让图像生成更精准匹配文本提示，解决漏元素和概念混淆问题。
SAGA: Learning Signal-Aligned Distributions for Improved Text-to-Image Generation
- 在去噪过程中显式建模信号成分，实现精细控制
- 无需训练即可提升生成图像与文本的对齐精度
- 兼容现有扩散模型和流匹配架构，支持框定条件
当前顶尖的文本到图像模型虽视觉效果出色，但常因与文本提示对齐不准，导致关键元素缺失或不同概念意外融合。本文提出一种新方法，学习以目标提示为条件的高成功率分布，确保生成图像忠实反映对应提示。该方法在去噪过程中显式建模信号成分，实现细粒度控制，缓解过优化和分布外伪影问题。框架无需训练，可无缝集成至现有扩散模型与流匹配架构，并支持边界框等额外条件模态以增强空间对齐。大量实验表明，该方法优于当前最先进水平。代码已开源于 https://github.com/grimalPaul/gsn-factory。
原文摘要 · Abstract (English)
State-of-the-art text-to-image models produce visually impressive results but often struggle with precise alignment to text prompts, leading to missing critical elements or unintended blending of distinct concepts. We propose a novel approach that learns a high-success-rate distribution conditioned on a target prompt, ensuring that generated images faithfully reflect the corresponding prompts. Our method explicitly models the signal component during the denoising process, offering fine-grained control that mitigates over-optimization and out-of-distribution artifacts. Moreover, our framework is training-free and seamlessly integrates with both existing diffusion and flow matching architectures. It also supports additional conditioning modalities -- such as bounding boxes -- for enhanced spatial alignment. Extensive experiments demonstrate that our approach outperforms current state-of-the-art methods. The code is available at https://github.com/grimalPaul/gsn-factory.
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。