让图像生成自动学习最优引导强度，减少伪影，提升图文一致
Adversarial Learning of Classifier-Free Guidance Schedules
- 用判别器估计真实与引导分布的密度比，动态生成引导强度
- 在多个文本到图像基准上超越静态引导和已有动态方法
- 适合追求高精度图文对齐的生成模型研究者
现代文本到图像扩散模型依赖无分类器引导（CFG）实现高图像保真度与文本对齐。然而，传统CFG通常在所有时间步、样本和条件下采用固定全局引导强度，这一设定常不理想，可能导致伪影。尽管时变引导调度可提升质量，但手工设计困难且依赖具体应用。本文将引导调度学习为扩散时间、条件信息及当前噪声样本的函数，以更好对齐生成图像与文本提示。我们将其建模为密度比估计问题：训练一个判别器估计真实与引导边际分布的时间相关对数密度比，同时轻量级生成网络预测状态相关的最优引导强度。实验表明，该方法在文本到图像生成基准上优于启发式静态引导及现有动态引导学习方法。
原文摘要 · Abstract (English)
Modern text-to-image diffusion models rely on classifier-free guidance (CFG) to achieve high image fidelity and text alignment. However, CFG typically applies a static, global scale across all timesteps, samples, and conditions -- a choice that is generally suboptimal and can introduce artifacts, as different states may benefit from different levels of guidance. While time-varying schedules are known to improve quality, designing them by hand is non-trivial and application-dependent. In this paper, we learn the guidance schedule as a function of diffusion time, conditioning and the current noisy sample, in order to better align sampled images with the text prompt. We frame this as a density ratio estimation problem: a discriminator is trained to estimate the time-dependent log-density ratio between the true and guided marginal distributions, while a lightweight generator network predicts the optimal, state-dependent guidance scale. Empirically, our approach outperforms both heuristic CFG schedules and prior methods for learning dynamic guidance on text-to-image generation benchmarks.
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。