Pith. sign in

REVIEW 1 cited by

Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy

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

arxiv 2410.09873 v1 pith:ZFIOE272 submitted 2024-10-13 cs.CV

classification cs.CV
keywords denoisingdiffusionnoiseprocessmodelspredictionresultsdifference
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Diffusion models have recently achieved great success in the synthesis of high-quality images and videos. However, the existing denoising techniques in diffusion models are commonly based on step-by-step noise predictions, which suffers from high computation cost, resulting in a prohibitive latency for interactive applications. In this paper, we propose AdaptiveDiffusion to relieve this bottleneck by adaptively reducing the noise prediction steps during the denoising process. Our method considers the potential of skipping as many noise prediction steps as possible while keeping the final denoised results identical to the original full-step ones. Specifically, the skipping strategy is guided by the third-order latent difference that indicates the stability between timesteps during the denoising process, which benefits the reusing of previous noise prediction results. Extensive experiments on image and video diffusion models demonstrate that our method can significantly speed up the denoising process while generating identical results to the original process, achieving up to an average 2~5x speedup without quality degradation.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SADA: Stability-guided Adaptive Diffusion Acceleration

    cs.LG 2025-07 conditional novelty 6.0 of 10

    SADA accelerates ODE-based generative model sampling by adaptively combining step skipping and token pruning through a stability criterion, giving about 1.8 times speedup with minor fidelity loss.

Pith tools