A Controllable Video Generation Method Based on Diffusion Models and ControlNet

DOI

10.2991/978-94-6239-737-8_9How to use a DOI?

Keywords

Diffusion Models; ControlNet; Video Generation; Controllable Generation; AIGC; Deep Learning

Abstract

With the rapid advancement of artificial intelligence, diffusion models have shown strong potential in video generation tasks. However, existing methods still suffer from limited controllability and inconsistent frame generation. To address these issues, this paper proposes a controllable video generation method based on diffusion models and ControlNet. The proposed approach integrates text-guided latent diffusion with structural control signals, such as pose and edge information, to achieve precise and flexible control over generated content. In addition, a temporal smoothing module is introduced to enhance inter-frame consistency. Experimental results demonstrate that the proposed method improves visual quality, semantic alignment, and structural consistency compared with baseline models. The method provides an effective and practical solution for AI-driven video generation in digital media applications.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Qi Chen
AU  - Xinyu Guo
AU  - Yang Liu
AU  - Wenchao Luo
PY  - 2026
DA  - 2026/08/18
TI  - A Controllable Video Generation Method Based on Diffusion Models and ControlNet
BT  - Proceedings of the 2026 5th International Conference on Art Design and Digital Technology (ADDT 2026)
PB  - Atlantis Press
SP  - 54
EP  - 60
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6239-737-8_9
DO  - 10.2991/978-94-6239-737-8_9
ID  - Chen2026
ER  -