Education, Science, Technology, Innovation and Life
Open Access
Sign In

AI Application to Generate an Expected Picture Using Keywords with Stable Diffusion

Download as PDF

DOI: 10.23977/jaip.2023.060110 | Downloads: 200 | Views: 1483


Zhan Shi 1


1 Shanghai Guanghua Qidi College, Shanghai, China

Corresponding Author

Zhan Shi


Nowadays, artificial intelligence (AI) has a big impact in the field of painting. In contrast to the hand-painting and challenging personal creativity, AI applications practices to add noise, remove noise, restore image and conserve the present process after converting to data. The various AI image generator models, Diffusion model is the latest application and consist of two main models, word-image mapping and diffusion algorithm. This article is introduced the mechanism of how images are generated and makes arguments about several ethical issues of AI application of image generation. As a result, sophisticated legal restrictions should be implemented to prevent possible negative effects of AI models.


Stable Diffusion; Diffusion model; Image processing; Ethical issues


Zhan Shi, AI Application to Generate an Expected Picture Using Keywords with Stable Diffusion. Journal of Artificial Intelligence Practice (2023) Vol. 6: 66-71. DOI:


[1] Ling Yang, Zhilong Zhang, Yang Song, Shenda Hong, Runsheng Xu, Yue Zhao, Yingxia Shao, Wentao Zhang, Bin Cui, and Minghsuan Yang. 2022. Diffusion Models: A Comprehensive Survey of Methods and Applications. 1, 1 (October 2022), 39 pages.
[2] Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In Advances in Neural Information Processing Systems, Vol. 33. 6840–6851.
[3] Daphne Koller and Nir Friedman. 2009. Probabilistic graphical models: principles and techniques. MIT press.
[4] Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using non-equilibrium thermodynamics. In International Conference on Machine Learning. 2256–2265.
[5] Cao Hanqun, Cheng Tan, Zhangyang Gao, Guangyong Chen, Pheng-Ann Heng and Stan Z. Li. "A Survey on Generative Diffusion Model." ArXiv abs/2209.02646 (2022)
[6] Kingma Diederik P., Tim Salimans and Max Welling. "Improved Variational Inference with Inverse Autoregressive Flow." ArXiv abs/1606.04934 (2016)
[7] Rombach, Robin, A. Blattmann, Dominik Lorenz, Patrick Esser and Björn Ommer. "High-Resolution Image Synthesis with Latent Diffusion Models." 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021): 10674-10685.

Downloads: 7897
Visits: 208232

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.