Artificial Intelligence-Assisted Artistic Creation: A Human-AI Collaborative Framework for Style Transfer and Detail Enhancement

DOI

10.2991/978-94-6239-737-8_47How to use a DOI?

Keywords

Artificial Intelligence; Artistic Creation; Style Transfer; Hu-man-AI Collaboration; Diffusion Model; Digital Painting

Abstract

To address the limitations of current AI-generated art tools in achieving fine-grained style control, preserving local details, and enabling iterative human refinement, this paper proposes a human-AI collaborative artistic creation framework. First, visual-semantic features are extracted from reference images and user brushstrokes to construct an artistic behavior prediction model. Second, mapping rules between AI-generated regions and editable layers in digital painting software (e.g., Procreate, Photoshop) are defined, and a combination of a Deep Q-Network (DQN) and a combination of a Deep Q-Network (DQN) for region-level action selection and a conditional diffusion model (CDM) for high-quality style transfer and detail enhancement is used to generate optimized solutions. The DQN determines which editing action to apply to each region, while the CDM executes the corresponding generation task. Finally, a three-stage workflow of “AI divergence + software refinement + artist tuning” is established. Experimental results show that the proposed method outperforms pure AI generation and pure manual creation in terms of style consistency, local editability, and user satisfaction, providing an efficient and flexible solution for AI-assisted art design.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ling Jin
AU  - Yingfei Jia
AU  - Weijing Zhong
AU  - Jiufang Mei
PY  - 2026
DA  - 2026/08/18
TI  - Artificial Intelligence-Assisted Artistic Creation: A Human-AI Collaborative Framework for Style Transfer and Detail Enhancement
BT  - Proceedings of the 2026 5th International Conference on Art Design and Digital Technology (ADDT 2026)
PB  - Atlantis Press
SP  - 377
EP  - 384
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6239-737-8_47
DO  - 10.2991/978-94-6239-737-8_47
ID  - Jin2026
ER  -