让图像生成精准匹配指定风格，只需一句风格提示。
SPG: Style-Prompting Guidance for Style-Specific Content Creation
- 用风格噪声向量引导扩散过程，实现风格可控生成。
- 结合无分类器引导，同时保证内容准确与风格一致。
- 兼容ControlNet等工具，适合需要精细控制的创作者。
尽管近期文本到图像（T2I）扩散模型在对齐生成图像与文本提示方面表现优异，但控制输出图像的视觉风格仍具挑战性。本文提出风格提示引导（SPG），一种面向特定风格图像生成的新采样策略。SPG构建风格噪声向量，并利用其相对于无条件噪声的方向偏移，引导扩散过程趋向目标风格分布。通过将SPG与无分类器引导（CFG）结合，方法在保持语义准确性的同时实现风格一致性。SPG方法简单、鲁棒，且兼容如ControlNet和IPAdapter等可控框架，具备实际应用价值与广泛适用性。大量实验表明，该方法在性能和通用性上优于现有最先进方法。代码已开源：https://github.com/Rumbling281441/SPG。
原文摘要 · Abstract (English)
Although recent text-to-image (T2I) diffusion models excel at aligning generated images with textual prompts, controlling the visual style of the output remains a challenging task. In this work, we propose Style-Prompting Guidance (SPG), a novel sampling strategy for style-specific image generation. SPG constructs a style noise vector and leverages its directional deviation from unconditional noise to guide the diffusion process toward the target style distribution. By integrating SPG with Classifier-Free Guidance (CFG), our method achieves both semantic fidelity and style consistency. SPG is simple, robust, and compatible with controllable frameworks like ControlNet and IPAdapter, making it practical and widely applicable. Extensive experiments demonstrate the effectiveness and generality of our approach compared to state-of-the-art methods. Code is available at https://github.com/Rumbling281441/SPG.
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。