{"slug": "caricharmony-contrastive-diffusion-paths-for-identity-preserving-caricature", "title": "CaricHarmony: Contrastive Diffusion Paths for Identity-Preserving Caricature Synthesis", "summary": "Researchers at an undisclosed institution introduced CaricHarmony, a training-free method for sketch-based caricature synthesis that resolves destructive interference between identity and shape conditions in diffusion models. The approach maintains parallel diffusion paths with novel energy functions to achieve balanced generation, outperforming prior methods with a shape CLIP score of 0.8615 and user preference score of 7.81 while generating results in under 16 seconds.", "body_md": "arXiv:2606.13964v1 Announce Type: new\nAbstract: 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 \\emph{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.", "url": "https://wpnews.pro/news/caricharmony-contrastive-diffusion-paths-for-identity-preserving-caricature", "canonical_source": "https://arxiv.org/abs/2606.13964", "published_at": "2026-06-15 04:00:00+00:00", "updated_at": "2026-06-15 04:13:50.707406+00:00", "lang": "en", "topics": ["generative-ai", "computer-vision", "machine-learning"], "entities": ["CaricHarmony", "DemoCaricature", "CaricatureBooth"], "alternates": {"html": "https://wpnews.pro/news/caricharmony-contrastive-diffusion-paths-for-identity-preserving-caricature", "markdown": "https://wpnews.pro/news/caricharmony-contrastive-diffusion-paths-for-identity-preserving-caricature.md", "text": "https://wpnews.pro/news/caricharmony-contrastive-diffusion-paths-for-identity-preserving-caricature.txt", "jsonld": "https://wpnews.pro/news/caricharmony-contrastive-diffusion-paths-for-identity-preserving-caricature.jsonld"}}