Intelligent Mining: Research and Application of Intelligent Generation Animation Technology

DOI

10.2991/978-2-38476-319-1_61How to use a DOI?

Keywords

GAN; CLIP model; Diffusion model; animation generation; image generation quality; cross-modal generation

Abstract

With the advancement of deep learning, the application of techniques such as Generative Adversarial Networks (GAN), CLIP and Diffusion Models in animation generation has become a popular research direction. In this paper, by comparing the performance of these models in animation generation, experiments are designed to evaluate their advantages and shortcomings in image generation quality, generation speed and application scene adaptability. The experimental results show that GAN performs well in generation quality and speed, CLIP excels in cross-modal understanding and generation tasks, and the diffusion model has unique advantages in generation accuracy and detail processing. The experiments in this paper provide new ideas for the future development of animation technology.

Copyright

© 2024 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  - Yujie Zhao
PY  - 2024
DA  - 2024/12/14
TI  - Intelligent Mining: Research and Application of Intelligent Generation Animation Technology
BT  - Proceedings of the 2024 6th International Conference on Literature, Art and Human Development (ICLAHD 2024)
PB  - Atlantis Press
SP  - 524
EP  - 533
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-319-1_61
DO  - 10.2991/978-2-38476-319-1_61
ID  - Zhao2024
ER  -