Artificial intelligence generation technology has brought new opportunities to the field of fashion design. Attribute knowledge has a significant impact on the overall effect of fashion design. Contemporary generative methods of fashion design frequently yield results lacking semantic information or missing specific attributes. To address the problem, this study aims for an intelligent generative method of fashion design through constructing prompt templates and a specific attribute low-rank adaption (LoRA) to combine fashion attribute knowledge into the generative process of the Stable Diffusion Model. First, a fashion attribute knowledge graph is constructed to establish prompt templates, and natural language descriptions are transformed into professional and complete prompt through GPT-4. Second, the fashion dataset is annotated with templates to filter specific attributes for LoRA training, followed by controlling fashion attributes in generation. Furthermore, analyses of the generation of women’s jacket designs show that the proposed method consistently improves the accuracy and stability of attributes in fashion design generation.
ArarMVoynovAHertzA, et al. PALP: Prompt aligned personalization of text-to-image models. 2024. DOI: 10.48550/arXiv.2401.06105.
2.
WangW.Research on intelligent design of clothing appearance based on deep learning. Master’s Thesis, Zhejiang University, China, 2022.
3.
HuY.Analysis of clothing structure and management in clothing design oriented to market demand via recommendation algorithm. Electron Commerce Res2023. doi:10.1007/s10660-023-09776-4
4.
LiuLZhangHZhouD, et al.
Toward fashion intelligence in the big data era: state-of-the-art and future prospects. IEEE Trans Consum Electron2023;
70. doi:10.1109/TCE.2023.3285880.
5.
PingQWuBDingW, et al. Fashion-AttGAN: Attribute-aware fashion editing with multi-objective gan. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, 2019, pp. 323–325.
6.
KimJLeeJKLeeKM. Deeply-recursive convolutional network for image super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2016, pp. 1637–1645.
7.
RombachRBlattmannALorenzD, et al. High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2022, pp. 10684–10695.
8.
ChoiYKwakSLeeK, et al. Improving diffusion models for virtual try-on. DOI: 10.48550/arXiv.2403.05139.
9.
XuYGuTChenW, et al.
Ootdiffusion: Outfitting fusion based latent diffusion for controllable virtual try-on. Computer Vision and Pattern Recognition (cs.CV)2024. doi:10.48550/arXiv.2403.01779.
10.
BaldratiAMorelliDCartellaG, et al. Multimodal garment designer: Human-centric latent diffusion models for fashion image editing. In: Computer Vision and Pattern Recognition. IEEE, 2023, pp. 23393–23402.
11.
ZhangXYangBKampffmeyerMC, et al. Diffcloth: Diffusion based garment synthesis and manipulation via structural cross-modal semantic alignment. IEEE International Conference on Computer Vision, 2023, pp. 23154–23163.
12.
HuangLChenDLiuY, et al. Composer: Creative and controllable image synthesis with composable conditions. 2023. doi:10.48550/arXiv.2302.09778.
13.
YangLYuZMengC, et al.
Mastering text-to-image diffusion: Recaptioning, planning, and generating with multimodal llms. CVPR’19, 2024. doi:10.48550/arXiv.1904.01538
14.
WangMLiuYZhangX, et al. LangGPT: Rethinking structured reusable prompt design framework for LLMs from the programming language. 2024. doi:arXiv:2402.16929, 2024.
15.
WangW-ZXiaoH-MFangY. Clothing image attribute editing based on generative adversarial network, with reference to an upper garment. Emerald Publishing Limited, 2024. doi:10.1108/ijcst-09-2023-0129.
16.
WangCCWangYYuenMM.Design automation for customized apparel products. Computer-aided Des2005;
37: 675–691.
17.
VolinoPCordierFMagnenat-ThalmannN.From early virtual garment simulation to interactive fashion design. Computer-aided Des2005;
37: 593–608.
18.
LiuKZengXBruniauxP, et al.
Fit evaluation of virtual garment try-on by learning from digital pressure data. Knowledge-Based Syst2017;
133: 174–182.
19.
AuCKMaY-S.Garment pattern definition, development and application with associative feature approach. Comput Ind2010;
61: 524–531.
20.
LuJ-MWangM-JJChenC-W, et al.
The development of an intelligent system for customized clothing making. Expert Syst Applicat2010;
37: 799–803.
21.
CuiX.An adaptive recommendation algorithm of intelligent clothing design elements based on large database. Mobile Inform Syst2022. doi:10.1155/2022/3334047.
22.
YangB.Clothing design style recommendation using decision tree algorithm combined with deep learning. Computat Intell Neurosci2022. doi:10.1155/2022/5745457.
23.
Abd Alaziz, HadeerMElmannaiHSalehH, et al.
Enhancing fashion classification with vision transformer (ViT) and developing recommendation fashion systems using DINOVA2. Electronics2023;
12: 4263. doi:10.3390/12204263.
24.
ShimizuRNakamuraTGotoM.Partial visual-semantic embedding: Fine-grained outfit image representation with massive volumes of tags via angular-based contrastive learning. Knowledge-Based Syst2023;
277: 110791. doi:10.1016/j.knosys.2023.110791.
25.
AnantrasirichaiNBullD.Artificial intelligence in the creative industries: a review. Artif Intell Rev2022;
55: 589–656.
26.
ZhuXLiXChenY, et al.
Interactive genetic algorithm based on typical style for clothing customization. J Eng Fibers Fabrics2020;
15: 1558925020920035.
27.
GoodfellowIPouget-AbadieJMirzaM, et al.
Generative adversarial networks. Commun ACM2020;
63: 139–144.
28.
WuQZhuBYongB, et al.
ClothGAN: Generation of fashionable Dunhuang clothes using generative adversarial networks. Connection Sci2021;
33: 341–358.
DhariwalPNicholA.Diffusion models beat GANs on image synthesis. Adv Neural Inform Process Syst2021;
34: 8780–8794.
33.
YangLZhangZSongY, et al.
Diffusion models: A comprehensive survey of methods and applications. ACM Comput Surv2023:
56: 1–39. doi:10.1145/3626235.
34.
YangLZhangZSongY, et al.
Diffusion models: A comprehensive survey of methods and applications. ACM Comput Surv2023;
56: 1–39.
35.
RuizNLiYJampaniV, et al. Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In: Computer Vision and Pattern Recognition (cs.CV). IEEE, 2023, pp. 22500–22510.
36.
HuEJShenYWallisP, et al. Lora: Low-rank adaptation of large language models. 2021. doi:10.48550/arXiv.2106.09685.
37.
CaoTWangCLiuB, et al. Beautifulprompt: Towards automatic prompt engineering for text-to-image synthesis. 2023. doi:10.48550/arXiv.2311.06752.
38.
RosenmanSLalVHowardP. NeuroPrompts: An adaptive framework to optimize prompts for text-to-image generation. 2023. doi:10.48550/arXiv.2311.12229.
39.
LeeKLiuHRyuM, et al. Aligning text-to-image models using human feedback. 2023. doi:10.48550/arXiv.2302.12192.
40.
DaikiMiyakeAkihiroIoharaYuSaito, andToshiyukiTanaka. Negative-prompt inversion: Fast image inversion for editing with textguided diffusion models. arXiv preprint arXiv:2305.16807, 2023. doi:10.48550/arXiv.2302.12192.
41.
BrownTMannBRyderN, et al.
Language models are few-shot learners. Adv Neural Inform Process Syst2020;
33: 1877–1901.
42.
ZhaoBJinWZhangY, et al.
Prompt learning for metonymy resolution: Enhancing performance with internal prior knowledge of pre-trained language models. Knowledge-Based Syst2023;
279: 110928.
43.
LiuZLuoPQiuS, et al. Deepfashion: Powering robust clothes recognition and retrieval with rich annotations. In: Computer Vision & Pattern Recognition. IEEE, 2016, pp. 1096–1104.
44.
ZouXKongXWongW, et al. Fashionai: A hierarchical dataset for fashion understanding. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, 2019.
45.
AnHLeeKYChoiY, et al.
Conceptual framework of hybrid style in fashion image datasets for machine learning. Fashion Text2023;
10: 18.
46.
BonattiPADeckerSPolleresA, et al. Knowledge graphs: new directions for knowledge representation on the semantic web (Dagstuhl seminar 18371). In: Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik. 2019, pp. 29–111.
47.
ZhaoYFengXZhuM, et al. Personalized clothing recommendation method based on knowledge graph. In: IEEE. 2023, pp. 230–237.
48.
ZhangTZhangYVineetV, et al. Controllable text-to-image generation with GPT-4. 2023. doi: 10.48550/arXiv.2305.18583.
49.
YangZLiLLinK, et al. The dawn of lMMs: preliminary explorations with GPT-4v (vision), 2023. DOI: 10.48550/arXiv.2309.17421.
ZhangLRaoAAgrawalaM. Adding conditional control to text-to-image diffusion models. In: Computer Vision and Pattern Recognition (cs.CV). IEEE, 2023, pp. 3836–3847.
54.
WangTYangXXuK, et al.
Spatial attentive single-image deraining with a high quality real rain dataset. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019. doi:10.48550/arXiv.1904.01538
55.
XuQHuangGYuanY, et al. An empirical study on evaluation metrics of generative adversarial networks. 2018. doi:10.48550/arXiv.1806.07755
56.
ZhangRIsolaPEfrosAA, et al. The unreasonable effectiveness of deep features as a perceptual metric. 2018. doi:10.1109/CVPR.2018.00068.
57.
MittalASoundararajanRBovikAC.Making a “completely blind” image quality analyzer. IEEE Signal Process Lett201220(3): 209–212.
58.
MittalAMoorthyAKBovikAC.No-reference image quality assessment in the spatial domain. IEEE Trans Image Process2012;
21(12): 4695–4708.
59.
CaoSChaiWHaoS, et al.
Difffashion: Reference-based fashion design with structure-aware transfer by diffusion models. IEEE, 2023. doi:10.1109/tmm.2023.3318297.
60.
WangSChenLJiangJ, et al. LoRA meets dropout under a unified framework. 2024. doi:10.48550/arXiv.2403.00812
61.
DattaSKuARamachandranD, et al. Prompt expansion for adaptive text-to-image generation. 2023. doi:10.48550/arXiv.2312.16720.
62.
YangLZhangZSongY, et al.
Diffusion models: A comprehensive survey of methods and applications. ACM Comput Surv2023. doi:10.1145/3626235
63.
IslamKZaheerMZMahmoodA, et al.
DiffuseMix: Label-preserving data augmentation with diffusion models. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024.
64.
GongQLiX.Research progress on knowledge graph in the field of clothingJ Silk; 2023.
65.
ArgyrouGDimitriouALymperaiouM, et al. Automatic Generation of Fashion Images using Prompting in Generative Machine Learning Models. 2024. doi:10.48550/arXiv.2407.14944.
