Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal Iterations

Guardado en:
Bibliografiske detaljer
Udgivet i:arXiv.org (Dec 11, 2024), p. n/a
Hovedforfatter: Nikil Roashan Selvam
Andre forfattere: Merchant, Amil, Ermon, Stefano
Udgivet:
Cornell University Library, arXiv.org
Fag:
Online adgang:Citation/Abstract
Full text outside of ProQuest
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!

MARC

LEADER 00000nab a2200000uu 4500
001 3143450415
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3143450415 
045 0 |b d20241211 
100 1 |a Nikil Roashan Selvam 
245 1 |a Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal Iterations 
260 |b Cornell University Library, arXiv.org  |c Dec 11, 2024 
513 |a Working Paper 
520 3 |a In diffusion models, samples are generated through an iterative refinement process, requiring hundreds of sequential model evaluations. Several recent methods have introduced approximations (fewer discretization steps or distillation) to trade off speed at the cost of sample quality. In contrast, we introduce Self-Refining Diffusion Samplers (SRDS) that retain sample quality and can improve latency at the cost of additional parallel compute. We take inspiration from the Parareal algorithm, a popular numerical method for parallel-in-time integration of differential equations. In SRDS, a quick but rough estimate of a sample is first created and then iteratively refined in parallel through Parareal iterations. SRDS is not only guaranteed to accurately solve the ODE and converge to the serial solution but also benefits from parallelization across the diffusion trajectory, enabling batched inference and pipelining. As we demonstrate for pre-trained diffusion models, the early convergence of this refinement procedure drastically reduces the number of steps required to produce a sample, speeding up generation for instance by up to 1.7x on a 25-step StableDiffusion-v2 benchmark and up to 4.3x on longer trajectories. 
653 |a Parallel processing 
653 |a Samplers 
653 |a Algorithms 
653 |a Diffusion rate 
653 |a Refining 
653 |a Differential equations 
653 |a Numerical methods 
653 |a Time integration 
700 1 |a Merchant, Amil 
700 1 |a Ermon, Stefano 
773 0 |t arXiv.org  |g (Dec 11, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3143450415/abstract/embedded/ZKJTFFSVAI7CB62C?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2412.08292