REVIEW 4 cited by
Multistep Distillation of Diffusion Models via Moment Matching
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
Signed reviews
read the original abstract
We present a new method for making diffusion models faster to sample. The method distills many-step diffusion models into few-step models by matching conditional expectations of the clean data given noisy data along the sampling trajectory. Our approach extends recently proposed one-step methods to the multi-step case, and provides a new perspective by interpreting these approaches in terms of moment matching. By using up to 8 sampling steps, we obtain distilled models that outperform not only their one-step versions but also their original many-step teacher models, obtaining new state-of-the-art results on the Imagenet dataset. We also show promising results on a large text-to-image model where we achieve fast generation of high resolution images directly in image space, without needing autoencoders or upsamplers.
Forward citations
Cited by 4 Pith papers
-
Fast Video Generation with Sliding Tile Attention
Sliding tile attention (STA) replaces full 3D attention in video diffusion transformers with dense tile-local windows, achieving 1.89x training-free and up to 3.53x fine-tuned end-to-end speedups on HunyuanVideo with ...
-
Diffusion Autoencoders are Scalable Image Tokenizers
A single diffusion L2 loss can train scalable image tokenizers that match or outperform GAN-LPIPS tokenizers for reconstruction and downstream generation.
-
VarDiU: A Variational Diffusive Upper Bound for One-Step Diffusion Distillation
VarDiU optimizes a variational upper bound on the diffusive KL divergence with an unbiased gradient estimator, improving one-step generation on a 2D 40-Gaussian toy benchmark compared with Diff-Instruct.
-
Reinforcement Learning: From Algorithms To Foundation Models
A dissertation uniting the author's published results: non-exploitable Nash-DQN policies and the FightLadder benchmark for games, plus diffusion/consistency-model world models for RL — a compilation rather than new results.
Discussion (0). Continue with ORCID to comment.