International Journal of Internet, Broadcasting and Communication

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on AI Softwear [Stable Diffusion] ControlNet plug-in Usabilities

  • Chenghao Wang (Dept. of Multimedia, Graduate School of Digital Image and Contents Dongguk University) ;
  • Jeanhun Chung (Dept. of Multimedia, Graduate School of Digital Image and Contents Dongguk University)
  • Received : 2023.09.19
  • Accepted : 2023.09.30
  • Published : 2023.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

With significant advancements in the field of artificial intelligence, many novel algorithms and technologies have emerged. Currently, AI painting can generate high-quality images based on textual descriptions. However, it is often challenging to control details when generating images, even with complex textual inputs. Therefore, there is a need to implement additional control mechanisms beyond textual descriptions. Based on ControlNet, this passage describes a combined utilization of various local controls (such as edge maps and depth maps) and global control within a single model. It provides a comprehensive exposition of the fundamental concepts of ControlNet, elucidating its theoretical foundation and relevant technological features. Furthermore, combining methods and applications, understanding the technical characteristics involves analyzing distinct advantages and image differences. This further explores insights into the development of image generation patterns.

Keywords

References

  1. Chenghao Wang, Jeanhun Chung. "Research on AI Painting Generation Technology Based on the [Stable Diffusion]" The International Journal of Advanced Smart Convergence 12.2 pp.90-95 (2023) : 90. DOI:http://dx.doi.org/10.7236/IJASC.2023.12.2.903
  2. Zhang, Lvmin, and Maneesh Agrawala. "Adding conditional control to text-to-image diffusion models." arXiv preprint arXiv:2302.05543 (2023). DOI:https://doi.org/10.48550/arXiv.2302.05543
  3. Jin, Ze, and Zorina Song. "Generating coherent comic with rich story using ChatGPT and Stable Diffusion." arXiv preprint arXiv:2305.11067 (2023). DOI:https://doi.org/10.48550/arXiv.2305.11067
  4. Zhao, Shihao, et al. "Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models." arXiv preprint arXiv:2305.16322 (2023). DOI:https://doi.org/10.48550/arXiv.2305.16322
  5. Qin, Can, et al. "UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild." arXiv preprint arXiv:2305.11147 (2023). DOI:https://doi.org/10.48550/arXiv.2305.11147
  6. Engadget, ControlNet the magic of controlled diffusion model. https://juejin.cn/post/7234554420163493944
  7. Hickman Design, AI Generated Art: A Revolutionary Creative Force With A Double Edge https://hickmandesign.co.uk/blog/news/ai-generated-art/
  8. 51CTO, ControlNet star count exceeds 10,000! In 2023, will AI painting go crazy? https://www.51cto.com/article/748002.html