用一键风格对齐提升大图生成质量，解决拼接缝隙与风格不一问题。
Guided and Variance-Corrected Fusion with One-shot Style Alignment for Large-Content Image Generation
- 加权融合抑制远距离区域干扰，减少拼接痕迹。
- 后置方差校正使扩散模型输出更准确，提升图像一致性。
- 无需额外计算，一键调整噪声实现全局风格统一，适合快速部署。
使用小型扩散模型生成大尺寸图像日益流行，因训练大型模型成本过高。常见方法是分块生成重叠图像块并拼接成大图，但现有方法常出现明显瑕疵，如接缝、物体和风格不一致。为此，我们提出引导融合（GF），通过加权平均重叠区域减轻远距离区域的负面影响；提出方差校正融合（VCF），在平均后修正数据方差，提升去噪扩散概率模型的融合精度；还提出一键风格对齐（SA），通过调整初始噪声生成连贯风格，无额外计算开销。大量实验表明，所提融合方法显著提升生成图像质量。该方法可作为即插即用模块，广泛应用于其他基于拼接的图像生成方法中。代码已开源。
原文摘要 · Abstract (English)
Producing large images using small diffusion models is gaining increasing popularity, as the cost of training large models could be prohibitive. A common approach involves jointly generating a series of overlapped image patches and obtaining large images by merging adjacent patches. However, results from existing methods often exhibit noticeable artifacts, e.g., seams and inconsistent objects and styles. To address the issues, we proposed Guided Fusion (GF), which mitigates the negative impact from distant image regions by applying a weighted average to the overlapping regions. Moreover, we proposed Variance-Corrected Fusion (VCF), which corrects data variance at post-averaging, generating more accurate fusion for the Denoising Diffusion Probabilistic Model. Furthermore, we proposed a one-shot Style Alignment (SA), which generates a coherent style for large images by adjusting the initial input noise without adding extra computational burden. Extensive experiments demonstrated that the proposed fusion methods improved the quality of the generated image significantly. The proposed method can be widely applied as a plug-and-play module to enhance other fusion-based methods for large image generation. Code: https://github.com/TitorX/GVCFDiffusion
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。