Generative-AI-based game asset creation: developing a system for supporting game production brainstorming
Resumo
Introduction: Recent advances in generative AI have surprised the public by quickly generating text and images of good quality, impacting many entertainment industries, like the game industry. Despite concerns related to data privacy and plagiarism, generative AI can support artists and developers during the brainstorming process, enhancing creativity and performance. Objective: This research develops a system that integrates different generative AI technologies to assist game asset creation (text, image, and sound) all in one place. Developers can define, among other things, a protagonist’s concept art, generate associated NPCs (both image and text), create quests (text), and a short soundtrack (audio). Methodology or Steps: To develop the proposed solution, an initial study on the different generative AI models for different assets was conducted. This was followed by the system development using Python, Streamlit, and some APIs. Finally, a set of experiments was conducted to analyze the system’s capability to generate high-quality and diverse assets for a role-playing game. Results: The results demonstrate the system’s potential to facilitate the creative process by optimizing the prompt engineering process and combining multiple generative AI technologies in a single tool, offering a versatile solution for both small teams and larger studios.
Palavras-chave:
Generative AI models, Assets generation, Game Development, Game Art Generation
Referências
AI, L. (2023). Layer ai: Customizable image generation for 3d assets. [link].
Ammanabrolu, P., Broniec, W., Mueller, A., Paul, J., e Riedl, M. O. (2020). Toward automated quest generation in text-adventure games.
Auroch Digital, I. (2022). How much does it cost to make a game. [link] [Accessado em: (12/01/2025)].
Buongiorno, S., Klinkert, L., Zhuang, Z., Chawla, T., e Clark, C. (2024). Pangea: procedural artificial narrative using generative ai for turn-based, role-playing video games. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, volume 20, pages 156–166.
Dang, H., Brudy, F., Fitzmaurice, G., e Anderson, F. (2023). Worldsmith: Iterative and expressive prompting for world building with a generative ai. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pages 1–17.
DeepMind (2024a). Deep seek: Advanced search and synthesis for textual information.
DeepMind, G. (2024b). Gemini: A multimodal approach for advanced ai tasks.
Deloitte (2024). Deloitte 2024 gaming outlook: Transmedia and generative ai. Accessed: 2025-01-26.
dos Santos, G. A. C., Baffa, A., Briot, J.-P., Feijó, B., e Furtado, A. L. (2022). An adaptive music generation architecture for games based on the deep learning transformer model. arXiv preprint arXiv:2207.01698.
Earle, S., Parajuli, S., e Banburski-Fahey, A. (2024). Dreamgarden: A designer assistant for growing games from a single prompt.
Esser, P., Kulal, S., Blattmann, A., Entezari, R., Müller, J., Saini, H., Levi, Y., Lorenz, D., Sauer, A., Boesel, F., et al. (2024). Scaling rectified flow transformers for high-resolution image synthesis. In Forty-first international conference on machine learning.
Future Trans (2024). Leveling up: How generative ai is revolutionizing game localization. Available at [link]. Accessed on January 28, 2025.
GDC, I. (2017). Achieving two worlds, every year: How magic the gathering sustainably doubled its worldbuilding. [link] [Accessado em: (02/02/2025)].
Géron, A. (2022). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems. "O’Reilly Media, Inc.".
JaeJun Lee, So-Youn Eom, J. L. (2023). Empowering game designers with generative ai. International Journal of Computer Science and Information Systems.
Kalyan, K. S. (2024). A survey of gpt-3 family large language models including chatgpt and gpt-4. Natural Language Processing Journal, 6:100048.
Mao, X., Yu, W., Yamada, K. D., e Zielewski, M. R. (2024). Procedural content generation via generative artificial intelligence.
Meta AI (2023a). Audiocraft: Ai music generation. [link].
Meta AI (2023b). Llama: Open and efficient foundation language models. [link].
OpenAI (2023). Gpt-4. [link].
Proxima Enterprises Inc (2024). Suck up! Digital. Available at: [link]. Accessed on January 28, 2025.
Schrum, J., Gutierrez, J., Volz, V., Liu, J., Lucas, S., e Risi, S. (2020). Interactive evolution and exploration within latent level-design space of generative adversarial networks.
Sun, Y., Li, Z., Fang, K., Lee, C. H., e Asadipour, A. (2023). Language as reality: a co-creative storytelling game experience in 1001 nights using generative ai. 19(1):425– 434.
Technologies, A. (2022). Aiva: Artificial intelligence virtual artist for music composition. [link].
Ammanabrolu, P., Broniec, W., Mueller, A., Paul, J., e Riedl, M. O. (2020). Toward automated quest generation in text-adventure games.
Auroch Digital, I. (2022). How much does it cost to make a game. [link] [Accessado em: (12/01/2025)].
Buongiorno, S., Klinkert, L., Zhuang, Z., Chawla, T., e Clark, C. (2024). Pangea: procedural artificial narrative using generative ai for turn-based, role-playing video games. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, volume 20, pages 156–166.
Dang, H., Brudy, F., Fitzmaurice, G., e Anderson, F. (2023). Worldsmith: Iterative and expressive prompting for world building with a generative ai. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pages 1–17.
DeepMind (2024a). Deep seek: Advanced search and synthesis for textual information.
DeepMind, G. (2024b). Gemini: A multimodal approach for advanced ai tasks.
Deloitte (2024). Deloitte 2024 gaming outlook: Transmedia and generative ai. Accessed: 2025-01-26.
dos Santos, G. A. C., Baffa, A., Briot, J.-P., Feijó, B., e Furtado, A. L. (2022). An adaptive music generation architecture for games based on the deep learning transformer model. arXiv preprint arXiv:2207.01698.
Earle, S., Parajuli, S., e Banburski-Fahey, A. (2024). Dreamgarden: A designer assistant for growing games from a single prompt.
Esser, P., Kulal, S., Blattmann, A., Entezari, R., Müller, J., Saini, H., Levi, Y., Lorenz, D., Sauer, A., Boesel, F., et al. (2024). Scaling rectified flow transformers for high-resolution image synthesis. In Forty-first international conference on machine learning.
Future Trans (2024). Leveling up: How generative ai is revolutionizing game localization. Available at [link]. Accessed on January 28, 2025.
GDC, I. (2017). Achieving two worlds, every year: How magic the gathering sustainably doubled its worldbuilding. [link] [Accessado em: (02/02/2025)].
Géron, A. (2022). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems. "O’Reilly Media, Inc.".
JaeJun Lee, So-Youn Eom, J. L. (2023). Empowering game designers with generative ai. International Journal of Computer Science and Information Systems.
Kalyan, K. S. (2024). A survey of gpt-3 family large language models including chatgpt and gpt-4. Natural Language Processing Journal, 6:100048.
Mao, X., Yu, W., Yamada, K. D., e Zielewski, M. R. (2024). Procedural content generation via generative artificial intelligence.
Meta AI (2023a). Audiocraft: Ai music generation. [link].
Meta AI (2023b). Llama: Open and efficient foundation language models. [link].
OpenAI (2023). Gpt-4. [link].
Proxima Enterprises Inc (2024). Suck up! Digital. Available at: [link]. Accessed on January 28, 2025.
Schrum, J., Gutierrez, J., Volz, V., Liu, J., Lucas, S., e Risi, S. (2020). Interactive evolution and exploration within latent level-design space of generative adversarial networks.
Sun, Y., Li, Z., Fang, K., Lee, C. H., e Asadipour, A. (2023). Language as reality: a co-creative storytelling game experience in 1001 nights using generative ai. 19(1):425– 434.
Technologies, A. (2022). Aiva: Artificial intelligence virtual artist for music composition. [link].
Publicado
30/09/2025
Como Citar
CAVALCANTI, Luiz Paulo S. B.; BEZERRA, Pamela T. L.; BARROS, Gabriella A. B..
Generative-AI-based game asset creation: developing a system for supporting game production brainstorming. In: TRILHA DE COMPUTAÇÃO – ARTIGOS CURTOS - SIMPÓSIO BRASILEIRO DE JOGOS E ENTRETENIMENTO DIGITAL (SBGAMES), 14. , 2025, Salvador/BA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 38-44.
DOI: https://doi.org/10.5753/sbgames_estendido.2025.10149.
