Comparative Analysis of Midjourney, Stable Diffusion and Krea: A Case Study on Storyboard Development with Artificial Intelligence
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
The landscape of artificial intelligence (AI) has witnessed a rapid and remarkable evolution, particularly within artistic applications. The integration of AI in artistic endeavors has been a longstanding practice. However, it attained widespread recognition with user-friendly workflows exemplified by Midjourney, DALL-E, and Stable Diffusion. The transformative capabilities of AI have empowered individuals to expeditiously generate artistic paintings, marking a paradigm shift in the temporal dynamics of artistic production. Consequently, this study undertakes a comprehensive comparative analysis of Midjourney, Stable Diffusion, and Krea within the context of storyboard development in animation pre-production. The primary focus centers on elucidating effective methodologies for leveraging these generators in storyboard creation. The analytical framework scrutinizes their distinctive approaches, output quality, user-friendliness, and overall impact on workflow dynamics. Crucially, the findings of this study underscore that these generators, while collectively enhancing efficiency and creative possibilities in storyboard development, each proffers unique advantages: Midjourney excels in the realms of artistic quality and visual allure, Stable Diffusion demonstrates superiority in user control and customization, while Krea distinguishes itself with its noteworthy real-time AI image generation capabilities.
Abstract
The landscape of artificial intelligence (AI) has witnessed a rapid and remarkable evolution, particularly within artistic applications. The integration of AI in artistic endeavors has been a longstanding practice. However, it attained widespread recognition with user-friendly workflows exemplified by Midjourney, DALL-E, and Stable Diffusion. The transformative capabilities of AI have empowered individuals to expeditiously generate artistic paintings, marking a paradigm shift in the temporal dynamics of artistic production. Consequently, this study undertakes a comprehensive comparative analysis of Midjourney, Stable Diffusion, and Krea within the context of storyboard development in animation pre-production. The primary focus centers on elucidating effective methodologies for leveraging these generators in storyboard creation. The analytical framework scrutinizes their distinctive approaches, output quality, user-friendliness, and overall impact on workflow dynamics. Crucially, the findings of this study underscore that these generators, while collectively enhancing efficiency and creative possibilities in storyboard development, each proffers unique advantages: Midjourney excels in the realms of artistic quality and visual allure, Stable Diffusion demonstrates superiority in user control and customization, while Krea distinguishes itself with its noteworthy real-time AI image generation capabilities.
참고문헌 (16)
- J-K. Bae, "The use of artificial intelligence technology in the business field and artificial intelligence ethics", Journal of The Korea Knowledge Information Technology Society, 17(6), pp.1341~1352 (2022)
- J. McCormack, "Autonomy, authenticity, authorship and intention in computer generated art", Computational Intelligence in Music, Sound, Art and Desig, pp.35~50 (2019)
- S. Ali, "Telling creative stories using generative visual aids", 35th Conference on Neural Information Processing Systems (2021)
- R. A. Partadiredja, "AI or human: the socio-ethical implications of AI-generated media content", 13th CMI Conference on Cybersecurity and Privacy (CMI) - Digital Transformation -Potentials and Challenges, (51275), pp.1~6 (2020)
- J-Y. Kim, "AI as a pair programming buddy:exploring design considerations for human-AI collaboration", Journal of The Korea Knowledge Information Technology Society, 18(4), pp.839~860 (2023)
- P. J. Cobb, "Large language models and generative AI, oh my! Archaeology in the time of ChatGPT, Midjourney, and beyond", Advances in Archaeological Practice, 11(3), pp.363~369 (2023)
- A. Borji, "Generated faces in the wild:quantitative comparison of Stable Diffusion, Midjourney and DALL-E 2", ~ (2022)
- - A case study on character drawing, "The International Journal of Advanced Culture Technology", 2023, 403~408
- J. Ploennigs, "AI art in architecture", AI in Civil Engineering, 2 (2023)
- A. Jaruga-Rozdolska, "Artificial intelligence as part of future practices in the architect's work: MidJourney generative tool as part of a process of creating an architectural form", Architect, 3(71), pp.95~104 (2022)
- M. Ruskov, "Grimm in wonderland: prompt engineering with Midjourney to illustrate fairytales", 19th Conference on Information and Research science Connecting to Digital and Library Science, 3365, pp.180~191 (2023)
- "Metaswipes resources" (2023)[URL]
- P. Ekman, "What is meant by calling emotions basic", Emotion Review, 3(4), pp.364~370 (2011)
- S. Gu, "A model for basic emotions using observations of behavior in drosophila", Frontiers in Psychology, 10 (2019)
- R. E. Jack, "Dynamic facial expressions of emotion transmit an evolving hierarchy of signals over time", Current Biology, 24(2), pp.187~192 (2014)
- E. Cetinic, "Understanding and creating art with AI: review and outlook", ACM Transactions on Multimedia Computing, Communications, and Applications, 18(2), pp.1~22 (2022)