Gaussian Mixture Solvers for Diffusion Models. (arXiv:2311.00941v1 [cs.LG])

Recently, diffusion models have achieved great success in generative tasks.
Sampling from diffusion models is equivalent to solving the reverse diffusion
stochastic differential equations (SDEs) or the corresponding probability flow
ordinary differential equations (ODEs). In comparison, SDE-based solvers can
generate samples of higher quality and are suited for image translation tasks
like stroke-based synthesis. During inference, however, existing SDE-based
solvers are severely constrained by the efficiency-effectiveness dilemma. Our
investigation suggests that this is because the Gaussian assumption in the
reverse …

arxiv comparison differential diffusion diffusion models flow generate generative image ordinary probability quality sampling stochastic success tasks translation