DOI QR코드

DOI QR Code

A Study on Character Consistency Generated in [Midjourney V6] Technology

  • Xi Chen (Dept. of Multimedia, Gradute School of Digital Image and Contents Dongguk University) ;
  • Jeanhun Chung (Dept. of Multimedia, Gradute School of Digital Image and Contents Dongguk University)
  • Received : 2024.04.28
  • Accepted : 2024.05.12
  • Published : 2024.06.30

Abstract

The emergence of programs like Midjourney, particularly known for its text-to-image capability, has significantly impacted design and creative industries. Midjourney continually updates its database and algorithms to enhance user experience, with a focus on character consistency. This paper's examination of the latest V6 version of Midjourney reveals notable advancements in its characteristics and design principles, especially in the realm of character generation. By comparing V6 with its predecessors, this study underscores the significant strides made in ensuring consistent character portrayal across different plots and timelines.Such improvements in AI-driven character consistency are pivotal for storytelling. They ensure coherent and reliable character representation, which is essential for narrative clarity, emotional resonance, and overall effectiveness. This coherence supports a more immersive and engaging storytelling experience, fostering deeper audience connection and enhancing creative expression.The findings of this study encourage further exploration of Midjourney's capabilities for artistic innovation. By leveraging its advanced character consistency, creators can push the boundaries of storytelling, leading to new and exciting developments in the fusion of technology and art.

Keywords

References

  1. CAO Yin, QIN Junping, MA Qianli, SUN Hao, YAN Kai, WANG Lei1,,REN Jiaqi,Survey of text-to-image synthesis.Journal of Zhejiang University (Engineering Science), Vol.58 ,No.2 pp.219-238, Feb. 2024 
  2. JlANG Shangsong SANG Ruijuan, Application of Text Semantic lmage Generation Technology in Furniture Design, Furniture,Vol.44 No.4, pp.36-41, 2023 
  3. Yang chenlu, Wan wanggen,Wang xuzhi, Image Semantic Understanding Based on Text-Aware and Non repetitive Word Generation,Industrial control computer, Vol. 36,No. 1,pp.105-109,2023. 
  4. YANG lili, AI Image Generation: Ending the Art Contract,Art China,vol.22(03).pp54-57,2023 
  5. Jihan Kim, A Study on the Usability of Digital Humans in New Media Contents,The International Journal of Advanced Smart Convergence, Vol.12 No.4,pp300-305,Dec,2023 
  6. DOI: http://dx.doi.org/10.7236/IJASC.2023.12.4.293 
  7. Ke Ma, Jeanhun Chung, A Research on 3D Texture Production Using Artificial Intelligence Softwear International Journal of Internet, Broadcasting and Communication Vol.15 No.4 pp178-184 (2023) DOI:http://dx.doi.org/10.7236/IJIBC.2023.15.4.178 
  8. SHI tianyuan,Research on the Theory and Method of Dialogue Response Diversity and Persona-Consistency Based on Neural Network,Chongqing University,Oct,2022