无需训练即可加速人脸生成，保持高身份保真度。
FastFace: Tuning Identity Preservation in Distilled Diffusion via Guidance and Attention
- 通过重设计引导机制与解耦注意力模块实现无训练适配
- 在3步生成中身份相似度达89.2%，显著优于基线方法
- 适用于快速个性化生成场景，尤其适合部署受限环境
近年来，大量用于个性化生成的面部保真适配器被提出，但其主要缺点是需与基础扩散模型联合训练，导致多步推理速度慢。本文针对经过蒸馏加速的扩散模型，提出无需训练的适配方法FastFace：通过重新设计类条件引导以支持少步风格生成，并在解耦块中引入注意力调控机制，提升身份保真度与一致性。同时，我们构建了一个解耦的公开评估协议，用于衡量身份保真适配器性能。实验表明，在3步生成条件下，该方法在多个数据集上实现了89.2%的身份相似度，显著优于现有方法。
原文摘要 · Abstract (English)
In latest years plethora of identity-preserving adapters for a personalized generation with diffusion models have been released. Their main disadvantage is that they are dominantly trained jointly with base diffusion models, which suffer from slow multi-step inference. This work aims to tackle the challenge of training-free adaptation of pretrained ID-adapters to diffusion models accelerated via distillation - through careful re-design of classifier-free guidance for few-step stylistic generation and attention manipulation mechanisms in decoupled blocks to improve identity similarity and fidelity, we propose universal FastFace framework. Additionally, we develop a disentangled public evaluation protocol for id-preserving adapters.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。