A Change of Pace
Generative AI and Storyboard Flexibility in Pre-production
DOI:
https://doi.org/10.65598/rps.6287Keywords:
storyboard, film pre-production, generative artificial intelligence, ComfyUI, FLUXAbstract
This article presents an exploratory study on the operational maturity of generative artificial intelligence applied to storyboarding in fiction film pre-production. Its aim is to examine whether a local, modular workflow based on ComfyUI can produce a functionally comparable version of a previously published professional storyboard from a script fragment and, from that visual base, generate variations in framing, composition, and action resolution without having to restart the process from scratch. To this end, the study adopts a single-case design focused on six panels from a commercial feature-film sequence, reconstructed through a local *image-to-image* and *inpainting* workflow using the FLUX.2 [klein] 9B fp8 model, without employing LoRAs or ControlNet. The results show that functional reconstruction was viable for all six panels, while controlled variations were successfully produced in four of them. The main limitations emerged when the image required precise representation of highly specific spatial and causal relations, such as a projectile striking an aircraft or the imminence of a crash, an area in which recent literature has identified persistent weaknesses in open diffusion models. The study concludes that ComfyUI, as a node-based, local, and configurable environment, already offers relevant professional utility for rapid storyboard ideation, reformulation, and alternative exploration, although its full professional use still requires additional control mechanisms in sequences demanding greater spatial or kinetic precision.
Downloads
References
Burton, T. (Director). (1989). Batman [Película]. Warner Bros.
Caballero, J., & Sora-Domenjó, C. (2024). Automation and creativity in AI-driven film editing: The view from the professional documentary sector. Communication & Society, 37(3), 201–218. https://doi.org/10.15581/003.37.3.201-218
Caballero, J., Sora-Domenjó, C., & Codina, L. (2025). Implications of generative artificial intelligence in cinematic narrative and aesthetics: A study of entries to OpenDocs and the +RAIN film festival. Anàlisi, 71, 55–76. https://doi.org/10.5565/rev/analisi.3773
Comfy-Org. (s. f.-a). ComfyUI official documentation. https://docs.comfy.org/
Comfy-Org. (s. f.-b). ComfyUI-Manager installation. https://docs.comfy.org/manager/install
ComfyUI. (2026, 15 de enero). FLUX.2 [klein] 4B & 9B: Fast local image editing and generation. ComfyUI Blog. https://blog.comfy.org/p/flux2-klein-4b-fast-local-image-editing
Dueñas Mohedas, S., & Jiménez Alcarria, F. (2025). Generative artificial intelligence in media production: The emerging role of artificial intelligence artist in Spain. Comunicação e Sociedade, 47, e025011. https://doi.org/10.17231/comsoc.47(2025).6212
Feng, Y., Gong, B., Chen, D., Shen, Y., Liu, Y., & Zhou, J. (2024). Ranni: Taming text-to-image diffusion for accurate instruction following. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4744–4753). https://openaccess.thecvf.com/content/CVPR2024/html/Feng_Ranni_Taming_Text-to-image_Diffusion_for_Accurate_Instruction_Following_CVPR_2024_paper.html
Filmsketchr. (2012, 18 de junio). Batman 1989 Batwing concept art and storyboards by David Russell. https://filmsketchr.blogspot.com/2012/06/batman-1989-batwing-concept-art-and.html
Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2021). LoRA: Low-rank adaptation of large language models [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2106.09685
Pallant, C., & Price, S. (2015). Storyboarding: A critical history. Palgrave Macmillan. https://doi.org/10.1057/9781137027603
Prisma Social. (s. f.). Política sobre uso de inteligencia artificial. https://revistaprismasocial.es/ps/politicaia
Russell, D. (s. f.). Batman [Portfolio de storyboard]. https://www.dynamicimagesdr.com/batman
Skills England. (2025). Storyboard artist (ST0489). https://skillsengland.education.gov.uk/apprenticeships/st0489-v1-1
Sookhom, A., Klinthai, P., A-masiri, P., & Kerdvibulvech, C. (2023). A new study of AI artists for changing the movie industries. Digital Society, 2, Article 37. https://doi.org/10.1007/s44206-023-00065-z
Wang, S., Menon, S., Long, T., Henderson, K., Li, D., Crowston, K., Hansen, M., Nickerson, J. V., & Chilton, L. B. (2024). ReelFramer: Human-AI co-creation for news-to-video translation. In Proceedings of the CHI Conference on Human Factors in Computing Systems. ACM. https://doi.org/10.1145/3613904.3642868
Wei, Z., Wu, H., Zhang, L., Xu, X., Zheng, Y., Hui, P., Agrawala, M., Qu, H., & Rao, A. (2025). CineVision: An interactive pre-visualization storyboard system for director-cinematographer collaboration. In Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology. ACM. https://doi.org/10.1145/3746059.3747793
YunoJuno. (s. f.). Storyboard artist freelance rates. Recuperado el 26 de abril de 2026 de https://www.yunojuno.com/freelancer-rates-job-role/storyboard-artist
Zhang, G., Fu, B., Fan, Q., Zhang, Q., Liu, R., Gu, H., Zhang, H., & Liu, X. (2025). CoMPaSS: Enhancing spatial understanding in text-to-image diffusion models. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 15253–15265). https://openaccess.thecvf.com/content/ICCV2025/html/Zhang_CoMPaSS_Enhancing_Spatial_Understanding_in_Text-to-image_Diffusion_Models_ICCV_2025_paper.html
Zhang, L., Rao, A., & Agrawala, M. (2023). Adding conditional control to text-to-image diffusion models. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 3836–3847). https://doi.org/10.1109/ICCV51070.2023.00355
Zhang, R., Yu, B., Min, J., Xin, Y., Wei, Z., Shi, J. N., Huang, M., Kong, X., Xin, N. L., Jiang, S., Bahuguna, P., Chan, M., Hora, K., Yang, L., Liang, Y., Bian, R., Liu, Y., Campillo Valencia, I., Morales Tredinick, P., Kozlov, I., Jiang, S., Huang, P., Chen, N., Liu, X., & Rao, A. (2025). Generative AI for film creation: A survey of recent advances [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2504.08296
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Authors retain copyright and transfer to the journal the right of first publication and publishing rights
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Those authors who publish in this journal accept the following terms:
-
Authors retain copyright.
-
Authors transfer to the journal the right of first publication. The journal also owns the publishing rights.
-
All published contents are governed by an Attribution-NoDerivatives 4.0 International License.
Access the informative version and legal text of the license. By virtue of this, third parties are allowed to use what is published as long as they mention the authorship of the work and the first publication in this journal. If you transform the material, you may not distribute the modified work. -
Authors may make other independent and additional contractual arrangements for non-exclusive distribution of the version of the article published in this journal (e.g., inclusion in an institutional repository or publication in a book) as long as they clearly indicate that the work was first published in this journal.
- Authors are allowed and recommended to publish their work on the Internet (for example on institutional and personal websites), following the publication of, and referencing the journal, as this could lead to constructive exchanges and a more extensive and quick circulation of published works (see The Effect of Open Access).
