage example."
            )

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

        # Upcast to avoid precision issues when computing prev_sample
        sample = sample.to(ms.float32)

        sigma = self.sigmas[self.step_index]

        gamma = min(s_churn / (len(self.sigmas) - 1), 2**0.5 - 1) if s_tmin <= sigma <= s_tmax else 0.0

        noise = randn_tensor(model_output.shape, dtype=model_output.dtype, generator=generator)

        eps = noise * s_noise
        sigma_hat = sigma * (gamma + 1)

        if gamma > 0:
            sample = sample + eps * (sigma_hat**2 - sigma**2) ** 0.5

        # 1. compute predicted original sample (x_0) from sigma-scaled predicted noise
        pred_original_sample = self.precondition_outputs(sample, model_output, sigma_hat)

        # 2. Convert to an ODE derivative
        derivative = (sample - pred_original_sample) / sigma_hat

        dt = self.sigmas[self.step_index + 1] - sigma_hat

        prev_sample = sample + derivative * dt

        # Cast sample back to model compatible dtype
        prev_sample = prev_sample.to(model_output.dtype)

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

        if not return_dict:
            return (prev_sample,)

        return EDMEulerSchedulerOutput(prev_sample=prev_sample, pred_original_sample=pred_original_sample)

    # Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler.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

        # self.begin_index is None when 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))

        noisy_samples = original_samples + noise * sigma
        return noisy_samples

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

mindone.diffusers.EDMEulerScheduler.begin_index property

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

mindone.diffusers.EDMEulerScheduler.step_index property

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

mindone.diffusers.EDMEulerScheduler.scale_model_input(sample, timestep)

Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. Scales the denoising model input by (sigma**2 + 1) ** 0.5 to match the Euler algorithm.

PARAMETER	DESCRIPTION
sample	The input sample. TYPE: `ms.Tensor`
timestep	The current timestep in the diffusion chain. TYPE: `int`, *optional*

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

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

def scale_model_input(self, sample: ms.Tensor, timestep: Union[float, ms.Tensor]) -> ms.Tensor:
    """
    Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
    current timestep. Scales the denoising model input by `(sigma**2 + 1) ** 0.5` to match the Euler algorithm.

    Args:
        sample (`ms.Tensor`):
            The input sample.
        timestep (`int`, *optional*):
            The current timestep in the diffusion chain.

    Returns:
        `ms.Tensor`:
            A scaled input sample.
    """
    if self.step_index is None:
        self._init_step_index(timestep)

    sigma = self.sigmas[self.step_index]
    sample = self.precondition_inputs(sample, sigma).to(sample.dtype)

    self.is_scale_input_called = True
    return sample

mindone.diffusers.EDMEulerScheduler.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_edm_euler.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.EDMEulerScheduler.set_timesteps(num_inference_steps)

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`

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

def set_timesteps(self, num_inference_steps: int):
    """
    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.
    """
    self.num_inference_steps = num_inference_steps

    ramp = ms.tensor(np.linspace(0, 1, self.num_inference_steps))
    if self.config.sigma_schedule == "karras":
        sigmas = self._compute_karras_sigmas(ramp)
    elif self.config.sigma_schedule == "exponential":
        sigmas = self._compute_exponential_sigmas(ramp)

    sigmas = sigmas.to(ms.float32)
    self.timesteps = self.precondition_noise(sigmas)

    self.sigmas = ops.cat([sigmas, ops.zeros(1)])
    self._step_index = None
    self._begin_index = None

mindone.diffusers.EDMEulerScheduler.step(model_output, timestep, sample, s_churn=0.0, s_tmin=0.0, s_tmax=float('inf'), s_noise=1.0, generator=None, return_dict=False)

Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion process from the learned model outputs (most often the predicted noise).

PARAMETER	DESCRIPTION
model_output	The direct output from learned diffusion model. TYPE: `ms.Tensor`
timestep	The current discrete timestep in the diffusion chain. TYPE: `float`
sample	A current instance of a sample created by the diffusion process. TYPE: `ms.Tensor`
s_churn	TYPE: `float` DEFAULT: 0.0
s_tmin	TYPE: (`float` DEFAULT: 0.0
s_tmax	TYPE: (`float` DEFAULT: float('inf')
s_noise	Scaling factor for noise added to the sample. TYPE: `float`, defaults to 1.0 DEFAULT: 1.0
generator	A random number generator. TYPE: `np.random.Generator`, *optional* DEFAULT: None
return_dict	Whether or not to return a [~schedulers.scheduling_euler_discrete.EDMEulerSchedulerOutput] or tuple. TYPE: `bool` DEFAULT: False

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

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

def step(
    self,
    model_output: ms.Tensor,
    timestep: Union[float, ms.Tensor],
    sample: ms.Tensor,
    s_churn: float = 0.0,
    s_tmin: float = 0.0,
    s_tmax: float = float("inf"),
    s_noise: float = 1.0,
    generator: Optional[np.random.Generator] = None,
    return_dict: bool = False,
) -> Union[EDMEulerSchedulerOutput, Tuple]:
    """
    Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion
    process from the learned model outputs (most often the predicted noise).

    Args:
        model_output (`ms.Tensor`):
            The direct output from learned diffusion model.
        timestep (`float`):
            The current discrete timestep in the diffusion chain.
        sample (`ms.Tensor`):
            A current instance of a sample created by the diffusion process.
        s_churn (`float`):
        s_tmin  (`float`):
        s_tmax  (`float`):
        s_noise (`float`, defaults to 1.0):
            Scaling factor for noise added to the sample.
        generator (`np.random.Generator`, *optional*):
            A random number generator.
        return_dict (`bool`):
            Whether or not to return a [`~schedulers.scheduling_euler_discrete.EDMEulerSchedulerOutput`] or tuple.

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

    if isinstance(timestep, int) or (isinstance(timestep, ms.Tensor) and timestep.dtype in [ms.int32, ms.int64]):
        raise ValueError(
            (
                "Passing integer indices (e.g. from `enumerate(timesteps)`) as timesteps to"
                " `EDMEulerScheduler.step()` is not supported. Make sure to pass"
                " one of the `scheduler.timesteps` as a timestep."
            ),
        )

    if not self.is_scale_input_called:
        logger.warning(
            "The `scale_model_input` function should be called before `step` to ensure correct denoising. "
            "See `StableDiffusionPipeline` for a usage example."
        )

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

    # Upcast to avoid precision issues when computing prev_sample
    sample = sample.to(ms.float32)

    sigma = self.sigmas[self.step_index]

    gamma = min(s_churn / (len(self.sigmas) - 1), 2**0.5 - 1) if s_tmin <= sigma <= s_tmax else 0.0

    noise = randn_tensor(model_output.shape, dtype=model_output.dtype, generator=generator)

    eps = noise * s_noise
    sigma_hat = sigma * (gamma + 1)

    if gamma > 0:
        sample = sample + eps * (sigma_hat**2 - sigma**2) ** 0.5

    # 1. compute predicted original sample (x_0) from sigma-scaled predicted noise
    pred_original_sample = self.precondition_outputs(sample, model_output, sigma_hat)

    # 2. Convert to an ODE derivative
    derivative = (sample - pred_original_sample) / sigma_hat

    dt = self.sigmas[self.step_index + 1] - sigma_hat

    prev_sample = sample + derivative * dt

    # Cast sample back to model compatible dtype
    prev_sample = prev_sample.to(model_output.dtype)

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

    if not return_dict:
        return (prev_sample,)

    return EDMEulerSchedulerOutput(prev_sample=prev_sample, pred_original_sample=pred_original_sample)

mindone.diffusers.schedulers.scheduling_edm_euler.EDMEulerSchedulerOutput dataclass

Bases: BaseOutput

Output class for the scheduler's step function output.

PARAMETER	DESCRIPTION
prev_sample	Computed sample (x_{t-1}) of previous timestep. prev_sample should be used as next model input in the denoising loop. TYPE: `ms.Tensor` of shape `(batch_size, num_channels, height, width)` for images
pred_original_sample	The predicted denoised sample (x_{0}) based on the model output from the current timestep. pred_original_sample can be used to preview progress or for guidance. TYPE: `ms.Tensor` of shape `(batch_size, num_channels, height, width)` for images DEFAULT: None

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

@dataclass
# Copied from diffusers.schedulers.scheduling_ddpm.DDPMSchedulerOutput with DDPM->EulerDiscrete
class EDMEulerSchedulerOutput(BaseOutput):
    """
    Output class for the scheduler's `step` function output.

    Args:
        prev_sample (`ms.Tensor` of shape `(batch_size, num_channels, height, width)` for images):
            Computed sample `(x_{t-1})` of previous timestep. `prev_sample` should be used as next model input in the
            denoising loop.
        pred_original_sample (`ms.Tensor` of shape `(batch_size, num_channels, height, width)` for images):
            The predicted denoised sample `(x_{0})` based on the model output from the current timestep.
            `pred_original_sample` can be used to preview progress or for guidance.
    """

    prev_sample: ms.Tensor
    pred_original_sample: Optional[ms.Tensor] = None