Automated deepfake generation process based on AI painting technology

Qianru Liu () and Ki-Hong Kim ()

Edelweiss Applied Science and Technology, 2025, vol. 9, issue 4, 2222-2234

Abstract: This paper addresses the significant data acquisition challenges in Deepfake technology by proposing an innovative methodology leveraging AI painting generation for creating facial datasets. The study aims to overcome traditional Deepfake limitations, including privacy concerns, copyright issues, and high costs associated with acquiring authentic portrait data. The research integrates AI art generation software (Midjourney with InsightFaceSwap) with Deepfake production software (DeepFace Lab) to create an automated workflow that generates diverse, consistent facial datasets for model training. Results demonstrate that AI-generated facial datasets can effectively substitute authentic human images while maintaining high-quality outputs. The proposed workflow significantly reduces data acquisition bottlenecks, mitigates legal risks, and substantially lowers production costs. Combining AI art generation with Deepfake technology offers a promising direction for advancing synthetic media creation while balancing innovation with ethical considerations. This methodology enhances the ethical application of Deepfake technology across entertainment, education, and digital media production, potentially transforming how synthetic visual content is created and used.

Keywords: Artificial intelligence painting; Deepfake; Model training; Workflow. (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://learning-gate.com/index.php/2576-8484/article/view/6539/2310 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ajp:edwast:v:9:y:2025:i:4:p:2222-2234:id:6539

Access Statistics for this article

More articles in Edelweiss Applied Science and Technology from Learning Gate
Bibliographic data for series maintained by Melissa Fernandes ().