轉移模型：重新思考生成式學習目標

摘要

生成模型领域存在一个根本性的困境：迭代扩散模型能够实现卓越的保真度，但需付出巨大的计算成本，而高效的少步替代方案则受限于一个难以突破的质量上限。这种生成步骤与输出质量之间的冲突源于训练目标的局限性，这些目标要么专注于无限小的动态（PF-ODEs），要么直接预测端点。我们通过引入一个精确的连续时间动态方程来解决这一挑战，该方程解析地定义了跨越任何有限时间间隔的状态转移。这催生了一种新的生成范式——转移模型（Transition Models, TiM），它能够适应任意步长的转移，从单步跨越到多步的精细调整，无缝贯穿生成轨迹。尽管仅拥有8.65亿参数，TiM在所有评估步数下均实现了最先进的性能，超越了如SD3.5（80亿参数）和FLUX.1（120亿参数）等领先模型。重要的是，与以往的少步生成器不同，TiM在采样预算增加时展现出单调的质量提升。此外，采用我们的原生分辨率策略时，TiM在高达4096x4096的分辨率下提供了卓越的保真度。

English

A fundamental dilemma in generative modeling persists: iterative diffusion models achieve outstanding fidelity, but at a significant computational cost, while efficient few-step alternatives are constrained by a hard quality ceiling. This conflict between generation steps and output quality arises from restrictive training objectives that focus exclusively on either infinitesimal dynamics (PF-ODEs) or direct endpoint prediction. We address this challenge by introducing an exact, continuous-time dynamics equation that analytically defines state transitions across any finite time interval. This leads to a novel generative paradigm, Transition Models (TiM), which adapt to arbitrary-step transitions, seamlessly traversing the generative trajectory from single leaps to fine-grained refinement with more steps. Despite having only 865M parameters, TiM achieves state-of-the-art performance, surpassing leading models such as SD3.5 (8B parameters) and FLUX.1 (12B parameters) across all evaluated step counts. Importantly, unlike previous few-step generators, TiM demonstrates monotonic quality improvement as the sampling budget increases. Additionally, when employing our native-resolution strategy, TiM delivers exceptional fidelity at resolutions up to 4096x4096.

轉移模型：重新思考生成式學習目標

Transition Models: Rethinking the Generative Learning Objective

摘要

Support