Cover Image

MultiCrafter: High-Fidelity Multi-Subject Generation via Disentangled Attention and Identity-Aware Preference Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Tao, Jiang, Yibo, Lu, Yehao, Wang, Zhizhong, Huang, Zeyi, Qin, Zequn, Li, Xi
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Free Lunch for Unified Multimodal Models: Enhancing Generation via Reflective Rectification with Inherent Understanding
by: Jiang, Yibo, et al.
Published: (2026)

MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement
by: She, Dong, et al.
Published: (2025)

DreamVAR: Taming Reinforced Visual Autoregressive Model for High-Fidelity Subject-Driven Image Generation
by: Jiang, Xin, et al.
Published: (2026)

ID-Crafter: VLM-Grounded Online RL for Compositional Multi-Subject Video Generation
by: Pan, Panwang, et al.
Published: (2025)

MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing
by: Zhao, Haoyu, et al.
Published: (2023)

FaceCrafter: Identity-Conditional Diffusion with Disentangled Control over Facial Pose, Expression, and Emotion
by: Mishima, Kazuaki, et al.
Published: (2025)

IdGlow: Dynamic Identity Modulation for Multi-Subject Generation
by: Cai, Honghao, et al.
Published: (2026)

BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment
by: Zhou, Dewei, et al.
Published: (2025)

FontCrafter: High-Fidelity Element-Driven Artistic Font Creation with Visual In-Context Generation
by: Luo, Wuyang, et al.
Published: (2026)

SpatialText: A Pure-Text Cognitive Benchmark for Spatial Understanding in Large Language Models
by: Jiang, Peiyao, et al.
Published: (2026)

SceneCrafter: Controllable Multi-View Driving Scene Editing
by: Zhu, Zehao, et al.
Published: (2025)

Quantifying and Enhancing Multi-modal Robustness with Modality Preference
by: Yang, Zequn, et al.
Published: (2024)

PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model
by: Lin, Baijiong, et al.
Published: (2025)

Subject-Aware Multi-Granularity Alignment for Zero-Shot EEG-to-Image Retrieval
by: Jiang, Lin, et al.
Published: (2026)

Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment
by: Zhang, Jianfei, et al.
Published: (2024)

LeVo: High-Quality Song Generation with Multi-Preference Alignment
by: Lei, Shun, et al.
Published: (2025)

Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs
by: Wang, Zitian, et al.
Published: (2025)

FocusDPO: Dynamic Preference Optimization for Multi-Subject Personalized Image Generation via Adaptive Focus
by: Jin, Qiaoqiao, et al.
Published: (2025)

LayerEdit: Disentangled Multi-Object Editing via Conflict-Aware Multi-Layer Learning
by: Fu, Fengyi, et al.
Published: (2025)

DynaIP: Dynamic Image Prompt Adapter for Scalable Zero-shot Personalized Text-to-Image Generation
by: Wang, Zhizhong, et al.
Published: (2025)

CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities
by: Wu, Tao, et al.
Published: (2024)

StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter
by: Liu, Gongye, et al.
Published: (2023)

Multi-Metric Preference Alignment for Generative Speech Restoration
by: Zhang, Junan, et al.
Published: (2025)

DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation
by: Chen, Hong, et al.
Published: (2023)

DOne: Decoupling Structure and Rendering for High-Fidelity Design-to-Code Generation
by: Huang, Xinhao, et al.
Published: (2026)

CityCraft: A Real Crafter for 3D City Generation
by: Deng, Jie, et al.
Published: (2024)

CamI2V: Camera-Controlled Image-to-Video Diffusion Model
by: Zheng, Guangcong, et al.
Published: (2024)

Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation
by: Zhu, Bangguo, et al.
Published: (2026)

MSR-Codec: A Low-Bitrate Multi-Stream Residual Codec for High-Fidelity Speech Generation with Information Disentanglement
by: Li, Jingyu, et al.
Published: (2025)

Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation
by: Dahary, Omer, et al.
Published: (2024)

EverybodyDance: Bipartite Graph-Based Identity Correspondence for Multi-Character Animation
by: Ling, Haotian, et al.
Published: (2025)

MM-Diff: High-Fidelity Image Personalization via Multi-Modal Condition Integration
by: Wei, Zhichao, et al.
Published: (2024)

MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation
by: Wang, Kuan-Chieh, et al.
Published: (2024)

PAN-Crafter: Learning Modality-Consistent Alignment for PAN-Sharpening
by: Do, Jeonghyeok, et al.
Published: (2025)

Preference Orchestrator: Prompt-Aware Multi-Objective Alignment for Large Language Models
by: Liu, Biao, et al.
Published: (2025)

Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learning
by: Meng, Xiangyu, et al.
Published: (2025)

GCMCG: A Clustering-Aware Graph Attention and Expert Fusion Network for Multi-Paradigm, Multi-task, and Cross-Subject EEG Decoding
by: Chen, Yiqiao, et al.
Published: (2025)

HiGR: Efficient Generative Slate Recommendation via Hierarchical Planning and Multi-Objective Preference Alignment
by: Pang, Yunsheng, et al.
Published: (2025)

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
by: Zhao, Haozhe, et al.
Published: (2026)

Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment
by: Le, Minh-Quan, et al.
Published: (2025)