The remarkable capabilities of pretrained image diffusion models have been utilized not only for generating fixed-size images but also for creating panoramas. However, naive stitching of multiple images often results in visible seams. Recent techniques have attempted to address this issue by performing joint diffusions in multiple windows and averaging latent features in overlapping regions. However, these approaches, which focus on seamless montage generation, often yield incoherent outputs by blending different scenes within a single image. To overcome this limitation, we propose SyncDiffusion, a plug-and-play module that synchronizes multiple diffusions through gradient descent from a perceptual similarity loss. Specifically, we compute the gradient of the perceptual loss using the predicted denoised images at each denoising step, providing meaningful guidance for achieving coherent montages. Our experimental results demonstrate that our method produces significantly more coherent outputs compared to previous methods (66.35% vs. 33.65% in our user study) while still maintaining fidelity (as assessed by GIQA) and compatibility with the input prompt (as measured by CLIP score).

翻译：预训练图像扩散模型的卓越能力不仅被用于生成固定尺寸图像，还被应用于创建全景图。然而，简单拼接多幅图像往往会导致可见接缝。近期技术尝试通过在多窗口中执行联合扩散并对重叠区域中的潜在特征进行平均化来应对这一问题。然而，这些专注于无缝蒙太奇生成的方法往往会因将不同场景混合到单张图像中而产生不连贯的输出。为克服这一局限，我们提出了SyncDiffusion——一种即插即用模块，通过基于感知相似性损失的梯度下降来同步多个扩散过程。具体而言，我们利用每个去噪步骤中预测的去噪图像来计算感知损失的梯度，从而为实现连贯蒙太奇提供有意义的引导。实验结果表明，与先前方法相比，我们的方法能产生显著更连贯的输出（用户研究中66.35%对比33.65%），同时仍能保持保真度（由GIQA评估）以及与输入提示的兼容性（由CLIP分数衡量）。