ReMix：迈向一致角色生成与编辑的统一视角
ReMix: Towards a Unified View of Consistent Character Generation and Editing
AI总结：
本文提出统一框架 ReMix，通过 ReMix Module 适配语义特征与 IP-ControlNet 解耦布局线索，在保留身份的同时实现一致的角色图像生成与编辑。
摘要：
大规模文本到图像扩散模型（如 FLUX.1）的最新进展极大地提升了角色一致生成与编辑的视觉保真度。然而，现有方法很少在单一框架内统一这些任务。基于生成的方法在跨实例的细粒度身份一致性上存在困难，而基于编辑的方法往往失去空间可控性和指令对齐。为弥补这一差距，我们提出了 ReMix，一个用于角色一致生成与编辑的统一框架。它由两个核心组件构成：ReMix Module 和 IP-ControlNet。ReMix Module 利用 MLLMs 的多模态推理能力来编辑输入图像的语义特征，并在不微调的情况下将指令嵌入适配到原生 DiT 主干。虽然这确保了连贯的语义布局，但像素级一致性和姿态可控性仍具挑战。为解决此问题，IP-ControlNet 扩展了 ControlNet，以从参考图像中解耦语义和布局线索，并引入了一个 ε-等变潜在空间，在共享噪声空间内联合对参考图像和目标图像去噪。受趋同进化和量子退相干启发，即环境噪声驱动状态收敛，该设计促进了隐藏空间中的特征对齐，在保留身份的同时实现一致的对象生成。ReMix 支持广泛的任务，包括个性化生成、图像编辑、风格迁移和多条件合成。大量实验验证了其作为角色一致图像生成与编辑统一框架的有效性和效率。
英文摘要：
Recent advances in large-scale text-to-image diffusion models (e.g., FLUX.1) have greatly improved visual fidelity in consistent character generation and editing. However, existing methods rarely unify these tasks within a single framework. Generation-based approaches struggle with fine-grained identity consistency across instances, while editing-based methods often lose spatial controllability and instruction alignment. To bridge this gap, we propose ReMix, a unified framework for character-consistent generation and editing. It constitutes two core components: the ReMix Module and IP-ControlNet. The ReMix Module leverages the multimodal reasoning ability of MLLMs to edit semantic features of input images and adapt instruction embeddings to the native DiT backbone without fine-tuning. While this ensures coherent semantic layouts, pixel-level consistency and pose controllability remain challenging. To address this, IP-ControlNet extends ControlNet to decouple semantic and layout cues from reference images and introduces an ε-equivariant latent space that jointly denoises the reference and target images within a shared noise space. Inspired by convergent evolution and quantum decoherence,i.e., where environmental noise drives state convergence, this design promotes feature alignment in the hidden space, enabling consistent object generation while preserving identity. ReMix supports a wide range of tasks, including personalized generation, image editing, style transfer, and multi-condition synthesis. Extensive experiments validate its effectiveness and efficiency as a unified framework for character-consistent image generation and editing.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
