CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidance

• URL: http://arxiv.org/abs/2503.10391v1
• Date: Thu, 13 Mar 2025 14:07:58 GMT
• Title: CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidance
• Authors: Yufan Deng, Xun Guo, Yizhi Wang, Jacob Zhiyuan Fang, Angtian Wang, Shenghai Yuan, Yiding Yang, Bo Liu, Haibin Huang, Chongyang Ma,
• Abstract summary: 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.
• Score: 34.345125922868
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video generation has witnessed remarkable progress with the advent of deep generative models, particularly diffusion models. While existing methods excel in generating high-quality videos from text prompts or single images, personalized multi-subject video generation remains a largely unexplored challenge. This task involves synthesizing videos that incorporate multiple distinct subjects, each defined by separate reference images, while ensuring temporal and spatial consistency. Current approaches primarily rely on mapping subject images to keywords in text prompts, which introduces ambiguity and limits their ability to model subject relationships effectively. In this paper, we propose CINEMA, a novel framework for coherent multi-subject video generation by leveraging Multimodal Large Language Model (MLLM). Our approach eliminates the need for explicit correspondences between subject images and text entities, mitigating ambiguity and reducing annotation effort. By leveraging MLLM to interpret subject relationships, our method facilitates scalability, enabling the use of large and diverse datasets for training. Furthermore, our framework can be conditioned on varying numbers of subjects, offering greater flexibility in personalized content creation. Through extensive evaluations, we demonstrate that our approach significantly improves subject consistency, and overall video coherence, paving the way for advanced applications in storytelling, interactive media, and personalized video generation.

Related papers

• Phantom: Subject-consistent video generation via cross-modal alignment [16.777805813950486]
  We propose a unified video generation framework for both single- and multi-subject references. The proposed method achieves high-fidelity subject-consistent video generation while addressing issues of image content leakage and multi-subject confusion.
  arXiv  Detail & Related papers  (2025-02-16T11:02:50Z)
• MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence [62.72540590546812]
  MovieDreamer is a novel hierarchical framework that integrates the strengths of autoregressive models with diffusion-based rendering. We present experiments across various movie genres, demonstrating that our approach achieves superior visual and narrative quality.
  arXiv  Detail & Related papers  (2024-07-23T17:17:05Z)
• SEED-Story: Multimodal Long Story Generation with Large Language Model [66.37077224696242]
  SEED-Story is a novel method that leverages a Multimodal Large Language Model (MLLM) to generate extended multimodal stories. We propose multimodal attention sink mechanism to enable the generation of stories with up to 25 sequences (only 10 for training) in a highly efficient autoregressive manner. We present a large-scale and high-resolution dataset named StoryStream for training our model and quantitatively evaluating the task of multimodal story generation in various aspects.
  arXiv  Detail & Related papers  (2024-07-11T17:21:03Z)
• Vivid-ZOO: Multi-View Video Generation with Diffusion Model [76.96449336578286]
  New challenges lie in the lack of massive captioned multi-view videos and the complexity of modeling such multi-dimensional distribution. We propose a novel diffusion-based pipeline that generates high-quality multi-view videos centered around a dynamic 3D object from text.
  arXiv  Detail & Related papers  (2024-06-12T21:44:04Z)
• Towards Multi-Task Multi-Modal Models: A Video Generative Perspective [5.495245220300184]
  This thesis chronicles our endeavor to build multi-task models for generating videos and other modalities under diverse conditions. We unveil a novel approach to mapping bidirectionally between visual observation and interpretable lexical terms. Our scalable visual token representation proves beneficial across generation, compression, and understanding tasks.
  arXiv  Detail & Related papers  (2024-05-26T23:56:45Z)
• Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception [63.03288425612792]
  We propose bfAnyRef, a general MLLM model that can generate pixel-wise object perceptions and natural language descriptions from multi-modality references. Our model achieves state-of-the-art results across multiple benchmarks, including diverse modality referring segmentation and region-level referring expression generation.
  arXiv  Detail & Related papers  (2024-03-05T13:45:46Z)
• Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization [52.63845811751936]
  Video pre-training is challenging due to the modeling of its dynamics video. In this paper, we address such limitations in video pre-training with an efficient video decomposition. Our framework is both capable of comprehending and generating image and video content, as demonstrated by its performance across 13 multimodal benchmarks.
  arXiv  Detail & Related papers  (2024-02-05T16:30:49Z)
• CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects [61.323597069037056]
  Current approaches for personalizing text-to-video generation suffer from tackling multiple subjects. We propose CustomVideo, a novel framework that can generate identity-preserving videos with the guidance of multiple subjects.
  arXiv  Detail & Related papers  (2024-01-18T13:23:51Z)
• VideoDreamer: Customized Multi-Subject Text-to-Video Generation with Disen-Mix Finetuning on Language-Video Foundation Models [43.46536102838717]
  VideoDreamer is a novel framework for customized multi-subject text-to-video generation. It can generate temporally consistent text-guided videos that faithfully preserve the visual features of the given multiple subjects.
  arXiv  Detail & Related papers  (2023-11-02T04:38:50Z)
• Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising [43.35391175319815]
  This study explores the potential of extending the text-driven ability to the generation and editing of multi-text conditioned long videos. We introduce a novel paradigm dubbed Gen-L-Video, capable of extending off-the-shelf short video diffusion models. Our experimental outcomes reveal that our approach significantly broadens the generative and editing capabilities of video diffusion models.
  arXiv  Detail & Related papers  (2023-05-29T17:38:18Z)

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.