无需训练即可实现高质量人物图像动画，保持身份和背景稳定。
FreeAnimate: Training-Free Human Image Animation with Preview-Guided Denoising
- 利用预览帧提供时序与结构先验，引导姿态对齐与背景一致。
- 在多个数据集上达到与顶尖方法相当的生成质量。
- 适合希望快速试用动画效果的研究者与开发者。
人物图像动画近年来发展迅速，主要依赖于扩散模型。然而，现有方法通常需要大量训练数据和计算资源才能获得高质量结果，限制了泛化能力和可及性。本文提出 FreeAnimate，一种无需训练的框架，利用图像扩散模型的固有能力，实现时序一致性、身份保持和背景稳定。该方法引入新颖的预览生成策略，从生成的预览帧中获取时序与结构先验，有效引导姿态对齐与背景一致性，无需训练。此外，FreeAnimate 还提出反演增强注意力与参考锚定自注意力模块，确保时序一致性和身份保真度。实验表明，FreeAnimate 在多个基准测试中优于现有的无训练方法，并达到与训练型基线相当的生成质量，展现出跨数据集的强大泛化能力。
原文摘要 · Abstract (English)
Human Image Animation has seen significant advancements, primarily driven by diffusion models. However, existing methods typically demand substantial training data and resources to achieve high-quality results, limiting generalization and accessibility. In this work, we introduce \emph{FreeAnimate}, a training-free framework that leverages the inherent capabilities of image diffusion models to enable temporal consistency, identity preservation, and background stability. Our approach incorporates a novel preview generation strategy that provides temporal and structural priors from generated preview frames, effectively guiding pose alignment and background consistency without training. Additionally, FreeAnimate introduces Inversion-Boosted Attention and Reference-Anchored Self-Attention modules to guarantee temporal consistency and identity preservation. Experimental results demonstrate that FreeAnimate outperforms existing training-free competitors and training-based baseline methods, achieving generation quality comparable to state-of-the-art methods and offering robust generalization across diverse datasets. Our project page is at https://freeani.github.io/.
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。