Home⇛International Journal of Multidisciplinary: Applied Business and Education Research⇛vol. 7 no. 4 (2026)

AI-Powered Sprite Generation for Visual Novel Games: A Latent Diffusion Model Approach

Pio Honesto Rico Belleza | Aaron Dwayne F. Esmaquel | Edmund N. Lazaro | Eliza B. Ayo

Discipline: computer games and animation

 

Abstract:

Creating character sprites for visual novel games has long been a re- source-intensive process, erecting significant barriers for independ- ent developers and small studios. Accessible, high-quality asset gen- eration remains an unmet need-one this study addresses by devel- oping a specialized AI-powered sprite generator built on a Latent Dif- fusion Model (LDM) fine-tuned with Low-Rank Adaptation (LoRA). Unlike general-purpose image generators, the system is optimized specifically for 2D anime-style character sprites with multiple emo- tional variants, making it suitable for narrative-driven gameplay. De- velopment followed a seven-phase Agile methodology, and evaluation involved 50 student game developers working against ISO/IEC 25010 software quality standards. Results confirm that the system reliably generates up to nine cohesive emotional variants from a single text prompt, substantially streamlining the asset-creation workflow. User scores indicate strong satisfaction with Functional Suitability (M=3.73), Security (M=3.74), and Usability (M=3.66). Performance Efficiency received a lower rating (M=3.20, Agree), attributable to a generation latency of approximately 2-3 minutes per sprite set-ac- ceptable for final production, but less so for rapid prototyping. Taken together, these findings support the viability of specialized LDM ap- plications as practical tools for democratizing visual game develop- ment and empowering collaborative storytelling.



References:

  1. Duan, H., & Zhang, J. (2022). AI-driven environ-mental concept design: A framework for adaptive visual stimuli in interactive sto-rytelling. Journal of Digital Media Arts, 14(2), 112-128.
  2. Ergen, T. (2023). Procedural generation of video game characters using StyleGAN2: techniques and applications. International Journal of Computer Games Technology, 2023, Article 451239.
  3. Gonzalez, M. (2020). The artificial art director: AI as a creative partner in game develop-ment. Game Studies, 20(1). http://gamestudies.org/2001/arti-cles/gonzalez">http://gamestudies.org/2001/arti-cles/gonzalez">http://gamestudies.org/2001/arti-cles/gonzalez
  4. Ma, X., Li, Y., & Chen, S. (2022). AI Illustrator: A cross-modal framework for narrative vis-ualization. IEEE Transactions on Multime-dia, 24, 2890-2902.
  5. Park, J., Kim, S., & Yoo, D. (2021). Enhancing digital literacy in education through AI-as-sisted storytelling tools. Computers & Edu-cation, 168, 104201.
  6. Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022). Hierarchical text-condi-tional image generation with CLIP latents. arXiv preprint arXiv:2204.06125.
  7. Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution im-age synthesis with latent diffusion mod-els. In Proceedings of the IEEE/CVF Confer-ence on Computer Vision and Pattern Recognition (pp. 10684-10695).
  8. Shi, Y., Wang, X., & Liu, Z. (2020). PokerFace-GAN: Generating neutral face templates for game character customization. ACM Transactions on Graphics, 39(4), 89:1-89:12.
  9. Tanaka, H., & Kobayashi, S. (2021). Automating game asset creation: A survey of AI-based approaches. Entertainment Computing, 38, 100412.Wu, L., Zhang, Y., & Wang, K. (2023). The impact of generative AI on video game visualiza-tion workflows. Journal of Graphics Tools, 27(1), 15-29.
  10. Xie, Y. (2024). Consistency challenges in AI-generated character art for serial narra-tives. Digital Creativity, 35(1), 45-60.
  11. Zhao, L., & Zhang, W. (2024). From GANs to Dif-fusion: A comparative analysis of text-to-image models in digital art. AI & Society, 39, 215-230.

Tools


Copyright © 2026  KITE Digital Educational Solutions |  Exclusively distributed by CE-Logic