# DDPM

## DDPM

[Denoising Diffusion Probabilistic Models](https://huggingface.co/papers/2006.11239) (DDPM) by Jonathan Ho, Ajay Jain and Pieter Abbeel proposes a diffusion based model of the same name. In the 🌍 Diffusers library, DDPM refers to the *discrete denoising scheduler* from the paper as well as the pipeline.

The abstract from the paper is:

*We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding. On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46 and a state-of-the-art FID score of 3.17. On 256x256 LSUN, we obtain sample quality similar to ProgressiveGAN.*

The original codebase can be found at [hohonathanho/diffusion](https://github.com/hojonathanho/diffusion).

Make sure to check out the Schedulers [guide](https://huggingface.co/using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](https://huggingface.co/using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.

## DDPMPipeline

#### class diffusers.DDPMPipeline

[\<source>](https://github.com/huggingface/diffusers/blob/v0.21.0/src/diffusers/pipelines/ddpm/pipeline_ddpm.py#L24)

( unetscheduler )

Parameters

* **unet** ([UNet2DModel](https://huggingface.co/docs/diffusers/v0.21.0/en/api/models/unet2d#diffusers.UNet2DModel)) — A `UNet2DModel` to denoise the encoded image latents.
* **scheduler** ([SchedulerMixin](https://huggingface.co/docs/diffusers/v0.21.0/en/api/schedulers/overview#diffusers.SchedulerMixin)) — A scheduler to be used in combination with `unet` to denoise the encoded image. Can be one of [DDPMScheduler](https://huggingface.co/docs/diffusers/v0.21.0/en/api/schedulers/ddpm#diffusers.DDPMScheduler), or [DDIMScheduler](https://huggingface.co/docs/diffusers/v0.21.0/en/api/schedulers/ddim#diffusers.DDIMScheduler).

Pipeline for image generation.

This model inherits from [DiffusionPipeline](https://huggingface.co/docs/diffusers/v0.21.0/en/api/pipelines/overview#diffusers.DiffusionPipeline). Check the superclass documentation for the generic methods implemented for all pipelines (downloading, saving, running on a particular device, etc.).

**\_\_call\_\_**

[\<source>](https://github.com/huggingface/diffusers/blob/v0.21.0/src/diffusers/pipelines/ddpm/pipeline_ddpm.py#L44)

( batch\_size: int = 1generator: typing.Union\[torch.\_C.Generator, typing.List\[torch.\_C.Generator], NoneType] = Nonenum\_inference\_steps: int = 1000output\_type: typing.Optional\[str] = 'pil'return\_dict: bool = True ) → [ImagePipelineOutput](https://huggingface.co/docs/diffusers/v0.21.0/en/api/pipelines/latent_diffusion_uncond#diffusers.ImagePipelineOutput) or `tuple`

Parameters

* **batch\_size** (`int`, *optional*, defaults to 1) — The number of images to generate.
* **generator** (`torch.Generator`, *optional*) — A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make generation deterministic.
* **num\_inference\_steps** (`int`, *optional*, defaults to 1000) — The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.
* **output\_type** (`str`, *optional*, defaults to `"pil"`) — The output format of the generated image. Choose between `PIL.Image` or `np.array`.
* **return\_dict** (`bool`, *optional*, defaults to `True`) — Whether or not to return a [ImagePipelineOutput](https://huggingface.co/docs/diffusers/v0.21.0/en/api/pipelines/latent_diffusion_uncond#diffusers.ImagePipelineOutput) instead of a plain tuple.

Returns

[ImagePipelineOutput](https://huggingface.co/docs/diffusers/v0.21.0/en/api/pipelines/latent_diffusion_uncond#diffusers.ImagePipelineOutput) or `tuple`

If `return_dict` is `True`, [ImagePipelineOutput](https://huggingface.co/docs/diffusers/v0.21.0/en/api/pipelines/latent_diffusion_uncond#diffusers.ImagePipelineOutput) is returned, otherwise a `tuple` is returned where the first element is a list with the generated images

The call function to the pipeline for generation.

Example:

Copied

```
>>> from diffusers import DDPMPipeline

>>> # load model and scheduler
>>> pipe = DDPMPipeline.from_pretrained("google/ddpm-cat-256")

>>> # run pipeline in inference (sample random noise and denoise)
>>> image = pipe().images[0]

>>> # save image
>>> image.save("ddpm_generated_image.png")
```

### ImagePipelineOutput

#### class diffusers.ImagePipelineOutput

[\<source>](https://github.com/huggingface/diffusers/blob/v0.21.0/src/diffusers/pipelines/pipeline_utils.py#L112)

( images: typing.Union\[typing.List\[PIL.Image.Image], numpy.ndarray] )

Parameters

* **images** (`List[PIL.Image.Image]` or `np.ndarray`) — List of denoised PIL images of length `batch_size` or NumPy array of shape `(batch_size, height, width, num_channels)`.

Output class for image pipelines.