Abstract
Artificial intelligence plays a large role in the way that we consume content acting as a director behind the scenes controlling what and how we interact with digital mediums daily. Only within the last decade has AI software and hardware advanced to a point where it can also help contribute directly to content creation with the use of technologies such as generative adversarial networks (GANs). In this paper, we will examine some modern GAN solutions as well as the viability of an at-home model training experience in 2021 and into 2022. Specifically, the task being examined is the image synthesis of Pokémon Trading Cards. This dataset was chosen for its familiarity, large number of uniform samples, accessibility, and to examine the effects of training on datasets that share many consistent elements (card layout, formatting, color schemes). Some implications of being able to generate images in such a way are faster prototyping, a more streamlined workflow, or near-instantaneous content creation for creative professionals and illustrators.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wikimedia Foundation. Magic: The gathering. Wikipedia, 14 January 2022. https://en.wikipedia.org/wiki/Magic:_The_Gathering. Accessed 15 Jan 2022
Wikimedia Foundation. Pokémon trading card game. Wikipedia, 20 December 2021. https://en.wikipedia.org/wiki/Pok%C3%A9mon_Trading_Card_Game. Accessed 15 Jan 2022
Goodfellow, I.J., et al.: Generative adversarial nets. In: NIPS (2014)
Ramesh, A., et al.: Zero-shot text-to-image generation, 26 February 2021. arXiv.org. https://arxiv.org/abs/2102.12092. Accessed 15 Jan 2022
Zhang, H., et al.: Stackgan: text to photo-realistic image synthesis with stacked generative adversarial networks, 5 August 2017. arXiv.org. https://arxiv.org/abs/1612.03242. Accessed 15 Jan 2022
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan, 23 March 2020. arXiv.org. from https://arxiv.org/abs/1912.04958. Accessed 15 Jan 2022
NVlabs. NVlabs/stylegan2: StyleGAN2 - Official Tensorflow Implementation. GitHub (n.d.). https://github.com/NVlabs/stylegan2. Accessed 15 Jan 2022
Welcome to the pokémon TCG API DOCS!: Pokémon TCG API documentation. Pokmon TCG API Documentation Blog RSS. (n.d.). https://docs.pokemontcg.io/. Accessed 15 Jan 2022
High fidelity image generation using diffusion models. Google AI Blog, 16 July 2021. https://ai.googleblog.com/2021/07/high-fidelity-image-generation-using.html. Accessed 15 Jan 2022
NVlabs. NVlabs/stylegan3: Official PYTORCH implementation of stylegan3. GitHub (n.d.). https://github.com/NVlabs/stylegan3. Accessed 15 Jan 2022
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Scoon, K., Samara, K. (2023). Synthesizing Pokémon Trading Cards Using Nvidia StyleGAN2 from Home. In: Arai, K. (eds) Intelligent Systems and Applications. IntelliSys 2022. Lecture Notes in Networks and Systems, vol 543. Springer, Cham. https://doi.org/10.1007/978-3-031-16078-3_44
Download citation
DOI: https://doi.org/10.1007/978-3-031-16078-3_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16077-6
Online ISBN: 978-3-031-16078-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)