added pndm docs (#391)

for issue  #293

docs/source/api/pipelines/pndm.mdx

@@ -1 +1,24 @@
-# GLIDE MODEL
+# PNDM
+
+## Overview
+
+[Pseudo Numerical methods for Diffusion Models on manifolds](https://arxiv.org/abs/2202.09778) (PNDM) by  Luping Liu, Yi Ren, Zhijie Lin and Zhou Zhao.
+
+The abstract of the paper is the following:
+
+Denoising Diffusion Probabilistic Models (DDPMs) can generate high-quality samples such as image and audio samples. However, DDPMs require hundreds to thousands of iterations to produce final samples. Several prior works have successfully accelerated DDPMs through adjusting the variance schedule (e.g., Improved Denoising Diffusion Probabilistic Models) or the denoising equation (e.g., Denoising Diffusion Implicit Models (DDIMs)). However, these acceleration methods cannot maintain the quality of samples and even introduce new noise at a high speedup rate, which limit their practicability. To accelerate the inference process while keeping the sample quality, we provide a fresh perspective that DDPMs should be treated as solving differential equations on manifolds. Under such a perspective, we propose pseudo numerical methods for diffusion models (PNDMs). Specifically, we figure out how to solve differential equations on manifolds and show that DDIMs are simple cases of pseudo numerical methods. We change several classical numerical methods to corresponding pseudo numerical methods and find that the pseudo linear multi-step method is the best in most situations. According to our experiments, by directly using pre-trained models on Cifar10, CelebA and LSUN, PNDMs can generate higher quality synthetic images with only 50 steps compared with 1000-step DDIMs (20x speedup), significantly outperform DDIMs with 250 steps (by around 0.4 in FID) and have good generalization on different variance schedules. 
+
+The original codebase can be found [here](https://github.com/luping-liu/PNDM).
+
+## Available Pipelines:
+
+| Pipeline | Tasks | Colab
+|---|---|:---:|
+| [pipeline_pndm.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/pndm/pipeline_pndm.py) | *Unconditional Image Generation* | - |
+
+
+## API
+
+[[autodoc]] pipelines.pndm.pipeline_pndm.PNDMPipeline
+    - __call__
+

src/diffusers/pipelines/pndm/pipeline_pndm.py

@@ -25,6 +25,16 @@ from ...schedulers import PNDMScheduler
 
 
 class PNDMPipeline(DiffusionPipeline):
+    r"""
+    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the
+    library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)
+
+    Parameters:
+        unet (:obj:`UNet2DModel`): U-Net architecture to denoise the encoded image latents.
+        scheduler ([`SchedulerMixin`]):
+            The `PNDMScheduler` to be used in combination with `unet` to denoise the encoded image.
+    """
+
     unet: UNet2DModel
     scheduler: PNDMScheduler
 
@@ -43,6 +53,23 @@ class PNDMPipeline(DiffusionPipeline):
         return_dict: bool = True,
         **kwargs,
     ) -> Union[ImagePipelineOutput, Tuple]:
+        r"""
+        Args:
+            batch_size (:obj:`int`, `optional`, defaults to 1): The number of images to generate.
+            num_inference_steps (:
+                obj:`int`, `optional`, defaults to 50): The number of denoising steps. More denoising steps usually
+                lead to a higher quality image at the expense of slower inference.
+            generator (:
+                obj:`torch.Generator`, `optional`): A [torch
+                generator](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make generation
+                deterministic.
+            output_type (:
+                obj:`str`, `optional`, defaults to :obj:`"pil"`): The output format of the generate image. Choose
+                between [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `nd.array`.
+            return_dict (:
+                obj:`bool`, `optional`, defaults to :obj:`True`): Whether or not to return a
+                [`~pipeline_utils.ImagePipelineOutput`] instead of a plain tuple.
+        """
         # For more information on the sampling method you can take a look at Algorithm 2 of
         # the official paper: https://arxiv.org/pdf/2202.09778.pdf