Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidance

Understand

Diffusion models have achieved unprecedented performance in generative modeling.

• The commonly-adopted formulation of the latent code of diffusion models is a sequence of gradually denoised samples, as opposed to the simpler (e.g., Gaussian) latent space of GANs, VAEs, and normalizing flows.
• This paper provides an alternative, Gaussian formulation of the latent space of various diffusion models, as well as an invertible DPM-Encoder that maps images into the latent space.
• While our formulation is purely based on the definition of diffusion models, we demonstrate several intriguing consequences.