发表机构
The University of Texas at Austin; Google/YouTube; University of Colorado Boulder（德克萨斯大学奥斯汀分校; 谷歌/YouTube; 科罗拉多大学博尔德分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出无需训练的LumaGuide框架，通过在采样时直接塑造输出分布，实现扩散模型的可控生成，可用于HDR及视频生成，无需重新训练模型。
AI 中文摘要
预训练的扩散模型能够生成逼真图像，但受训练数据统计偏差限制，生成高动态范围（HDR）内容的能力有限。本研究提出LumaGuide，一种用于扩散模型分布塑造的无需训练的框架。该框架不修改模型参数，而是通过基于可微分能量的引导来控制采样过程，使其匹配目标特征分布。针对HDR生成，我们在感知均匀的PQ空间中控制亮度分布以实例化该框架。结果表明，对齐亮度直方图足以诱导与HDR一致的行为，包括连贯的高光和保留的阴影细节，同时保持语义保真度。除HDR外，LumaGuide还能通过数据驱动预设、参考图像或文本驱动预测器灵活指定目标分布，并自然扩展到具有时间一致性约束的视频生成。更广泛地说，本研究证明可通过在采样时直接塑造输出分布来实现可控生成，无需重新训练扩散模型。
英文摘要
Pretrained diffusion models generate realistic images but are constrained by the statistical biases of their training data, limiting their ability to produce high dynamic range (HDR) content. In this work, we introduce LumaGuide, a training-free framework for distribution shaping in diffusion models. Instead of modifying model parameters, LumaGuide steers the sampling process to match target feature distributions via differentiable energy-based guidance. We instantiate this framework for HDR generation by controlling luminance distributions in perceptually uniform PQ space. Our results show that aligning luminance histograms is sufficient to induce HDR-consistent behavior, including coherent highlights and preserved shadow detail, while maintaining semantic fidelity. Beyond HDR, LumaGuide enables flexible specification of target distributions through data-driven presets, reference images, or text-driven predictors, and extends naturally to video generation with temporal consistency constraints. More broadly, our work demonstrates that controllable generation can be achieved by directly shaping output distributions at sampling time, without retraining diffusion models.
