Document-to-Markdown (Qwen2-VL + QLoRA)

Fine-tuned on the Nougat dataset for scientific document conversion.

Upload Document Image

Markdown Output

# Present high quality image synthesis results using diffusion probabilistic models

Jonathan Ho

UC Berkeley

jonathanho@berkeley.edu

Ajay Jain

UC Berkeley

ajajj@berkeley.edu

Pieter Abbeel

UC Berkeley

pabbeel@cs.berkeley.edu

## Abstract

We present high quality image synthesis results using diffusion probabilistic 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. Our implementation is available at https://github.com/jonathanho/diffusion.