Speed up the inference of diffusion models via shortcut MCMC sampling
This addresses the computational bottleneck for users of diffusion models in image synthesis, though it appears incremental.
The paper tackles the slow inference problem in diffusion models by proposing a shortcut MCMC sampling algorithm that balances training and inference while maintaining image quality, with initial experiments showing promising results.
Diffusion probabilistic models have generated high quality image synthesis recently. However, one pain point is the notorious inference to gradually obtain clear images with thousands of steps, which is time consuming compared to other generative models. In this paper, we present a shortcut MCMC sampling algorithm, which balances training and inference, while keeping the generated data's quality. In particular, we add the global fidelity constraint with shortcut MCMC sampling to combat the local fitting from diffusion models. We do some initial experiments and show very promising results. Our implementation is available at https://github.com//vividitytech/diffusion-mcmc.git.