Authors: Jonathan Ho, Ajay Jain, Pieter Abbeel
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.
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-ema-celebahq-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.save("ddpm_generated_image.png")
For more in-detail information, please have a look at the official inference example
If you want to train your own model, please have a look at the official training example # <- TODO(PVP) add link
- Downloads last month