CaricHarmony：用于身份保持漫画合成的对比扩散路径
CaricHarmony: Contrastive Diffusion Paths for Identity-Preserving Caricature Synthesis
提出免训练的并行扩散路径与基于交叉注意力特征的能量函数，用于解决多条件生成中的信号污染问题，可复用于其他需要平衡多个冲突条件的可控生成任务。
原文依据 We present CaricHarmony, the first training-free method that explicitly resolves this contamination through parallel uncontaminated diffusion paths.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于草图的漫画合成存在一个根本性失败模式：当身份和形状条件在扩散模型中结合时，它们会产生破坏性干扰，导致不可避免地坍缩为平淡的肖像或无法识别的扭曲。我们将根本原因识别为条件信号污染——去噪轨迹中相互竞争的概率分布使得平衡生成无法实现。我们提出 CaricHarmony，这是首个通过并行无污染扩散路径显式解决该污染的免训练方法。在推理过程中，我们维护三条路径：\mathcal P ^ \mathrm i（纯身份）、\mathcal P ^ \mathrm s（纯形状）和 \mathcal P ^ \mathrm i+s（协调输出）。作用于交叉注意力特征的新颖能量函数提供梯度引导，将 \mathcal P ^ \mathrm i+s 导向最优平衡：\mathcal E _ \mathrm shape 通过布局和语义对齐确保草图保真度，而 \mathcal E _ \mathrm id 采用对极端扭曲鲁棒的 token 级对应匹配。与需要每个身份 70 秒微调的 DemoCaricature 或受限于贝塞尔曲线的 CaricatureBooth 不同，CaricHarmony 接受任意草图格式并在 16 秒内生成。实验展示了最优性能：在相当的身份一致性分数下，形状 CLIP 分数为 0.8615（对比 0.8450），整体用户偏好分数为 7.81（对比 6.06）。我们的方法从根本上将 ID-形状冲突重新概念化为扩散模型的条件信号污染，在保持可识别性的同时实现了前所未有的创意控制。
英文原文摘要 1677 字符
Sketch-based caricature synthesis suffers from a fundamental failure mode: when identity and shape conditions are combined in diffusion models, they create destructive interference that causes inevitable collapse toward either bland portraits or unrecognizable distortions. We identify the root cause as condition signal contamination -- competing probability distributions in the denoising trajectory that make balanced generation impossible. We present CaricHarmony, the first training-free method that explicitly resolves this contamination through parallel uncontaminated diffusion paths. During inference, we maintain three paths: \mathcal P ^ \mathrm i (pure identity), \mathcal P ^ \mathrm s (pure shape), and \mathcal P ^ \mathrm i+s (harmonized output). Novel energy functions operating on cross-attention features provide gradient guidance that steers \mathcal P ^ \mathrm i+s toward optimal balance: \mathcal E _ \mathrm shape ensures sketch fidelity through layout and semantic alignment, while \mathcal E _ \mathrm id employs token-level correspondence matching robust to extreme distortions. Unlike DemoCaricature requiring 70 seconds per-identity fine-tuning or CaricatureBooth constrained to Bezier curves, CaricHarmony accepts any sketch format and generates in under 16 seconds. Experiments demonstrate state-of-the-art performance: 0.8615 shape CLIP score (vs. 0.8450) under comparable identity consistency score, with 7.81 overall user preference score (vs. 6.06). Our method fundamentally reconceptualizes the ID-shape conflict as conditioning signal contamination for diffusion models, enabling unprecedented creative control while preserving recognition.