Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment

• URL: http://arxiv.org/abs/2607.04311v2
• Date: Tue, 07 Jul 2026 14:30:21 GMT
• Title: Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
• Abstract summary: Aura is a unified framework for high-fidelity and identity-consistent video generation.<n>We introduce AI director-level captions that provide dense and structured descriptions of video content.<n>We build a high-quality video-subject image dataset through a dedicated data construction pipeline.
• Score: 20.811984469709508
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Subject-driven and multi-element video generation are central to controllable video synthesis, but existing methods still struggle to preserve identity consistency and model complex relationships among multiple subjects. In this paper, we propose Aura, a unified framework for high-fidelity and identity-consistent video generation. To better capture scene dynamics and subject interactions, we introduce AI director-level captions that provide dense and structured descriptions of video content. We further leverage a vision-language model (VLM) with learnable queries to extract multimodal semantic features from textual and visual references, covering both global semantics and fine-grained visual cues. To bridge the representational gap between the VLM and the Diffusion Transformer (DiT), we design a two-stage alignment strategy that progressively maps VLM features into the DiT feature space. For visual conditioning, we adopt token concatenation to inject reference information directly into the generation process. To distinguish heterogeneous subject types and reduce common copy-paste artifacts, we develop a subject-aware RoPE-Shift mechanism. To further differentiate reference images of different categories, we introduce subject-aware learnable tokens. In addition, we introduce Memory Tokens to balance the training signal across examples with different numbers of reference subjects. During inference, Progressive-APG (Adaptive Prompt Guidance) further alleviates oversaturation and improves semantic alignment with user prompts. Finally, we build a high-quality video-subject image dataset through a dedicated data construction pipeline. Extensive experiments show that our method achieves state-of-the-art performance on both single-subject generation and more challenging multi-element scenarios.

Related papers

• HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enhancement [49.760248537839715]
  Human-object centric video personalization (HOCVP) is a core task within subject-driven video generation.<n>We propose HOMIE, an HOCVP framework that tackles both inter- and intra-subject input settings in a unified manner.<n>We introduce global multimodal guidance within self-attention to better align MLLM-derived semantic features with VAE tokens.
  arXiv  Detail & Related papers  (2026-07-20T17:51:35Z)
• Multimodal Large Language Models for Multi-Subject In-Context Image Generation [56.20395856287325]
  Music is the first MLLM specifically designed for textbfMUlti-textbfSubject textbfIn-textbfContext image generation.<n>We enhance the model's understanding of multi-subject semantic relationships through a vision chain-of-thought mechanism.<n>By incorporating complex subject images during training, we improve the model's capacity for chained reasoning.
  arXiv  Detail & Related papers  (2026-04-08T15:37:42Z)
• ID-Composer: Multi-Subject Video Synthesis with Hierarchical Identity Preservation [48.59900036213667]
  Video generative models pretrained on large-scale datasets can produce high-quality videos, but are often conditioned on text or a single image.<n>We introduce ID-Composer, a novel framework that tackles multi-subject video generation from a text prompt and reference images.
  arXiv  Detail & Related papers  (2025-11-01T11:29:14Z)
• BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration [56.98981194478512]
  We propose a unified framework that handles a broad range of subject-to-video scenarios.<n>We introduce an MLLM-DiT framework in which a pretrained multimodal large language model performs deep cross-modal reasoning to ground entities.<n>Experiments on the OpenS2V benchmark demonstrate that our method achieves superior performance across subject consistency, naturalness, and text relevance in generated videos.
  arXiv  Detail & Related papers  (2025-10-01T02:41:11Z)
• FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation [55.01077993490845]
  Recent Large Vision Language Models (LVLMs) demonstrate promising capabilities in unifying visual understanding and generative modeling.<n>We introduce FOCUS, a unified LVLM that integrates segmentation-aware perception and controllable object-centric generation within an end-to-end framework.
  arXiv  Detail & Related papers  (2025-06-20T07:46:40Z)
• PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement [26.89021788485701]
  PolyVivid is a multi-subject video customization framework that enables flexible and identity-consistent generation.<n>In experiments, PolyVivid achieves superior performance in identity fidelity, video realism, and subject alignment, outperforming existing open-source and commercial baselines.
  arXiv  Detail & Related papers  (2025-06-09T15:11:09Z)
• MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement [47.064467920954776]
  We introduce MAGREF, a unified and effective framework for any-reference video generation.<n>Our approach incorporates masked guidance and a subject disentanglement mechanism.<n>Experiments on a comprehensive benchmark demonstrate that MAGREF consistently outperforms existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-05-29T17:58:15Z)
• CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidance [34.345125922868]
  We propose CINEMA, a novel framework for coherent multi-subject video generation by leveraging Multimodal Large Language Model (MLLM)<n>Our approach eliminates the need for explicit correspondences between subject images and text entities, mitigating ambiguity and reducing annotation effort.<n>Our framework can be conditioned on varying numbers of subjects, offering greater flexibility in personalized content creation.
  arXiv  Detail & Related papers  (2025-03-13T14:07:58Z)
• MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing [90.06041718086317]
  We propose a unified Multi-alignment Diffusion, dubbed as MagDiff, for both tasks of high-fidelity video generation and editing. The proposed MagDiff introduces three types of alignments, including subject-driven alignment, adaptive prompts alignment, and high-fidelity alignment.
  arXiv  Detail & Related papers  (2023-11-29T03:36:07Z)
• RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation [53.4319652364256]
  This paper presents the RefSAM model, which explores the potential of SAM for referring video object segmentation. Our proposed approach adapts the original SAM model to enhance cross-modality learning by employing a lightweight Cross-RValModal. We employ a parameter-efficient tuning strategy to align and fuse the language and vision features effectively.
  arXiv  Detail & Related papers  (2023-07-03T13:21:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.