Interactive Mobile AI Video Creation: System Design Integrating Style Transfer and Narrative Control.

Saved in:

Bibliographic Details
Title:	Interactive Mobile AI Video Creation: System Design Integrating Style Transfer and Narrative Control.
Authors:	Wang, Nan¹ beautifulnancy1984@163.com, Zhao, Ziwei¹ 13933675555@139.com
Source:	International Journal of Interactive Mobile Technologies. 2026, Vol. 20 Issue 9, p43-56. 14p.
Subjects:	Narration, Real-time computing, Human-computer interaction, Mobile apps, Aesthetics of art
Abstract:	Existing AI-based video stylization techniques face significant challenges when deployed on mobile devices, including high latency, insufficient temporal coherence, lack of narrative control, and poor resource adaptability. To address these limitations, this paper proposes a low-latency interactive AI video creation system specifically designed for mobile platforms. Without relying on newly developed foundational AI models, the proposed system leverages a hierarchical system architecture, lightweight model optimization, deep integration of narrative logic, and device-side collaborative scheduling to enable real-time video generation, temporal consistency, and controllable storytelling on resource-constrained mobile devices. This paper focuses on the technical implementation of the system's core innovative modules. Extensive multi-dimensional experiments demonstrate that the proposed system achieves significant advantages in performance, generation quality, and user interaction experience. Experimental results show that the per-frame processing latency on three representative mobile devices is reduced to as low as 28 ms, 32 ms, and 45 ms, respectively, with end-to-end latency consistently maintained below 200 ms. The system attains a temporal consistency score of 0.92 and a stylization quality rating of 8.6, significantly outperforming three baseline models. Moreover, the proposed system exhibits strong adaptability across heterogeneous computing capabilities, maintains low power consumption (=200 mA/hr), and delivers high-quality creative outputs. These results indicate that the system provides an efficient and practical engineering solution for deploying AI video creation on mobile devices. This study contributes a feasible and effective pathway toward the large-scale application of intelligent video creation technologies on mobile platforms and holds substantial significance for advancing mobile AI-driven creative systems. [ABSTRACT FROM AUTHOR]
	Copyright of International Journal of Interactive Mobile Technologies is the property of International Journal of Interactive Mobile Technologies and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Existing AI-based video stylization techniques face significant challenges when deployed on mobile devices, including high latency, insufficient temporal coherence, lack of narrative control, and poor resource adaptability. To address these limitations, this paper proposes a low-latency interactive AI video creation system specifically designed for mobile platforms. Without relying on newly developed foundational AI models, the proposed system leverages a hierarchical system architecture, lightweight model optimization, deep integration of narrative logic, and device-side collaborative scheduling to enable real-time video generation, temporal consistency, and controllable storytelling on resource-constrained mobile devices. This paper focuses on the technical implementation of the system's core innovative modules. Extensive multi-dimensional experiments demonstrate that the proposed system achieves significant advantages in performance, generation quality, and user interaction experience. Experimental results show that the per-frame processing latency on three representative mobile devices is reduced to as low as 28 ms, 32 ms, and 45 ms, respectively, with end-to-end latency consistently maintained below 200 ms. The system attains a temporal consistency score of 0.92 and a stylization quality rating of 8.6, significantly outperforming three baseline models. Moreover, the proposed system exhibits strong adaptability across heterogeneous computing capabilities, maintains low power consumption (=200 mA/hr), and delivers high-quality creative outputs. These results indicate that the system provides an efficient and practical engineering solution for deploying AI video creation on mobile devices. This study contributes a feasible and effective pathway toward the large-scale application of intelligent video creation technologies on mobile platforms and holds substantial significance for advancing mobile AI-driven creative systems. [ABSTRACT FROM AUTHOR]
ISSN:	18657923
DOI:	10.3991/ijim.v20i09.61739