diffusers/pr_12595/en/api/schedulers/edm_euler.md

# EDMEulerScheduler

The Karras formulation of the Euler scheduler (Algorithm 2) from the [Elucidating the Design Space of Diffusion-Based Generative Models](https://huggingface.co/papers/2206.00364) 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](https://github.com/crowsonkb/k-diffusion/blob/481677d114f6ea445aa009cf5bd7a9cdee909e47/k_diffusion/sampling.py#L51) implementation by [Katherine Crowson](https://github.com/crowsonkb/).


## EDMEulerScheduler[[diffusers.EDMEulerScheduler]]
<div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8">


<docstring><name>class diffusers.EDMEulerScheduler</name><anchor>diffusers.EDMEulerScheduler</anchor><source>https://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/schedulers/scheduling_edm_euler.py#L49</source><parameters>[{"name": "sigma_min", "val": ": float = 0.002"}, {"name": "sigma_max", "val": ": float = 80.0"}, {"name": "sigma_data", "val": ": float = 0.5"}, {"name": "sigma_schedule", "val": ": str = 'karras'"}, {"name": "num_train_timesteps", "val": ": int = 1000"}, {"name": "prediction_type", "val": ": str = 'epsilon'"}, {"name": "rho", "val": ": float = 7.0"}, {"name": "final_sigmas_type", "val": ": str = 'zero'"}]</parameters><paramsdesc>- **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://huggingface.co/papers/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].
- **final_sigmas_type** (`str`, 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.</paramsdesc><paramgroups>0</paramgroups></docstring>

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://huggingface.co/papers/2206.00364

This model inherits from [SchedulerMixin](/docs/diffusers/pr_12595/en/api/schedulers/overview#diffusers.SchedulerMixin) and [ConfigMixin](/docs/diffusers/pr_12595/en/api/configuration#diffusers.ConfigMixin). Check the superclass documentation for the generic
methods the library implements for all schedulers such as loading and saving.





<div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8">


<docstring><name>scale_model_input</name><anchor>diffusers.EDMEulerScheduler.scale_model_input</anchor><source>https://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/schedulers/scheduling_edm_euler.py#L191</source><parameters>[{"name": "sample", "val": ": Tensor"}, {"name": "timestep", "val": ": typing.Union[float, torch.Tensor]"}]</parameters><paramsdesc>- **sample** (`torch.Tensor`) --
  The input sample.
- **timestep** (`int`, *optional*) --
  The current timestep in the diffusion chain.</paramsdesc><paramgroups>0</paramgroups><rettype>`torch.Tensor`</rettype><retdesc>A scaled input sample.</retdesc></docstring>

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.








</div>
<div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8">


<docstring><name>set_begin_index</name><anchor>diffusers.EDMEulerScheduler.set_begin_index</anchor><source>https://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/schedulers/scheduling_edm_euler.py#L153</source><parameters>[{"name": "begin_index", "val": ": int = 0"}]</parameters><paramsdesc>- **begin_index** (`int`) --
  The begin index for the scheduler.</paramsdesc><paramgroups>0</paramgroups></docstring>

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




</div>
<div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8">


<docstring><name>set_timesteps</name><anchor>diffusers.EDMEulerScheduler.set_timesteps</anchor><source>https://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/schedulers/scheduling_edm_euler.py#L215</source><parameters>[{"name": "num_inference_steps", "val": ": int = None"}, {"name": "device", "val": ": typing.Union[str, torch.device] = None"}, {"name": "sigmas", "val": ": typing.Union[torch.Tensor, typing.List[float], NoneType] = None"}]</parameters><paramsdesc>- **num_inference_steps** (`int`) --
  The number of diffusion steps used when generating samples with a pre-trained model.
- **device** (`str` or `torch.device`, *optional*) --
  The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
- **sigmas** (`Union[torch.Tensor, List[float]]`, *optional*) --
  Custom sigmas to use for the denoising process. If not defined, the default behavior when
  `num_inference_steps` is passed will be used.</paramsdesc><paramgroups>0</paramgroups></docstring>

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




</div>
<div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8">


<docstring><name>step</name><anchor>diffusers.EDMEulerScheduler.step</anchor><source>https://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/schedulers/scheduling_edm_euler.py#L310</source><parameters>[{"name": "model_output", "val": ": Tensor"}, {"name": "timestep", "val": ": typing.Union[float, torch.Tensor]"}, {"name": "sample", "val": ": Tensor"}, {"name": "s_churn", "val": ": float = 0.0"}, {"name": "s_tmin", "val": ": float = 0.0"}, {"name": "s_tmax", "val": ": float = inf"}, {"name": "s_noise", "val": ": float = 1.0"}, {"name": "generator", "val": ": typing.Optional[torch._C.Generator] = None"}, {"name": "return_dict", "val": ": bool = True"}, {"name": "pred_original_sample", "val": ": typing.Optional[torch.Tensor] = None"}]</parameters><paramsdesc>- **model_output** (`torch.Tensor`) --
  The direct output from learned diffusion model.
- **timestep** (`float`) --
  The current discrete timestep in the diffusion chain.
- **sample** (`torch.Tensor`) --
  A current instance of a sample created by the diffusion process.
- **s_churn** (`float`) --
- **s_tmin**  (`float`) --
- **s_tmax**  (`float`) --
- **s_noise** (`float`, defaults to 1.0) --
  Scaling factor for noise added to the sample.
- **generator** (`torch.Generator`, *optional*) --
  A random number generator.
- **return_dict** (`bool`) --
  Whether or not to return a `~schedulers.scheduling_euler_discrete.EDMEulerSchedulerOutput` or tuple.</paramsdesc><paramgroups>0</paramgroups><rettype>`~schedulers.scheduling_euler_discrete.EDMEulerSchedulerOutput` or `tuple`</rettype><retdesc>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.</retdesc></docstring>

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).








</div></div>

## EDMEulerSchedulerOutput[[diffusers.schedulers.scheduling_edm_euler.EDMEulerSchedulerOutput]]
<div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8">


<docstring><name>class diffusers.schedulers.scheduling_edm_euler.EDMEulerSchedulerOutput</name><anchor>diffusers.schedulers.scheduling_edm_euler.EDMEulerSchedulerOutput</anchor><source>https://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/schedulers/scheduling_edm_euler.py#L32</source><parameters>[{"name": "prev_sample", "val": ": Tensor"}, {"name": "pred_original_sample", "val": ": typing.Optional[torch.Tensor] = None"}]</parameters><paramsdesc>- **prev_sample** (`torch.Tensor` of shape `(batch_size, num_channels, height, width)` for images) --
  Computed sample `(x_{t-1})` of previous timestep. `prev_sample` should be used as next model input in the
  denoising loop.
- **pred_original_sample** (`torch.Tensor` of shape `(batch_size, num_channels, height, width)` for images) --
  The predicted denoised sample `(x_{0})` based on the model output from the current timestep.
  `pred_original_sample` can be used to preview progress or for guidance.</paramsdesc><paramgroups>0</paramgroups></docstring>

Output class for the scheduler's `step` function output.




</div>

<EditOnGithub source="https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/schedulers/edm_euler.md" />