Ddpm Celebahq 256

🚀 Denoising Diffusion Probabilistic Models (DDPM)

This project presents high - quality image synthesis results using diffusion probabilistic models, offering a new approach to latent variable models inspired by non - equilibrium thermodynamics.

🚀 Quick Start

Inference

DDPM models can use discrete noise schedulers such as:

• scheduling_ddpm
• scheduling_ddim
• scheduling_pndm

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.

Training

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

💻 Usage Examples

Basic Usage

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

model_id = "google/ddpm-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[0].save("ddpm_generated_image.png")

Advanced Usage

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

📚 Documentation

Paper

Paper: Denoising Diffusion Probabilistic Models

Authors

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.

📄 License

This project is licensed under the Apache 2.0 license.

Samples