While recent text-to-video (T2V) diffusion models have achieved impressive quality and prompt alignment, they often produce low-diversity outputs when sampling multiple videos from a single text prompt. We tackle this challenge by formulating it as a set-level policy optimization problem, with the goal of training a policy that can cover the diverse range of plausible outcomes for a given prompt. To address this, we introduce DPP-GRPO, a novel framework for diverse video generation that combines Determinantal Point Processes (DPPs) and Group Relative Policy Optimization (GRPO) theories to enforce explicit reward on diverse generations. Our objective turns diversity into an explicit signal by imposing diminishing returns on redundant samples (via DPP) while supplies groupwise feedback over candidate sets (via GRPO). Our framework is plug-and-play and model-agnostic, and encourages diverse generations across visual appearance, camera motions, and scene structure without sacrificing prompt fidelity or perceptual quality. We implement our method on WAN and CogVideoX, and show that our method consistently improves video diversity on state-of-the-art benchmarks such as VBench, VideoScore, and human preference studies. Moreover, we release our code and a new benchmark dataset of 30,000 diverse prompts to support future research.
翻译:尽管近期文本到视频(T2V)扩散模型在生成质量和提示对齐方面取得了显著进展,但在从单一文本提示采样多个视频时,其输出往往缺乏多样性。我们将此问题建模为集合层面的策略优化问题,旨在训练一个能够覆盖给定提示下多种合理结果的策略。为此,我们提出了DPP-GRPO,一种结合行列式点过程(DPPs)与分组相对策略优化(GRPO)理论的多样化视频生成新框架,通过对多样化生成施加显式奖励来解决该问题。我们的目标通过以下方式将多样性转化为显式信号:对冗余样本施加收益递减约束(通过DPP实现),同时对候选集合提供分组反馈(通过GRPO实现)。该框架具备即插即用和模型无关的特性,能够在视觉外观、摄像机运动和场景结构方面促进多样化生成,且不损害提示保真度或感知质量。我们在WAN和CogVideoX上实现了该方法,结果表明,在VBench、VideoScore等前沿基准测试及人类偏好研究中,我们的方法持续提升了视频多样性。此外,我们开源了代码并发布了包含30,000个多样化提示的新基准数据集,以支持未来研究。