# IPNDMScheduler

`IPNDMScheduler` is a fourth-order Improved Pseudo Linear Multistep scheduler. The original implementation can be found at [crowsonkb/v-diffusion-pytorch](https://github.com/crowsonkb/v-diffusion-pytorch/blob/987f8985e38208345c1959b0ea767a625831cc9b/diffusion/sampling.py#L296).

## IPNDMScheduler[[diffusers.IPNDMScheduler]]

#### diffusers.IPNDMScheduler[[diffusers.IPNDMScheduler]]

```python
diffusers.IPNDMScheduler(num_train_timesteps: int = 1000, trained_betas: numpy.ndarray | list[float] | None = None)
```

[Source](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ipndm.py#L24)

**Parameters:**

num_train_timesteps (`int`, defaults to 1000) : The number of diffusion steps to train the model.

trained_betas (`np.ndarray` or `List[float]`, *optional*) : Pass an array of betas directly to the constructor to bypass `beta_start` and `beta_end`.

A fourth-order Improved Pseudo Linear Multistep scheduler.

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

#### index_for_timestep[[diffusers.IPNDMScheduler.index_for_timestep]]

```python
index_for_timestep(timestep: typing.Union[float, torch.Tensor], schedule_timesteps: typing.Optional[torch.Tensor] = None)
```

[Source](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ipndm.py#L124)

**Parameters:**

timestep (`float` or `torch.Tensor`) : The timestep value to find in the schedule.

schedule_timesteps (`torch.Tensor`, *optional*) : The timestep schedule to search in. If `None`, uses `self.timesteps`.

**Returns:** `int`

The index of the timestep in the schedule. For the very first step, returns the second index if
multiple matches exist to avoid skipping a sigma when starting mid-schedule (e.g., for image-to-image).

Find the index of a given timestep in the timestep schedule.

#### scale_model_input[[diffusers.IPNDMScheduler.scale_model_input]]

```python
scale_model_input(sample: Tensor, *args, **kwargs)
```

[Source](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ipndm.py#L228)

**Parameters:**

sample (`torch.Tensor`) : The input sample.

**Returns:** `torch.Tensor`

A scaled input sample.

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

#### set_begin_index[[diffusers.IPNDMScheduler.set_begin_index]]

```python
set_begin_index(begin_index: int = 0)
```

[Source](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ipndm.py#L85)

**Parameters:**

begin_index (`int`, defaults to `0`) : The begin index for the scheduler.

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

#### set_timesteps[[diffusers.IPNDMScheduler.set_timesteps]]

```python
set_timesteps(num_inference_steps: int, device: typing.Union[str, torch.device, NoneType] = None)
```

[Source](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ipndm.py#L95)

**Parameters:**

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.

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

#### step[[diffusers.IPNDMScheduler.step]]

```python
step(model_output: Tensor, timestep: typing.Union[int, torch.Tensor], sample: Tensor, return_dict: bool = True)
```

[Source](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ipndm.py#L170)

**Parameters:**

model_output (`torch.Tensor`) : The direct output from learned diffusion model.

timestep (`int` or `torch.Tensor`) : The current discrete timestep in the diffusion chain.

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

return_dict (`bool`) : Whether or not to return a [SchedulerOutput](/docs/diffusers/main/en/api/schedulers/dpm_discrete_ancestral#diffusers.schedulers.scheduling_utils.SchedulerOutput) or tuple.

**Returns:** [SchedulerOutput](/docs/diffusers/main/en/api/schedulers/dpm_discrete_ancestral#diffusers.schedulers.scheduling_utils.SchedulerOutput) or `tuple`

If return_dict is `True`, [SchedulerOutput](/docs/diffusers/main/en/api/schedulers/dpm_discrete_ancestral#diffusers.schedulers.scheduling_utils.SchedulerOutput) is returned, otherwise a
tuple is returned where the first element is the sample tensor.

Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with
the linear multistep method. It performs one forward pass multiple times to approximate the solution.

## SchedulerOutput[[diffusers.schedulers.scheduling_utils.SchedulerOutput]]

#### diffusers.schedulers.scheduling_utils.SchedulerOutput[[diffusers.schedulers.scheduling_utils.SchedulerOutput]]

```python
diffusers.schedulers.scheduling_utils.SchedulerOutput(prev_sample: Tensor)
```

[Source](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_utils.py#L66)

**Parameters:**

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.

Base class for the output of a scheduler's `step` function.