ddpm-cifar10-32 / README.md
patrickvonplaten's picture
Update README.md
ff056c9
|
raw
history blame
2.98 kB
metadata
license: apache-2.0
tags:
  - pytorch
  - diffusers
  - unconditional-image-generation

Denoising Diffusion Probabilistic Models (DDPM)

Paper: Denoising Diffusion Probabilistic Models

Authors: Jonathan Ho, Ajay Jain, Pieter Abbeel

Abstract:

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.

Inference

DDPM models can use discrete noise schedulers such as:

for inference. Note that while the ddpm scheduler yields the highest quality, it also takes the longest. For a good trade-off between quality and inference speed you might want to consider the ddim or pndm schedulers instead.

See the following code:

# !pip install diffusers
from diffusers import DDPMPipeline, DDIMPipeline, PNDMPipeline

model_id = "google/ddpm-cifar10-32"

# load model and scheduler
ddpm = DDPMPipeline.from_pretrained(model_id)  # you can replace DDPMPipeline with DDIMPipeline or PNDMPipeline for faster inference

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

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

For more in-detail information, please have a look at the official inference example

Training

If you want to train your own model, please have a look at the official training example

Samples

  1. sample_1
  2. sample_2
  3. sample_3
  4. sample_4