MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization
Video identity customization seeks to produce high-fidelity videos that maintain consistent identity and exhibit significant dynamics based on users' reference images. However, existing approaches face two key challenges: identity degradation over extended video length and reduced dynamics during training, primarily due to their reliance on traditional self-reconstruction training with static images. To address these issues, we introduce $\textbf{MagicID}$, a novel framework designed to directly promote the generation of identity-consistent and dynamically rich videos tailored to user preferences. Specifically, we propose constructing pairwise preference video data with explicit identity and dynamic rewards for preference learning, instead of sticking to the traditional self-reconstruction. To address the constraints of customized preference data, we introduce a hybrid sampling strategy. This approach first prioritizes identity preservation by leveraging static videos derived from reference images, then enhances dynamic motion quality in the generated videos using a Frontier-based sampling method. By utilizing these hybrid preference pairs, we optimize the model to align with the reward differences between pairs of customized preferences. Extensive experiments show that MagicID successfully achieves consistent identity and natural dynamics, surpassing existing methods across various metrics.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MagicID: Flexible ID Fidelity Generation System
Portrait Fidelity Generation is a prominent research area in generative models, with a primary focus on enhancing both controllability and fidelity. Current methods face challenges in generating high-fidelity portrait re…
Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment
Standard RLHF relies on transitive scalar rewards, failing to capture the cyclic nature of human preferences. While some approaches like the General Preference Model (GPM) address this, we identify a theoretical limitati…
Active Preference Learning over Latent Preference Archetypes for Many-Objective Bayesian Optimization
Preference-based many-objective Bayesian optimization typically assumes that all pairwise comparisons arise from a single latent utility function, despite real decision makers often exhibiting multiple latent preference …
SAMPO-Path: Segmentation Intent-Aligned Preference Optimization for Pathology Foundation Model Segmentation
Foundation models have shown strong performance in multi-object segmentation with visual prompts, yet histopathology images remain challenging due to high cellular density, heterogeneity, and the gap between pixel-level …
Object SegmentationHybrid Alignment Training for Large Language Models
Alignment training is crucial for enabling large language models (LLMs) to cater to human intentions and preferences. It is typically performed based on two stages with different objectives: instruction-following alignme…
Instruction Following