A Comparative Study on the Practicality of AI Video Generation Tools in Short Video Creation

Main Article Content

Ruolin Wang
Shandong Normal University, Daxue Road, Jinan City, Shandong Province, China

DOI: https://doi.org/10.70267/aitia.2026427434

Keywords

AI video generation, text-to-video, short-video platforms, sora, runway, Seedance

Abstract

With the rapid advancement of artificial intelligence, AI-generated content (AIGC) is experiencing explosive growth on short-form video platforms. It is increasingly permeating diverse fields, including lifestyle entertainment, gaming, and anime. Currently, the mainstream AI video-generation technologies primarily include three paradigms: text-to-video (T2V), image-to-video (I2V), and video-to-video (V2V). These three types of technologies differ significantly in their generation mechanisms, underlying principles, and output quality. Empirical studies reveal that the quality of AI-generated videos exhibits considerable heterogeneity. Some works achieve a remarkable level of realism, closely resembling real-world scenarios, while other low-quality content displays obvious flaws that make it easily identifiable. In-depth analysis shows that T2V technology excels in following user instructions and generating high-quality videos, while V2V technology also delivers impressive visual transformation results. By contrast, I2V technology is constrained by the limited information in the source images and insufficient guidance from prompts, which often makes it difficult to produce satisfactory dynamic videos. Moreover, influenced by the algorithmic recommendation mechanisms of short-video platforms, different platforms adopt varying strategies for distributing AI-generated content. Based on these observations, this paper aims to explore how to optimize the AI video creation process and, in conjunction with platform rules, develop effective publishing strategies to enhance the dissemination and impact of AI-generated content within the short-video ecosystem.

Abstract 9 | PDF Downloads 3

References

  • [1] V. Arkhipkin et al., “ImproveYourVideos: Architectural Improvements for Text-to-Video Generation Pipeline,” IEEE Access, vol. 13, pp. 1986–2003, Jan. 2025, doi: 10.1109/access.2024.3522510.
  • [2] I. Chivileva, P. Lynch, T. E. Ward, and A. F. Smeaton, “A dataset of text prompts, videos and video quality metrics from generative text-to-video AI models,” Data Brief, vol. 54, p. 110514, Jun. 2024, doi: 10.1016/j.dib.2024.110514.
  • [3] Y. Chen, W. Chu, Y. Wu, J. Yang, X. Mao, and W. Liu, “COTA-motion: Controllable image-to-video synthesis with dense semantic trajectories,” Neurocomputing, vol. 657, p. 131671, Dec. 2025, doi: 10.1016/j.neucom.2025.131671.
  • [4] G. T. T. Nguyen and H. T. M. Nguyen, “AI Content, User Fatigue, and Churn on TikTok: Testing an Integrated Stressor Model,” Hum. Behav. Emerg. Technol., vol. 2026, no. 1, p. 9977742, 2026, doi: 10.1155/hbe2/9977742.
  • [5] P. Bijalwan, A. Gupta, A. Johri, M. Wasiq, and S. K. Wani, “Unveiling sora open AI’s impact: a review of transformative shifts in marketing and advertising employment,” Cogent Bus. Manag., vol. 12, no. 1, p. 2440640, Dec. 2025, doi: 10.1080/23311975.2024.2440640.
  • [6] Z. Qi et al., “T2VEval: Benchmark dataset and objective evaluation method for T2V-generated videos,” Displays, vol. 91, p. 103178, Jan. 2026, doi: 10.1016/j.displa.2025.103178.
  • [7] O. Hellmann, “Colonial Bias in AI Training Data: Prompting Sora to Generate Images of Aotearoa New Zealand’s Historical Past,” Kotuitui-N. Z. J. Soc. Sci. Online, vol. 21, no. 1, p. e70016, Feb. 2026, doi: 10.1002/kot2.70016.
  • [8] K. Z. Zhou, A. Choudhry, E. Gumusel, and M. R. Sanfilippo, “‘Sora is incredible and scary’: public perceptions and governance challenges of text-to-video generative AI models,” Inf. Res.- Int. Electron. J., vol. 30, pp. 508–522, Mar. 2025, doi: 10.47989/ir30iConf47290.
  • [9] “Sora Service Discontinuation Notice,” OpenAI Help Center. Accessed: Jun. 27, 2026. [Online]. Available: https://help.openai.com/zh-hans-cn/articles/20001152-what-to-know-about-the-sora- discontinuation?f_link_type=f_linkinlinenote&show_loading=0&flow_extra=eyJpbmxpbmVfZGlzcGx heV9wb3NpdGlvbiI6MCwiZG9jX3Bvc2l0aW9uIjowLCJkb2NfaWQiOiIzNDZiYTlmMWVjNThjYzkz LTY1MjZmZjFmYzAyMTBhYTIifQ%3D%3D&webview_progress_bar=1&push_animated=1&theme =light
  • [10] V. Video, “Veo 3 - Google DeepMind,” Vexa Video. Accessed: Jun. 27, 2026. [Online]. Available: https://vexavideo.com/zh/veo3
  • [11] “Veo: a text-to-video generation system.” deepmind google. [Online]. Available: https://storage.googleapis.com/deepmind-media/veo/Veo-3-Tech-Report.pdf
  • [12] A. Budiman, N. A. Rakhmawati, and D. Purwitasari, “Cultivating Participatory Learning Ecologies: Social Network Analysis of Peer-Driven Learning Network,” J. Inf. Technol. Educ. -Res., vol. 25, p. 6, 2026, doi: 10.28945/5719.
  • [13] “Free Pika AI Video Generator | Powered by Pika Art Labs for Efficient Creative Expression,” Pika AI. Accessed: Jun. 27, 2026. [Online]. Available: https://pikaai.org/blog/detail/Pika-AI-by-Pika-Lab%3A- Revolutionizing-Video-Creation-with-AI-Technology-c6772b05b14a/
  • [14] M. Kawka, “Theological imaginal reflections with AI artworks: revealing and obscuring divine knowledge in aesthetic experience,” Pract. Theol., vol. 18, no. 2, pp. 152–167, Mar. 2025, doi: 10.1080/1756073X.2025.2474318.
  • [15] “Creating with Keyframes on Gen -3,” Runway. Accessed: Jun. 27, 2026. [Online]. Available: https://help.runwayml.com/hc/en-us/articles/34170748696595-Creating-with-Keyframes-on-Gen-3
  • [16] “Product Updates & Changelog | Runway AI.” Accessed: Jun. 27, 2026. [Online]. Available: https://runwayml.com/changelog?show_loading=0&webview_progress_bar=1&flow_extra=eyJpbmxpb mVfZGlzcGxheV9wb3NpdGlvbiI6MCwiZG9jX3Bvc2l0aW9uIjowLCJkb2NfaWQiOiI3Nzg0MzFjYz U3Yjg4NzE4LTU0NWFmMDkyMmU5ZDMzZTYifQ%3D%3D&f_link_type=f_linkinlinenote&push _animated=1&theme=light
  • [17] “Runway Research | Autoregressive-to-Diffusion Vision Language Models.” Accessed: Jun. 27, 2026. [Online]. Available: https://runwayml.com/research/autoregressive-to-diffusion-vlms
  • [18] “Team Dynamics-ByteDance Seed.” Accessed: Jun. 27, 2026. [Online]. Available: https://seed.bytedance.com/zh/blog/seedance-2-0-official-launch?view_from=content_recommend
  • [19] “Seedance 2.0.” Accessed: Jun. 27, 2026. [Online]. Available: https://seed.bytedance.com/zh/seedance2_0
  • [20] “Douyin Rule Center.” Accessed: Jun. 27, 2026. [Online]. Available: https://api.amemv.com/magic/eco/runtime/release/6458b8f26a0a4e036e02ee15?appType=douyin&magi c_page_no=1&magic_source=minebanner
  • [21] “Announcement on the Governance of the Misuse of AI-Generated Virtual Characters.” Accessed: Jun. 27, 2026. [Online]. Available: https://api.amemv.com/magic/eco/runtime/release/6603900cbc1ea9062e329273?appType=douyin&hide _nav_bar=1&auto_play_bgm=1&container_bg_color=%23ffffff&loading_bg_color=%23ffffff&loading _duration=1000&_pia_=1&loader_name=forest
  • [22] “Stop calling it GPT! Codex is the true ‘engineer’ of AI programming —a comprehensive guide to breaking down advantages, risks, and implementation.” Accessed: Jun. 27, 2026. [Online]. Available: https://juejin.cn/post/7642725839920463882?webview_progress_bar=1&push_animated=1&show_load ing=0&flow_extra=eyJpbmxpbmVfZGlzcGxheV9wb3NpdGlvbiI6MCwiZG9jX3Bvc2l0aW9uIjowLCJ kb2NfaWQiOiIyNzQzZjRmMDFjYjg1MmZkLWQxYjg3N2UyOGU2OTkzN2EifQ%3D%3D&f_link_ type=f_linkinlinenote&theme=light
  • [23] D. Dharrao et al., “AI-driven audio-to-video generation for dynamic content creation via stable diffusion and CNN-augmented transformers,” Sci. Rep., vol. 16, no. 1, p. 10295, Feb. 2026, doi: 10.1038/s41598 - 026-38758-3.
  • [24] A. El Assadi, “Ai vs. human creativity: the impact of text-to-image and text-to-video ads on customer engagement,” Electron. Commer. Res., Feb. 2026, doi: 10.1007/s10660-026-10103-w.
  • [25] I. T. Seo, H. Liu, H. Li, and J. -S. Lee, “AI-infused video marketing: Exploring the influence of AI-generated tourism videos on tourist decision-making,” Tour. Manag., vol. 110, p. 105182, Oct. 2025, doi: 10.1016/j.tourman.2025.105182.

Article Sidebar

PDF
Published
Sep 13, 2026
Conference Proceedings Volume
Vol. 16 (2026): Proceedings of the 2026 International Conference on AI and Technological Innovation Applications (AITIA 2026)
Section
Articles
Creative Commons License

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

How to Cite

Wang, Ruolin. “A Comparative Study on the Practicality of AI Video Generation Tools in Short Video Creation”. Exploring Science Academic Conference Series, vol. 16, Sept. 2026, pp. 427-34, https://doi.org/10.70267/aitia.2026427434.