REVIEW 8 cited by
Multistep Consistency Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Diffusion models are relatively easy to train but require many steps to generate samples. Consistency models are far more difficult to train, but generate samples in a single step. In this paper we propose Multistep Consistency Models: A unification between Consistency Models (Song et al., 2023) and TRACT (Berthelot et al., 2023) that can interpolate between a consistency model and a diffusion model: a trade-off between sampling speed and sampling quality. Specifically, a 1-step consistency model is a conventional consistency model whereas a $\infty$-step consistency model is a diffusion model. Multistep Consistency Models work really well in practice. By increasing the sample budget from a single step to 2-8 steps, we can train models more easily that generate higher quality samples, while retaining much of the sampling speed benefits. Notable results are 1.4 FID on Imagenet 64 in 8 step and 2.1 FID on Imagenet128 in 8 steps with consistency distillation, using simple losses without adversarial training. We also show that our method scales to a text-to-image diffusion model, generating samples that are close to the quality of the original model.
Forward citations
Cited by 8 Pith papers
-
Amortized Moment Matching for Visual Generation
Amortized Fréchet Distance uses neural nets to match conditional means and covariances, yielding stronger one-step visual generators than explicit FD-loss or multi-step teachers.
-
Heterogeneous Decentralized Diffusion Models
Isolated experts trained with mixed DDPM and Flow Matching objectives can be fused at inference via deterministic conversion, cutting reported DDM compute ~16× while slightly improving FID and diversity over a homogen...
-
Consistency Deep Equilibrium Models
C-DEQ trains a consistency model to map intermediate solver states directly to the DEQ equilibrium, enabling accurate one-to-few-step inference for deep equilibrium models.
-
Understanding, Accelerating, and Improving MeanFlow Training
Training MeanFlow by first forming instantaneous velocity and short-gap average velocity, then shifting to long gaps, improves 1-NFE ImageNet FID from 3.43 to 2.87 and speeds training by about 2.5x.
-
MACS: Measurement-Aware Consistency Sampling for Inverse Problems
MACS replaces the variance term in aDDIM with a measurement residual, yielding better FID/KID than fast ODE baselines in two-step consistency-model inverse problems.
-
Continuous Semi-Implicit Models
CoSIM extends hierarchical semi-implicit variational inference to continuous time, yielding a simulation-free, multistep consistency-style distillation of pretrained diffusion models.
-
A Continuous-Time Consistency Model for 3D Point Cloud Generation
ConTiCoM-3D trains a continuous-time consistency-style model directly on raw 3D point clouds using flow matching plus Chamfer distance, with one- to two-step generation.
-
SplitMeanFlow: Interval Splitting Consistency in Few-Step Generative Modeling
A purely algebraic interval-splitting consistency objective trains few-step generative models without JVP computations and recovers MeanFlow's differential identity as a special limit.
Discussion (0). Sign in to comment.