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-cat-256"
# 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()["sample"]
# save image
image[0].save("ddpm_generated_image.png")
For more in-detail information, please have a look at the official inference example # <- TODO(PVP) add link
Training
If you want to train your own model, please have a look at the official training example # <- TODO(PVP) add link
