FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining
초록
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.
저자 (13명)
- Jinghong Lan — LinkedIn 검색
- Wei Cheng — LinkedIn 검색
- Yunuo Chen — LinkedIn 검색
- Ziqi Ye — LinkedIn 검색
- Peng Xing — LinkedIn 검색
- Yixiao Fang — LinkedIn 검색
- Rui Wang — LinkedIn 검색
- Yufeng Yang — LinkedIn 검색
- Xuanyang Zhang — LinkedIn 검색
- Xianfang Zeng — LinkedIn 검색
- Difan Zou — LinkedIn 검색
- Gang Yu — LinkedIn 검색
- Chi Zhang — LinkedIn 검색
저자 LinkedIn 변경 추적은 추후 자동화 예정입니다. 현재는 검색 링크를 제공합니다.