Shortcut models enable high-quality single or few-step sampling in diffusion models with one network and training phase by conditioning on desired step size.
A comprehensive survey on knowledge distillation of diffusion models.arXiv preprint arXiv:2304.04262
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
A new residual-sampling scheme for diffusion models permits block verification and yields up to 6.3% speedup via a heuristic self-speculative drafter that needs no training.
PPM derives a tractable gradient for exact KL optimization in diffusion variational inversion to achieve unbiased posterior matching without heuristic approximations.
DriftXpress approximates the attraction field of drifting models with a Nyström landmark projection, reducing training time by 2.6–6.7× at comparable FID.
citing papers explorer
-
One Step Diffusion via Shortcut Models
Shortcut models enable high-quality single or few-step sampling in diffusion models with one network and training phase by conditioning on desired step size.
-
Accelerating Speculative Diffusions via Block Verification
A new residual-sampling scheme for diffusion models permits block verification and yields up to 6.3% speedup via a heuristic self-speculative drafter that needs no training.
-
Unbiased Diffusion Variational Inversion via Principled Posterior Matching
PPM derives a tractable gradient for exact KL optimization in diffusion variational inversion to achieve unbiased posterior matching without heuristic approximations.
-
DriftXpress: Faster Drifting Models via Projected RKHS Fields
DriftXpress approximates the attraction field of drifting models with a Nyström landmark projection, reducing training time by 2.6–6.7× at comparable FID.