发表机构
Digital Masterpieces GmbH（Digital Masterpieces 有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出将ControlNet与IP-Adapter风格化流程中的两个条件权重从全局标量提升为逐位置空间图，实现单次生成中对内容和风格的局部、逐轴控制，无需重训练，可即插即用。
AI 中文摘要
潜在扩散模型的图像风格化将两个独立细化的轴纠缠在一起：区域描绘的内容及其描绘方式。此类流程仅提供全局控制，但专业修图需要精细的区域特定控制。我们将ControlNet + IP-Adapter风格化流程中已有的两个条件权重从全局标量提升为逐位置的空间图，从而在单次生成过程中实现对内容和风格的局部、逐轴控制。由于这两个权重作用于不相交的路径，独立调整它们可形成2x2的修图词汇表，涵盖从自由重建到身份保持。我们验证了编辑局限于修图区域，且每个权重主要控制其自身轴。我们的方法无需重新训练，可直接应用于任何此类流程。
英文摘要
Image stylization with latent-diffusion models entangles two independently refined axes: what a region depicts and how it is depicted. Such pipelines expose only global controls, yet professional retouching demands deliberate, region-specific control. We lift two conditioning weights already present in a ControlNet + IP-Adapter stylization pipeline from global scalars to per-location spatial maps, yielding local, per-axis control of content and style in a single generative pass. Because the two weights act on disjoint pathways, adjusting them independently spans a 2x2 retouching vocabulary, from free regeneration to identity preservation. We validate that edits stay confined to the retouched region and that each weight predominantly steers its own axis. Our approach requires no retraining and drops unchanged into any such pipeline.
CommentsSIGGRAPH Asia 2026 Technical Communications. 4 pages, 4 figures, 1 table. Supplemental material included as an ancillary file
