AI Pulse
📄 论文解读

AI画画终于能分清「风格」和「内容」了

以前你想让AI画一张「梵高风格的猫」,它要么把猫画成梵高自画像里的样子(风格泄漏),要么猫的姿势被梵高的笔触带偏。FreeStyle 把「风格」和「内容」彻底拆开:它从社区里挖出大量 LoRA 模型作为风格锚点,再用两阶段训练——先让模型学会只转移风格不转移内容,再处理更难的「风格+内容双参考」任务。关键创新是两种防泄漏机制:注意力层约束防止风格参考里的物体形状渗入,频率感知 RoPE 调制防止位置信息串扰。最终模型在风格相似度、内容保留、指令遵循上都达到新平衡。它不是你明天就能用的工具,但解释了为什么之前的AI画画总「画不对」——问题不在画功,在没学会分离。

📄 原文摘要(英文)

Style-content dual-reference generation aims to synthesize an image that preserves the structure and semantics of a content reference while adopting the style of a separate style reference.Despite recent progress, this setting remains challenging because models must balance content fidelity, style alignment, and instruction following avoiding semantic leakage from the style reference.A key bottleneck is the lack of large-scale triplet data with clean content-style separation and broad long-tail style coverage.In this work, we propose FreeStyle, a scalable dual-reference generation framework based on community LoRA mining.We treat community LoRAs as compositional anchors for style and content, and design a rigorous generation and filtering pipeline to construct large-scale Style-Reference and Content-Reference triplets across multiple base models.To address content leakage, we adopt a two-stage curriculum with stage-specific disentanglement mechanisms: an attention-level enrichment constraint that suppresses style-reference leakage in the style-transfer stage, and a frequency-aware RoPE modulation strategy that targets positional-correspondence-based leakage in the harder dual-reference stage.We also introduce a benchmark covering both style-reference and dual-reference generation, with evaluations on style similarity, content preservation, aesthetics, instruction following, and leakage rejection. The benchmark incorporates a style-invariant Content Alignment Score (CAS) and introduces a calibrated VLM-based Rejection Score for evaluating generation reliability and leakage suppression.Extensive experiments show that our model achieves a strong balance among style alignment, content preservation, and leakage suppression.

arXiv 原文

订阅 AI Pulse

每天 08:00 · 12:30 · 18:30 · 23:50 更新