XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation
Achieving fine-grained control over subject identity and semantic attributes (pose, style, lighting) in text-to-image generation, particularly for multiple subjects, often undermines the editability and coherence of Diffusion Transformers (DiTs). Many approaches introduce artifacts or suffer from attribute entanglement. To overcome these challenges, we propose a novel multi-subject controlled generation model XVerse. By transforming reference images into offsets for token-specific text-stream modulation, XVerse allows for precise and independent control for specific subject without disrupting image latents or features. Consequently, XVerse offers high-fidelity, editable multi-subject image synthesis with robust control over individual subject characteristics and semantic attributes. This advancement significantly improves personalized and complex scene generation capabilities.
Code (1)
Tasks
AttributeImage GenerationScene GenerationText to Image GenerationText-to-Image GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
CRAFT: Constrained Reward via Attention Fine-Tuning for Subject Personalization without Composed Targets
Subject-driven image personalization---generating new images that preserve the identity of one or several reference subjects in novel scenes---is a foundational capability for modern visual content creation. It is curren…
CopyCat: Improving Fine-Grained Subject Consistency in Subject-to-Image Models within Seconds
Recent subject-to-image models have achieved impressive progress in personalized image generation, yet they still struggle to preserve fine-grained subject-specific details. A major reason is the lack of high-quality fin…
Personalized Image GenerationWhen Identities Collapse: A Stress-Test Benchmark for Multi-Subject Personalization
Subject-driven text-to-image diffusion models have achieved remarkable success in preserving single identities, yet their ability to compose multiple interacting subjects remains largely unexplored and highly challenging…
DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation
Building general-purpose dexterous manipulation policies requires benchmarks that go beyond isolated tasks to systematically evaluate policies across diverse interaction modes, sensory conditions, and robot embodiments. …
PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement
Despite recent advances in video generation, existing models still lack fine-grained controllability, especially for multi-subject customization with consistent identity and interaction. In this paper, we propose PolyViv…
Video Generation