Collocation Generation and Style Consistency Verification of Personalized Soft Outfit Based on Diffusion Model
DOI:
https://doi.org/10.70393/6a696574.343132ARK:
https://n2t.net/ark:/40704/JIET.v1n2a03Disciplines:
Intelligent SystemsSubjects:
OtherReferences:
25Keywords:
Soft Outfit Design, Style Consistency Verification, Diffusion Model, Collocation Generation, ArtFID and Furnishing CLIP ScoreAbstract
There are some problems in traditional soft outfit design, such as low efficiency, difficult style understanding and low user participation, and the development of generative AI has brought new opportunities to solve these problems. In this study, a collaborative soft outfit generation system between users and AI is constructed. Through multi-modal condition fusion and dynamic style constraint method, users' fuzzy preferences are transformed into quantitative conditions, and personalized soft outfit schemes conforming to specific styles are generated. The system uses CLIP text and image encoder to extract features, and controls them in the potential space based on Stable Diffusion architecture, and optimizes the generation effect by combining style contrast loss. At the same time, a three-level verification system is proposed, including quantitative evaluation indicators such as ArtFID and FCS (Furnishing CLIP Score), and human evaluation as a supplement to objectively quantify the matching degree between the generated results and the target style. The experiment uses the FurniSynth data set built by ourselves, covering 10 mainstream decoration styles. The results show that compared with the existing methods, the method proposed in this paper has the best performance in style consistency, with an ArtFID index score of 19.3, a FCS semantic matching degree of 0.83, and a designer's subjective score of 4.6. In addition, the ablation experiment shows that the overall performance of the model can be gradually improved by adding each component in turn. This study not only technically breaks through the control problem of traditional model on style consistency, but also reduces the design cost of small and medium-sized enterprises in industry and improves efficiency, and promotes the integration of personalized consumption mode and smart home aesthetic design in society.
References
[1] Gangloff, H., & Jouvin, N. (2024). Jinns: a JAX library for physics-informed neural networks. arXiv preprint arXiv:2412.14132.
[2] Hutson, J., & Schnellmann, A. (2023). The poetry of prompts: the collaborative role of generative artificial intelligence in the creation of poetry and the anxiety of machine influence. Global journal of computer science and technology: D, 23(1).
[3] Murzyn-Kupisz, M. (2026). Geographies of (sustainable) fashion: research topics, issues, and discourses. In Changing Geographies of Fashion in the European Semi-Periphery: Transition Towards Sustainability? (pp. 1-105). Cham: Springer Nature Switzerland.
[4] Wang, J., Chang, Y., Cao, S., Dong, Y., Li, S., Jia, L., & Li, W. (2025). Explanatory framework of typhoon extreme wind speed predictions integrating the effects of climate changes. Climate Dynamics, 63(3), 142.
[5] Brenner, D. M., Chaudhary, Y., Geraci, R. M., Graves, M., Griese, H., Kruger, E., ... & Schwarting, M. (2024). Technical and religious perspectives on AI misinformation and disinformation. Available at SSRN 4360413.
[6] Ghorbani, A., Ghorbani, V., Nazari-Heris, M., & Asadi, S. (2023). Data assimilation for agent-based models. Mathematics, 11(20), 4296.
[7] Hao, Z. (2026). Dynamic Task Prioritization for Edge AI in Smart Cities: Balancing Latency and Energy Efficiency. Journal of Intelligence and Engineering Technology, 1(1), 60-69.
[8] Lin, A. (2026). Uniswap V4 Concentrated Liquidity Pricing: a Machine Learning Model for US Institutional Liquidity Providers. Journal of Intelligence and Engineering Technology, 1(1), 19-26.
[9] Wu, Y. (2025). Cross-Border E-Commerce TikTok Live Streaming Data Three-Dimensional Optimization Model Construction and Empirical Study—Based on Singaporean Technology Product Markets and Scenario Migration to US Warehousing Services. Journal of World Economy, 4(6), 44-50.
[10] Wang, C. (2025). Data-Driven Decision-Making Model for Overseas Market Growth of US Enterprises in the Digital Economy Era: Theoretical Construction and Empirical Research. Journal of World Economy, 4(6), 58-65.
[11] Wang, H., Li, Q., & Liu, Y. (2022). Regularized Buckley–James method for right‐censored outcomes with block‐missing multimodal covariates. Stat, 11(1), e515.
[12] Wang, C. (2026). A Study on Data-Driven Budget Optimization for US Enterprises’ Cross-Border Marketing. Frontiers in Management Science, 5(1), 41-46.
[13] Wu, Y. (2025). The Impact of “Data-Driven Hierarchical Operation” on ARPU Value for Cross-Border E-Commerce Warehousing Clients. Journal of Progress in Engineering and Physical Science, 4(6), 15-21.
[14] Calefato, P. (2021). Fashion as cultural translation: Signs, images, narratives. Anthem Press.
[15] Wang, H., Li, Q., & Liu, Y. (2023). Adaptive supervised learning on data streams in reproducing kernel Hilbert spaces with data sparsity constraint. Stat, 12(1), e514.
[16] Lin, A. (2026). Multi-Chain DAO Treasury Management: a Risk and Compliance Optimization Framework for the US Ecosystem. Journal of Intelligence and Engineering Technology, 1(1), 11-18.
[17] Wang, H., Sun, W., & Liu, Y. (2022). Prioritizing autism risk genes using personalized graphical models estimated from single-cell rna-seq data. Journal of the American Statistical Association, 117(537), 38-51.
[18] Hao, Z. (2025). Fault-Tolerant Real-Time Scheduling for Edge AI in US Critical Infrastructure. Engineering Frontiers, 1(4).
[19] Wang, P., Wang, H., Li, Q., Shen, D., & Liu, Y. (2024). Joint and individual component regression. Journal of Computational and Graphical Statistics, 33(3), 763-773.
[20] Hao, Z. (2026). Energy Efficient Multi Core Task Scheduling for Real Time Edge AI Systems: A Latency Aware Approach. International Journal of Advance in Applied Science Research, 5(3), 1-14.
[21] Li, K., Chen, X., Song, T., Zhang, H., Zhang, W., & Shan, Q. (2025, January). Gptdrawer: Enhancing visual synthesis through chatgpt. In 2025 5th International Conference on Neural Networks, Information and Communication Engineering (NNICE) (pp. 368-372). IEEE.
[22] Luo, M., Zhang, W., Song, T., Li, K., Zhu, H., Du, B., & Wen, H. (2021, January). Rebalancing expanding EV sharing systems with deep reinforcement learning. In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence (pp. 1338-1344).
[23] Hao, Z. (2026). Structure-Aware Deep Reinforcement Learning for Latency-Minimal Scheduling of Edge AI Inference on Heterogeneous Cores. Journal of Intelligence and Engineering Technology, 1(1), 50-59.
[24] Wang, J., Tim, K. T., Li, S., Chan, T. K., & Fung, J. C. (2023). A systematic comparison of the wind profile codifications in the Western Pacific Region. Wind & structures, 37(2), 105-115.
[25] Stephanidis, C., Antona, M., Ntoa, S., & Salvendy, G. (Eds.). (2025). HCI International 2025 Posters: 27th International Conference on Human-Computer Interaction, HCII 2025, Gothenburg, Sweden, June 22–27, 2025, Proceedings, Part VIII. Springer Nature.
Downloads
Published
How to Cite
Issue
Section
ARK
License
Copyright (c) 2026 The author retains copyright and grants the journal the right of first publication.
This work is licensed under a Creative Commons Attribution 4.0 International License.
