PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models

TL;DR

PIA is a novel personalized image animation framework that enables motion controllability and style preservation in text-to-image models without requiring model-specific tuning.

Contribution

It introduces a plug-and-play condition module and temporal alignment layers to transform personalized T2I models into animation models with high fidelity.

Findings

Achieves high-quality personalized animations with motion controllability.

Maintains style and detail fidelity during animation.

Compatible with various T2I models without additional tuning.

Abstract

Recent advancements in personalized text-to-image (T2I) models have revolutionized content creation, empowering non-experts to generate stunning images with unique styles. While promising, adding realistic motions into these personalized images by text poses significant challenges in preserving distinct styles, high-fidelity details, and achieving motion controllability by text. In this paper, we present PIA, a Personalized Image Animator that excels in aligning with condition images, achieving motion controllability by text, and the compatibility with various personalized T2I models without specific tuning. To achieve these goals, PIA builds upon a base T2I model with well-trained temporal alignment layers, allowing for the seamless transformation of any personalized T2I model into an image animation model. A key component of PIA is the introduction of the condition module, which utilizes the condition frame and inter-frame affinity as input to transfer appearance information guided by the affinity hint for individual frame synthesis in the latent space. This design mitigates the challenges of appearance-related image alignment within and allows for a stronger focus on aligning with motion-related guidance.