Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.20192 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908902945193984 |
|---|---|
| author | Xing, Jiazheng Du, Fei Yuan, Hangjie Liu, Pengwei Xu, Hongbin Ci, Hai Niu, Ruigang Chen, Weihua Wang, Fan Liu, Yong |
| author_facet | Xing, Jiazheng Du, Fei Yuan, Hangjie Liu, Pengwei Xu, Hongbin Ci, Hai Niu, Ruigang Chen, Weihua Wang, Fan Liu, Yong |
| contents | Recent advances in diffusion models have significantly improved text-to-video generation, enabling personalized content creation with fine-grained control over both foreground and background elements. However, precise face-attribute alignment across subjects remains challenging, as existing methods lack explicit mechanisms to ensure intra-group consistency. Addressing this gap requires both explicit modeling strategies and face-attribute-aware data resources. We therefore propose LumosX, a framework that advances both data and model design. On the data side, a tailored collection pipeline orchestrates captions and visual cues from independent videos, while multimodal large language models (MLLMs) infer and assign subject-specific dependencies. These extracted relational priors impose a finer-grained structure that amplifies the expressive control of personalized video generation and enables the construction of a comprehensive benchmark. On the modeling side, Relational Self-Attention and Relational Cross-Attention intertwine position-aware embeddings with refined attention dynamics to inscribe explicit subject-attribute dependencies, enforcing disciplined intra-group cohesion and amplifying the separation between distinct subject clusters. Comprehensive evaluations on our benchmark demonstrate that LumosX achieves state-of-the-art performance in fine-grained, identity-consistent, and semantically aligned personalized multi-subject video generation. Code and models are available at https://jiazheng-xing.github.io/lumosx-home/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_20192 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation Xing, Jiazheng Du, Fei Yuan, Hangjie Liu, Pengwei Xu, Hongbin Ci, Hai Niu, Ruigang Chen, Weihua Wang, Fan Liu, Yong Computer Vision and Pattern Recognition Artificial Intelligence Recent advances in diffusion models have significantly improved text-to-video generation, enabling personalized content creation with fine-grained control over both foreground and background elements. However, precise face-attribute alignment across subjects remains challenging, as existing methods lack explicit mechanisms to ensure intra-group consistency. Addressing this gap requires both explicit modeling strategies and face-attribute-aware data resources. We therefore propose LumosX, a framework that advances both data and model design. On the data side, a tailored collection pipeline orchestrates captions and visual cues from independent videos, while multimodal large language models (MLLMs) infer and assign subject-specific dependencies. These extracted relational priors impose a finer-grained structure that amplifies the expressive control of personalized video generation and enables the construction of a comprehensive benchmark. On the modeling side, Relational Self-Attention and Relational Cross-Attention intertwine position-aware embeddings with refined attention dynamics to inscribe explicit subject-attribute dependencies, enforcing disciplined intra-group cohesion and amplifying the separation between distinct subject clusters. Comprehensive evaluations on our benchmark demonstrate that LumosX achieves state-of-the-art performance in fine-grained, identity-consistent, and semantically aligned personalized multi-subject video generation. Code and models are available at https://jiazheng-xing.github.io/lumosx-home/. |
| title | LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.20192 |