Narrative Weaver: Towards Controllable Long-Range Visual Consistency with Multi-Modal Conditioning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yao, Zhengjian, Li, Yongzhi, Gao, Xinyuan, Chen, Quan, Jiang, Peng, Lu, Yanye
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914389980872704
author Yao, Zhengjian
Li, Yongzhi
Gao, Xinyuan
Chen, Quan
Jiang, Peng
Lu, Yanye
author_facet Yao, Zhengjian
Li, Yongzhi
Gao, Xinyuan
Chen, Quan
Jiang, Peng
Lu, Yanye
contents We present "Narrative Weaver", a novel framework that addresses a fundamental challenge in generative AI: achieving multi-modal controllable, long-range, and consistent visual content generation. While existing models excel at generating high-fidelity short-form visual content, they struggle to maintain narrative coherence and visual consistency across extended sequences - a critical limitation for real-world applications such as filmmaking and e-commerce advertising. Narrative Weaver introduces the first holistic solution that seamlessly integrates three essential capabilities: fine-grained control, automatic narrative planning, and long-range coherence. Our architecture combines a Multimodal Large Language Model (MLLM) for high-level narrative planning with a novel fine-grained control module featuring a dynamic Memory Bank that prevents visual drift. To enable practical deployment, we develop a progressive, multi-stage training strategy that efficiently leverages existing pre-trained models, achieving state-of-the-art performance even with limited training data. Recognizing the absence of suitable evaluation benchmarks, we construct and release the E-commerce Advertising Video Storyboard Dataset (EAVSD) - the first comprehensive dataset for this task, containing over 330K high-quality images with rich narrative annotations. Through extensive experiments across three distinct scenarios (controllable multi-scene generation, autonomous storytelling, and e-commerce advertising), we demonstrate our method's superiority while opening new possibilities for AI-driven content creation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_06688
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Narrative Weaver: Towards Controllable Long-Range Visual Consistency with Multi-Modal Conditioning
Yao, Zhengjian
Li, Yongzhi
Gao, Xinyuan
Chen, Quan
Jiang, Peng
Lu, Yanye
Computer Vision and Pattern Recognition
Artificial Intelligence
We present "Narrative Weaver", a novel framework that addresses a fundamental challenge in generative AI: achieving multi-modal controllable, long-range, and consistent visual content generation. While existing models excel at generating high-fidelity short-form visual content, they struggle to maintain narrative coherence and visual consistency across extended sequences - a critical limitation for real-world applications such as filmmaking and e-commerce advertising. Narrative Weaver introduces the first holistic solution that seamlessly integrates three essential capabilities: fine-grained control, automatic narrative planning, and long-range coherence. Our architecture combines a Multimodal Large Language Model (MLLM) for high-level narrative planning with a novel fine-grained control module featuring a dynamic Memory Bank that prevents visual drift. To enable practical deployment, we develop a progressive, multi-stage training strategy that efficiently leverages existing pre-trained models, achieving state-of-the-art performance even with limited training data. Recognizing the absence of suitable evaluation benchmarks, we construct and release the E-commerce Advertising Video Storyboard Dataset (EAVSD) - the first comprehensive dataset for this task, containing over 330K high-quality images with rich narrative annotations. Through extensive experiments across three distinct scenarios (controllable multi-scene generation, autonomous storytelling, and e-commerce advertising), we demonstrate our method's superiority while opening new possibilities for AI-driven content creation.
title Narrative Weaver: Towards Controllable Long-Range Visual Consistency with Multi-Modal Conditioning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.06688