a class of latent variable models inspired by considerations from nonequilibrium thermodynamics.
~
Here we learn the real application for prompt based image synthesis:
HO, Jonathan, JAIN, Ajay and ABBEEL, Pieter, 2020. Denoising Diffusion Probabilistic Models. In: Advances in Neural Information Processing Systems. Online. Curran Associates, Inc. 2020. p. 6840–6851. [Accessed 19 January 2023]. Available from: https://proceedings.neurips.cc/paper/2020/hash/4c5bcfec8584af0d967f1ab10179ca4b-Abstract.html
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.