Generative AI technology’s fast expansion is driving increasing application in visual creation. This work presents an artificial intelligence generative visual creativity system (KRGVS) with knowledge retrieval to automate user intent understanding and high-quality visual content creation. Its key uniqueness is the ability of the KRGVS system to extract deeper purpose from confused user inputs, call suitable knowledge resources, and produce innovative and valuable visual creations based on a semantically enriched generative model. Experimental results imply that the KRGVS system can use cross-modally knowledge to improve visual content creativity, logic, and explanatory power, generation quality, and user customisation. This paper provides a new data-driven and intelligent aid direction for the creative industry and supports the change of AI from a content generating tool to a human-machine collaborative creativity partner.
El ArdeliyaVTaylorJWolfsonJ. Exploration of artificial intelligence in creative fields: generative art, music, and design. International Journal of Cyber and IT Service Management2024; 4: 40–46.
2.
TakaleDGMahallePNSuleB. Advancements and applications of generative artificial intelligence. J Inf Technol Sci2024; 10: 20–27.
3.
LampropoulosGKeramopoulosEDiamantarasK. Enhancing the functionality of augmented reality using deep learning, semantic web and knowledge graphs: a review. Vis Inform2020; 4: 32–42.
4.
ZhangLLiuSLiuD, et al.Rich visual knowledge-based augmentation network for visual question answering. IEEE Trans Neural Netw Learn Syst2020; 32: 4362–4373.
5.
AlawadMAHamdanMQHamdiKA. Innovative variational autoencoder for an end-to-end communication system. IEEE Access2022; 11: 86834–86847.
6.
ChenFZhangCNingB. CRKG: combining retrieval knowledge with generative language models. J Supercomput2025; 81: 1–24.
7.
ChenLZhangYHanJ, et al.A foundation model enhanced approach for generative design in combinational creativity. J Eng Des2024; 35: 1394–1420.
8.
MehmoodRBashirRGiriK. Deep generative models: a review. Indian J Sci Technol2023; 16: 460–467.
9.
BansalGNawalAChamolaV, et al.Revolutionizing visuals: the role of generative AI in modern image generation. ACM Trans Multimedia Comput Commun Appl2024; 20: 1–22.
10.
AlqahtaniHKavakli-ThorneMKumarG. Applications of generative adversarial networks (gans): an updated review. Arch Comput Methods Eng2021; 28: 525–552.
11.
WangLChenWYangW, et al.A state-of-the-art review on image synthesis with generative adversarial networks. IEEE Access2020; 8: 63514–63537.
12.
PengJLiYLiaoZ, et al.Seismic data strong noise attenuation based on diffusion model and principal component analysis. IEEE Trans Geosci Remote Sens2024; 62: 1–11.
13.
LewAJBuehlerMJ. Single-shot forward and inverse hierarchical architected materials design for nonlinear mechanical properties using an attention-diffusion model. Mater Today2023; 64: 10–20.
14.
ChenJHuangYLvT, et al.Textdiffuser: diffusion models as text painters. Adv Neural Inf Process Syst2023; 36: 9353–9387.
15.
GezawaASZhangYWangQ, et al.A review on deep learning approaches for 3D data representations in retrieval and classifications. IEEE Access2020; 8: 57566–57593.
16.
PanXYeTHanD, et al.Contrastive language-image pre-training with knowledge graphs. Adv Neural Inf Process Syst2022; 35: 22895–22910.
17.
ZhangYHeZLiJ, et al.MapGPT: an autonomous framework for mapping by integrating large language model and cartographic tools. Cartogr Geogr Inf Sci2024; 51: 717–743.
18.
FangLLuoYFengK, et al.A knowledge-enriched ensemble method for word embedding and multi-sense embedding. IEEE Trans Knowl Data Eng2022; 35: 5534–5549.
19.
BaltrušaitisTAhujaCMorencyL-P. Multimodal machine learning: a survey and taxonomy. IEEE Trans Pattern Anal Mach Intell2018; 41: 423–443.
20.
CroitoruF-AHondruVIonescuRT, et al.Diffusion models in vision: a survey. IEEE Trans Pattern Anal Mach Intell2023; 45: 10850–10869.
21.
ZhanFYuYWuR, et al.Multimodal image synthesis and editing: the generative AI era. IEEE Trans Pattern Anal Mach Intell2023; 45: 15098–15119.
22.
HuJZhuYWuL, et al.Text semantic matching algorithm based on the introduction of external knowledge under contrastive learning. Int J Mach Learn Cybern2025; 16: 741–753.
23.
ChenZXuTWuX-J, et al.Hybrid Riemannian graph-embedding metric learning for image set classification. IEEE Trans Big Data2021; 9: 75–92.
24.
LiJSiGTianP, et al.Overview of indoor scene recognition and representation methods based on multimodal knowledge graphs. Appl Intell2024; 54: 899–923.
25.
ZhaoGWangWWangX, et al.Incremental recognition of multi-style Tibetan character based on transfer learning. IEEE Access2024; 12: 44190–44206.
XuNZhangHLiuA-A, et al.Multi-level policy and reward-based deep reinforcement learning framework for image captioning. IEEE Trans Multimedia2019; 22: 1372–1383.
28.
KrzeminskaA. Self-optimisation and the technologically mediated self. Historical Social Research/Historische Sozialforschung2024; 49: 77–101.
29.
ScottGJHaganKCMarcumRA, et al.Enhanced fusion of deep neural networks for classification of benchmark high-resolution image data sets. IEEE Geosci Remote Sens Lett2018; 15: 1451–1455.
30.
ElpeltagyMSallamH. Automatic prediction of COVID− 19 from chest images using modified ResNet50. Multimed Tools Appl2021; 80: 26451–26463.
31.
IglesiasGTalaveraEGonzález-PrietoÁ, et al.Data augmentation techniques in time series domain: a survey and taxonomy. Neural Comput Appl2023; 35: 10123–10145.
32.
LeivadeasAFalknerM. A survey on intent-based networking. IEEE Commun Surv Tutorials2022; 25: 625–655.
