通过直接监督原始图像加速可控生成模型训练，提升效果与速度。
Improving Controllable Generation: Faster Training and Better Performance via $x_0$-Supervision
- 直接对干净图像进行监督（x₀-监督），优化训练损失函数。
- 收敛速度最快提升2倍，视觉质量与控制精度同步提高。
- 适合需要快速训练可控生成模型的研究者与开发者。
文本到图像扩散/流模型在视觉保真度和文本对齐方面取得了显著进展，但在用户需要精确控制图像布局时仍受限，因为自然语言难以可靠表达布局信息。可控生成方法通过引入额外条件来增强初始模型，以更易描述场景。以往工作直接使用初始模型的损失函数训练增强网络，虽看似合理，但可能导致训练时间过长。本文通过分析去噪动态，重新审视可控扩散模型的训练目标，提出对原始图像（x₀）进行直接监督或等效重加权扩散损失，可显著加快收敛。在多个控制设置下的实验表明，新方法使收敛速度提升达2倍（基于新指标均值曲线下面积 - mAUCC），同时改善了视觉质量和条件准确性。代码已开源。
原文摘要 · Abstract (English)
Text-to-Image (T2I) diffusion/flow models have recently achieved remarkable progress in visual fidelity and text alignment. However, they remain limited when users need to precisely control image layouts, something that natural language alone cannot reliably express. Controllable generation methods augment the initial T2I model with additional conditions that more easily describe the scene. Prior works straightforwardly train the augmented network with the same loss as the initial network. Although natural at first glance, this can lead to very long training times in some cases before convergence. In this work, we revisit the training objective of controllable diffusion models through a detailed analysis of their denoising dynamics. We show that direct supervision on the clean target image, dubbed $x_0$-supervision, or an equivalent re-weighting of the diffusion loss, yields faster convergence. Experiments on multiple control settings demonstrate that our formulation accelerates convergence by up to 2$\times$ according to our novel metric (mean Area Under the Convergence Curve - mAUCC), while also improving both visual quality and conditioning accuracy. Our code is available at https://github.com/CEA-LIST/x0-supervision
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。