Intelligent interaction system for art image creation: challenges, methodologies, and future prospects

Abstract

Graphic visual art is undergoing a profound transformation driven by generative artificial intelligence (AI). This transformation extends beyond technological innovation, reshaping the paradigms of artistic image creation. This paper examines human-centered interactive systems for artistic image creation, aiming to bridge the gap between technology-oriented and art-oriented research. We identify three core challenges in interactive generative art creation: controllability, integrity, and creativity, and analyze in depth the underlying trade-offs among them. Building on this analysis, we systematically review the evolution of generative models, approaches to integrating artistic knowledge, and the emergence of collaborative agentic AI systems. Looking ahead, we emphasize the need to develop human-AI collaborative frameworks that offer greater controllability, preserve human creative agency, and ensure regulatory compliance, while exploring a wide range of potential applications. This study proposes a unified analytical framework that connects AI technologies, human-AI interaction processes, and the integration and innovation of artistic image creation. It further outlines a task-oriented roadmap to guide future research and the development of collaborative systems for artistic image creation.

Keywords

Cross-media intelligence / Human-AI collaboration / Visual art creation / Interactive systems / Controllability / Integrity / Creativity

References

[1] Achlioptas P , Ovsjanikov M , Haydarov K , et al., 2021. ArtEmis: affective language for visual art. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.11564- 11574.

[2] Adamkiewicz K , Woźniak PW , Dominiak J , et al., 2025. PromptMap: an alternative interaction style for AI-based image generation. Proc 30^th Int Conf on Intelligent User Interfaces, p.1162- 1176.

[3] Agudo U , Arrese M , Liberal KG , et al., 2022. Assessing emotion and sensitivity of AI artwork. Front Psychol, 13: 879088.

[4] AlDahoul N , Rahwan T , Zaki Y , 2025. AI-generated faces influence gender stereotypes and racial homogenization. Sci Rep, 15 (1): 14449.

[5] Amabile TM , 1982. Social psychology of creativity:a consensual assessment technique. J Pers Soc Psychol, 43 (5): 997- 1013.

[6] Ambartsumian Y , Cannon MT , et al., 2025. Why the obsession with human creativity? A comparative analysis on copyright registration of AI-generated works. Harvard Int Law J

[7] Avakri A , Avakri I , 2025. Analysis of the creative mode of intelligent image generation art. Proc Int Conf on Artificial Intelligence, Digital Media Technology and Interaction Design, p.246- 250.

[8] Avrahami O , Lischinski D , Fried O , 2022. Blended diffusion for text-driven editing of natural images. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.18187- 18197.

[9] Bahng H , Yoo S , Cho W , et al., 2018. Coloring with words:guiding image colorization through text-based palette generation. Proc 15^th European Conf on Computer Vision, p.443- 459.

[10] Bau D , Zhu JY , Strobelt H , et al., 2019. GAN dissection: visualizing and understanding generative adversarial networks. Proc 7^th Int Conf on Learning Representations.

[11] Bayramli Z , Suleymanzade A , An NM , et al., 2025. Diffusion models through a global lens: are they culturally inclusive? Proc 63^rd Annual Meeting of the Association for Computational Linguistics, p.31137- 31155.

[12] Blattmann A , Rombach R , Ling H , et al., 2023. Align your latents:high-resolution video synthesis with latent diffusion models. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.22563- 22575.

[13] Boden MA , 2004. The Creative Mind:Myths and Mechanisms.2^nd Edition.Routledge, London, UK.

[14] Brooks T , Holynski A , Efros AA , 2023. InstructPix2Pix:learning to follow image editing instructions. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.18392- 18402.

[15] Buolamwini J , Gebru T , 2018. Gender shades: intersectional accuracy disparities in commercial gender classification. Proc Conf on Fairness, Accountability and Transparency, p.77- 91.

[16] Cai A , Rick SR , Heyman JL , et al., 2023. DesignAID:using generative AI and semantic diversity for design inspiration. Proc ACM Collective Intelligence Conf, p.1- 11.

[17] Canny J , 1986. A computational approach to edge detection. IEEE Trans Patt Anal Mach Intell, PAMI-8 (6): p.679- 698.

[18] Cao HQ , Tan C , Gao ZY , et al., 2024. A survey on generative diffusion models. IEEE Trans Knowl Data Eng, 36 (7): 2814- 2830.

[19] Carlini N , Hayes J , Nasr M , et al., 2023. Extracting training data from diffusion models. Proc 32^nd USENIX Conf on Security Symp, Article 294.

[20] Chamberlain R , Mullin C , Scheerlinck B , et al., 2018. Putting the art in artificial:aesthetic responses to computer-generated art. Psychol Aesthet Crea Arts, 12 (2): 177- 192.

[21] Chang HW , Zhang H , Jiang L , et al., 2022. MaskGIT:masked generative image transformer. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.11305- 11315.

[22] Chen C , Liu DC , Xu C , 2024. Towards memorization-free diffusion models. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.8425- 8434.

[23] Chen LC , Zhu YK , Papandreou G , et al., 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation. Proc 15^th European Conf on Computer Vision, p.833- 851.

[24] Cheng JH , Yin BQ , Cai KX , et al., 2024. TheaterGen: character management with LLM for consistent multi-turn image generation.https://arxiv.org/abs/2404.18919

[25] Chung JJY , Adar E , 2023. PromptPaint: steering text-to-image generation through paint medium-like interactions. Proc 36^th Annual ACM Symp on User Interface Software and Technology, Article 6.

[26] Coalition for Content Provenance and Authenticity , 2024. C2PA Specifications.https://spec.c2pa.org/[Accessed on Aug.4, 2026].

[27] Coalition for Content Provenance and Authenticity , 2026a. Content Credentials: C2PA Technical Specification.https://spec.c2pa.org/specifications/specifications/2.4/specs/C2PA_Specification.html[Accessed on Aug.4, 2026].

[28] Coalition for Content Provenance and Authenticity , 2026b. Guiding Principles for C2PA Designs and Specifications.https://c2pa.org/principles/[Accessed on Aug.4, 2026].

[29] Costa V , Alonso-Moral JM , Falomir Z , et al., 2023. An art painting style explainable classifier grounded on logical and commonsense reasoning. Soft Comput.

[30] Cui P , Lü Z , Zhang YS , 2025. Construction and design application of plant pattern cultural genealogy in Changsha kiln. Furnit Interior Des, 32 (10): p.64- 71 (in Chinese).

[31] Cyberspace Administration of China , 2025. Measures for Labelling Artificial-Intelligence-Generated and Synthetic Content (in Chinese).https://www.cac.gov.cn/2025-03/14/c_1743654684782215.htm[Accessed on Aug.4, 2026].

[32] Dalal N , Triggs B , 2005. Histograms of oriented gradients for human detection. Proc IEEE Computer Society Conf on Computer Vision and Pattern Recognition, p.886- 893.

[33] Darda KM , Chatterjee A , 2023. The impact of contextual information on aesthetic engagement of artworks. Sci Rep, 13 (1): 4273.

[34] Demmer TR , Kühnapfel C , Fingerhut J , 2023. Does an emotional connection to art really require a human artist? Emotion and intentionality responses to AI- versus human-created art and impact on aesthetic experience. Comput Hum Behav, 148: p.107875.

[35] Desai DR , Riedl M , 2024. Between copyright and computer science: the law and ethics of generative AI.https://arxiv.org/abs/2403.14653

[36] Dhariwal P , Nichol A , 2021. Diffusion models beat GANs on image synthesis. Proc 35^th Int Conf on Neural Information Processing Systems, Article 672.

[37] D'Incà M , Peruzzo E , Mancini M , et al., 2024. OpenBias: open-set bias detection in text-to-image generative models.https://arxiv.org/abs/2404.07990

[38] Ding X , Wang YW , Zhang K , et al., 2026. CCDM:continuous conditional diffusion models for image generation. IEEE Trans Multimedia, 28: 4360- 4372.

[39] Esser P , Rombach R , Ommer B , 2021. Taming transformers for high-resolution image synthesis. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.12868- 12878.

[40] European Commission , 2025. Explanatory Notice and Template for the Public Summary of Training Content for General-Purpose AI Models.https://digital-strategy.ec.europa.eu/en/library/explanatory-notice-and-template-public-summary-training-content-general-purpose-ai-models [Accessed on Aug.4, 2026].

[41] European Union , 2024. Regulation (EU) 2024/1689 Laying Down Harmonised Rules on Artificial Intelligence.https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX:?32024R1689 [Accessed on Aug.4, 2026].

[42] Frich J , MacDonald Vermeulen L , Remy C , et al., 2019. Mapping the landscape of creativity support tools in HCI. Proc CHI Conf on Human Factors in Computing Systems, Article 389.

[43] Garcia N , Renoust B , Nakashima Y , 2019. Context-aware embeddings for automatic art analysis. Proc ACM Int Conf on Multimedia Retrieval, p.25- 33.

[44] Goodfellow IJ , Pouget-Abadie J , Mirza M , et al., 2014. Generative adversarial nets. Proc 28^th Int Conf on Neural Information Processing Systems, p.2672- 2680.

[45] Gu A , Dao T , 2024. Mamba: linear-time sequence modeling with selective state spaces. Proc 1^st Conf on Language Modeling.

[46] Han SJ , Fussell SR , 2025. Understanding user perceptions and the role of AI image generators in image creation workflows. Proc CHI Conf on Human Factors in Computing Systems, Article 547.

[47] Härkönen E , Hertzmann A , Lehtinen J , et al., 2020. GANSpace: discovering interpretable GAN controls. Proc 34^th Int Conf on Neural Information Processing Systems, Article 825.

[48] He BX , Guo Y , Zhu YB , et al., 2024. From signal to knowledge:the diagnostic value of raw data in the artificial intelligence prediction of human data for the first time. Engineering, 34: 60- 69.

[49] Hertz A , Mokady R , Tenenbaum J , et al., 2022. Prompt-to-prompt image editing with cross attention control.https://arxiv.org/abs/2208.01626

[50] Hessel J , Holtzman A , Forbes M , et al., 2021. CLIPScore:a reference-free evaluation metric for image captioning. Proc Conf on Empirical Methods in Natural Language Processing, p.7514- 7528.

[51] Heusel M , Ramsauer H , Unterthiner T , et al., 2017. GANs trained by a two time-scale update rule converge to a local Nash equilibrium. Proc 31^st Int Conf on Neural Information Processing Systems, p.6629- 6640.

[52] Higgins I , Matthey L , Pal A , et al., 2017. β-VAE: learning basic visual concepts with a constrained variational framework. Proc 5^th Int Conf on Learning Representations.

[53] Ho J , Salimans T , 2022. Classifier-free diffusion guidance.https://arxiv.org/abs/2207.12598

[54] Ho J , Jain A , Abbeel P , 2020. Denoising diffusion probabilistic models. Proc 34^th Int Conf on Neural Information Processing Systems, Article 574.

[55] Hu MH , Zheng JB , Liu DQ , et al., 2023. Cocktail: mixing multi-modality controls for text-conditional image generation.https://arxiv.org/abs/2306.00964

[56] Huang LH , Chen D , Liu Y , et al., 2023. Composer: creative and controllable image synthesis with composable conditions. Proc 40^th Int Conf on Machine Learning, p.13753- 13773.

[57] Huang YK , Ning Z , Cheng M , 2025. LACE: exploring turn-taking and parallel interaction modes in human-AI co-creation for iterative image generation.https://arxiv.org/abs/2504.14827

[58] Isola P , Zhu JY , Zhou TH , et al., 2017. Image-to-image translation with conditional adversarial networks. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.5967- 5976.

[59] Jeong S , Choi I , Yun Y , et al., 2025. Culture-TRIP:culturally-aware text-to-image generation with iterative prompt refinement. Proc Conf of the Nations of the Americas Chapter of the Association for Computational Linguistics:Human Language Technologies, p.9543- 9573.

[60] Jing PG , Liu XY , Wang J , 2023. StyleEDL:style-guided high-order attention network for image emotion distribution learning. Proc 31^st ACM Int Conf on Multimedia, p.853- 861.

[61] Ju X , Zeng AL , Zhao CC , et al., 2023. HumanSD:a native skeleton-guided diffusion model for human image generation. Proc IEEE/CVF Int Conf on Computer Vision, p.15942- 15952.

[62] Ju X , Liu X , Wang XT , et al., 2024. BrushNet:a plug-and-play image inpainting model with decomposed dual-branch diffusion. Proc 18^th European Conf on Computer Vision, p.150- 168.

[63] Jucker JL , Barrett JL , Wlodarski R , 2014. "I just don't get it":perceived artists' intentions affect art evaluations. Empir Stud Arts, 32 (2): 149- 182.

[64] Karras T , Laine S , Aila T , 2019. A style-based generator architecture for generative adversarial networks. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.4396- 4405.

[65] Karras T , Laine S , Aittala M , et al., 2020. Analyzing and improving the image quality of StyleGAN. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.8107- 8116.

[66] Kirstain Y , Polyak A , Singer U , et al., 2023. Pick-a-Pic: an open dataset of user preferences for text-to-image generation. Proc 37^th Int Conf on Neural Information Processing Systems, Article 1594.

[67] Klassert T , Ulges A , Fu BY , 2026. BAFIS:dataset + framework to assess occupational bias and human preference in modern text-to-image models. Proc IEEE/CVF Winter Conf on Applications of Computer Vision, p.2168- 2177.

[68] Lan XY , An JX , Guo YS , et al., 2025. Imagining the Far East: exploring perceived biases in AI-generated images of East Asian women. Proc CHI Conf on Human Factors in Computing Systems, Article 332.

[69] Leder H , Belke B , Oeberst A , et al., 2004. A model of aesthetic appreciation and aesthetic judgments. Brit J Psychol, 95 (4): 489- 508.

[70] Li YH , Liu HT , Wu QY , et al., 2023. GLIGEN:open-set grounded text-to-image generation. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.22511- 22521.

[71] Li YT , Gan Z , Shen YL , et al., 2019. StoryGAN:a sequential conditional GAN for story visualization. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.6322- 6331.

[72] Li ZJ , Zhang Y , Zhou SZ , et al., 2025. RealtimeGen:an intervenable AI image generation system for commercial digital art asset creators. Int J Hum-Comput Interact, 41 (11): 6613- 6636.

[73] Liu QQ , Yan YP , Jin YC , et al., 2024. Secure federated evolutionary optimization-a survey. Engineering, 34: 23- 42.

[74] Long J , Shelhamer E , Darrell T , 2015. Fully convolutional networks for semantic segmentation. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.3431- 3440.

[75] Lv KT , Chen HB , Yuan YJ , et al., 2025. How to inject knowledge efficiently? Knowledge infusion scaling law for pre-training large language models. Proc Conf on Empirical Methods in Natural Language Processing, p.26193- 26208.

[76] Ma Z , Li QM , Zhang XH , et al., 2025. An inversion-based measure of memorization for diffusion models. Proc IEEE/CVF Int Conf on Computer Vision, p.16959- 16969.

[77] Machajdik J , Hanbury A , 2010. Affective image classification using features inspired by psychology and art theory. Proc 18^th ACM Int Conf on Multimedia, p.83- 92.

[78] Maher ML , Grace K , Karimi P , et al., 2018. Evaluating creativity in computational co-creative systems. Proc 9^th Int Conf on Computational Creativity, p.104- 111.

[79] Man F , Chen X , Wang H , et al., 2025. K-EVER2: knowledge-enhanced visual emotion reasoning and retrieval. Proc 33^rd ACM Int Conf on Multimedia.

[80] Matsumoto H , Nakamura A , Hamaguchi K , et al., 2025. From sketch to refinement:interactive drawing support with generative AI. Proc 14^th Global Conf on Consumer Electronics, p.32- 36.

[81] Millet K , Buehler F , Du GZ , et al., 2023. Defending humankind:anthropocentric bias in the appreciation of AI art. Comput Hum Behav, 143: 107707.

[82] Mokady R , Hertz A , Aberman K , et al., 2023. Null-text inversion for editing real images using guided diffusion models. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.6038- 6047.

[83] Mou C , Wang XT , Xie LB , et al., 2024. T2I-Adapter:learning adapters to dig out more controllable ability for text-to-image diffusion models. Proc 38^th AAAI Conf on Artificial Intelligence, p.4296- 4304.

[84] Nayak S , Bhatia M , Zhang XF , et al., 2025. CulturalFrames: assessing cultural expectation alignment in text-to-image models and evaluation metrics. Proc Association for Computational Linguistics, p.20918- 20953.

[85] Nazeri K , Ng E , Joseph T , et al., 2019. EdgeConnect: generative image inpainting with adversarial edge learning.https://arxiv.org/abs/1901.00212

[86] O'Donovan P , Agarwala A , Hertzmann A , 2011. Color compatibility from large datasets. ACM Trans Graph, 30 (4): 43.

[87] Ojala T , Pietikainen M , Mäenpää T , 2002. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Patt Anal Mach Intell, 24 (7): p.971- 987.

[88] Oppenlaender J , Johnston H , Silvennoinen JM , et al., 2025. Artworks reimagined:exploring human-AI co-creation through body prompting. Proc ACM Hum-Comput Interact, 9 (4): EICS012.

[89] O'Quin K , Besemer SP , 1989. The development, reliability, and validity of the revised creative product semantic scale. Creativ Res J, 2 (4): 267- 278.

[90] Pan XG , Tewari A , Leimkühler T , et al., 2023. Drag your GAN: interactive point-based manipulation on the generative image manifold. Proc ACM SIGGRAPH Conf, Article 78.

[91] Pan YH , 2019. On visual knowledge. Front Inform Technol Electron Eng, 20 (8): 1021- 1025.

[92] Pan YH , 2020. Multiple knowledge representation of artificial intelligence. Engineering, 6 (3): 216- 217.

[93] Park T , Liu MY , Wang TC , et al., 2019. Semantic image synthesis with spatially-adaptive normalization. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.2332- 2341.

[94] Parmar G , Singh KK , Zhang R , 2023. Zero-shot image-to-image translation. Proc ACM SIGGRAPH Conf, Article 11.

[95] Peng YJ , Han JH , Zhang ZL , et al., 2024. The Tong test:evaluating artificial general intelligence through dynamic embodied physical and social interactions. Engineering, 34: 12- 22.

[96] Qadri R , Mirowski P , Gabriellan A , et al., 2024. Dialogue with the machine and dialogue with the art world: evaluating generative AI for culturally-situated creativity.https://arxiv.org/abs/2412.14077

[97] Radford A , Kim JW , Hallacy C , et al., 2021. Learning transferable visual models from natural language supervision. Proc 38^th Int Conf on Machine Learning, p.8748- 8763.

[98] Rafner JF , Zana B , Hansen IB , et al., 2025. Agency in human-AI collaboration for image generation and creative writing: preliminary insights from think-aloud protocols. Creativ Res J.

[99] Ramesh A , Pavlov M , Goh G , et al., 2021. Zero-shot text-to-image generation. Proc 38th Int Conf on Machine Learning, p.8821- 8831.

[100] Ramesh A , Dhariwal P , Nichol A , et al., 2022. Hierarchical text-conditional image generation with CLIP latents.https://arxiv.org/abs/2204.06125

[101] Ranftl R , Bochkovskiy A , Koltun V , 2021. Vision transformers for dense prediction. Proc IEEE/CVF Int Conf on Computer Vision, p.12159- 12168.

[102] Rezwana J , Maher ML , 2023. Designing creative AI partners with COFI:a framework for modeling interaction in human-AI cocreative systems. ACM Trans Computer-Human Interact, 30 (5): 67.

[103] Rhodes M , 1961. An analysis of creativity. Phi Delta Kappan, 42 (7): p.305- 310.

[104] Rombach R , Blattmann A , Lorenz D , et al., 2022. High-resolution image synthesis with latent diffusion models. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.10674- 10685.

[105] Royal Courts of Justice , 2025. In the High Court of Justice Business and Property Courts of England and Wales Intellectual Property List (ChD).https://www.judiciary.uk/wpcontent/uploads/2025/11/Getty-Images-v-Stability-AI.pdf [Accessed on Aug.4, 2026].

[106] Ruiz N , Li YZ , Jampani V , et al., 2023. DreamBooth:fine tuning text-to-image diffusion models for subject-driven generation. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.22500- 22510.

[107] Runco MA , Jaeger GJ , 2012. The standard definition of creativity. Creativ Res J, 24 (1): 92- 96.

[108] Saharia C , Chan W , Chang HW , et al., 2022a. Palette: image-to-image diffusion models. Proc ACM SIGGRAPH Conf, Article 15.

[109] Saharia C , Chan W , Saxena S , et al., 2022b. Photorealistic text-to-image diffusion models with deep language understanding. Proc 36^th Int Conf on Neural Information Processing Systems, Article 2643.

[110] Satkunarajan J , Koch S , Kurzhals K , 2025. The joy of co-painting:creative human-AI collaboration for traceable image-generation workflows. Proc 18^th Pacific Visualization Conf, p.318- 328.

[111] Sengar SS , Hasan AB , Kumar S , et al., 2025. Generative artificial intelligence:a systematic review and applications. Multimed Tools Appl, 84 (21): 23661- 23700.

[112] Seshadri P , Singh S , Elazar Y , 2024. The bias amplification paradox in text-to-image generation. Proc Conf of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies, p.6367- 6384.

[113] Shahriar S , 2022. Gan computers generate arts? A survey on visual arts, music, and literary text generation using generative adversarial network. Displays, 73: 102237.

[114] Shan S , Cryan J , Wenger E , et al., 2023. Glaze: protecting artists from style mimicry by text-to-image models.https://arxiv.org/abs/2302.04222

[115] Shen YJ , Gu JJ , Tang XO , et al., 2020. Interpreting the latent space of GANs for semantic face editing. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.9240- 9249.

[116] Shi HY , Wang L , Zheng NN , et al., 2022. Loss functions for pose guided person image generation. Patt Recognit, 122: 108351.

[117] Shi WY , Upadhyay S , Quek G , et al., 2025. TalkSketch: multimodal generative AI for real-time sketch ideation with speech.https://arxiv.org/abs/2511.05817

[118] Shneiderman B , 2022. Human-Centered AI.Oxford University Press, Oxford, UK.

[119] Song Y , Sohl-Dickstein J , Kingma DP , 2021. Score-based generative modeling through stochastic differential equations. Proc 9^th Int Conf on Learning Representations.

[120] Song ZR , Yan B , Liu YH , et al., 2025. Injecting domain-specific knowledge into large language models: a comprehensive survey. Proc Association for Computational Linguistics, p.25297- 25311.

[121] Stein G , Cresswell JC , Hosseinzadeh R , et al., 2023. Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models. Proc 37^th Int Conf on Neural Information Processing Systems, Article 165.

[122] Stober S , Dornis TW , 2025. Generative AI training and copyright law.https://arxiv.org/abs/2502.15858

[123] Tan WR , Chan CS , Aguirre HE , et al., 2019. Improved ArtGAN for conditional synthesis of natural image and artwork. IEEE Trans Image Process, 28 (1): 394- 409.

[124] Tan ZT , Chai ML , Chen DD , et al., 2021. Diverse semantic image synthesis via probability distribution modeling. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.7958- 7967.

[125] Tao M , Tang H , Wu F , et al., 2020. DF-GAN:a simple and effective baseline for text-to-image synthesis. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.16494- 16504.

[126] Tholander J , Jonsson M , 2023. Design ideation with AI-sketching, thinking and talking with generative machine learning models. Proc ACM Designing Interactive Systems Conf, p.1930- 1940.

[127] UNESCO , 2003. Text of the Convention for the Safeguarding of the Intangible Cultural Heritage.https://ich.unesco.org/en/convention[Accessed on Aug.4, 2026].

[128] UNESCO , 2021. Recommendation on the Ethics of Artificial Intelligence.https://www.unesco.org/en/legal-affairs/recommendation-ethics-artificial-intelligence[Accessed on Aug.4, 2026].

[129] U.S. Copyright Office , 2025a. Copyright and Artificial Intelligence, Part 2: Copyrightability.U.S. Copyright Office, Washington, DC, USA.

[130] U.S. Copyright Office , 2025b. Copyright and Artificial Intelligence, Part 3: Generative AI Training.U.S. Copyright Office, Washington, DC, USA.

[131] Ungless E , Ross B , Lauscher A , 2023. Stereotypes and smut:the(mis)representation of non-cisgender identities by text-to-image models. Proc Association for Computational Linguistics, p.7919- 7942.

[132] United States Court of Appeals for the District of Columbia Circuit , 2025. Thaler v. Perlmutter (D.C. Cir. 2025).https://law.justia.com/cases/federal/appellate-courts/cadc/23-5233/23-5233-2025-03-18.html [Accessed on Aug.4, 2026].

[133] United States District Court for the Northern District of California , 2026. 23-201-Andersen et al. v. Stability AI Ltd. et al.https://www.govinfo.gov/app/details/USCOURTS-cand-3_23-cv-00201[Accessed on Aug.4, 2026].

[134] van den Oord A , Vinyals O , Kavukcuoglu K , 2017. Neural discrete representation learning. Proc 31^st Int Conf on Neural Information Processing Systems, p.6309- 6318.

[135] Vice J , Akhtar N , Sigal L , et al., 2026. On the fairness, diversity and reliability of text-to-image generative models. Artif Intell Rev, 59: 57.

[136] von Gioi RG , Jakubowicz J , Morel JM , et al., 2010. LSD: a fast line segment detector with a false detection control. IEEE Trans Patt Anal Mach Intell, 32 (4): p.722- 732.

[137] Wadinambiarachchi S , Kelly RM , Pareek S , et al., 2024. The effects of generative AI on design fixation and divergent thinking. Proc CHI Conf on Human Factors in Computing Systems, Article 380.

[138] Wan YX , Wu D , Wang HR , et al., 2024a. The factuality tax of diversity-intervened text-to-image generation: benchmark and fact-augmented intervention. Proc Conf on Empirical Methods in Natural Language Processing, p.9082- 9100.

[139] Wan YX , Subramonian A , Ovalle A , et al., 2024b. Survey of bias in text-to-image generation: definition, evaluation, and mitigation.https://arxiv.org/abs/2404.01030

[140] Wang BY , Chen QF , Wang ZY , 2025. Diffusion-based visual art creation:a survey and new perspectives. ACM Comput Surv, 57 (10): 268.

[141] Wang HF , Xing P , Huang RY , et al., 2024. InstantStyle-Plus: style transfer with content-preserving in text-to-image generation.https://arxiv.org/abs/2407.00788

[142] Wang P , Zhang X , Wei LY , et al., 2026. Human-AI co-ideation via combinational generative model. J Eng Des, 37 (2): 458- 494.

[143] Wang RC , Zhang JL , Xie QS , et al., 2024. PainterNet: adaptive image inpainting with actual-token attention and diverse mask control.https://arxiv.org/abs/2412.01223

[144] Wang YW , Shen T , Zhang SY , et al., 2024. Advances in edge-cloud collaboration and evolution for large-small models. J Image Graph, 29 (6): 1510- 1534 (in Chinese).

[145] Wang ZY , Li AX , Li ZG , et al., 2024. GenArtist: multimodal LLM as an agent for unified image generation and editing. Proc 38^th Int Conf on Neural Information Processing Systems.

[146] Wortsman M , Ilharco G , Gadre SY , et al., 2022. Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. Proc 39^th Int Conf on Machine Learning, p.23965- 23998.

[147] Wu F , Shen T , Bäck T , et al., 2025. Knowledge-empowered, collaborative, and co-evolving AI models: the post-LLM roadmap. Engineering, 44: p.87- 100.

[148] Wu JZ , Ge YX , Wang XT , et al., 2023. Tune-A-Video:one-shot tuning of image diffusion models for text-to-video generation. Proc IEEE/CVF Int Conf on Computer Vision, p.7589- 7599.

[149] Xu JF , Liu ZY , Wang SL , et al., 2023. Foundations and applications of information systems dynamics. Engineering, 27: 254- 265.

[150] Xu T , Zhang PC , Huang QY , et al., 2018. AttnGAN:fine-grained text to image generation with attentional generative adversarial networks. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.1316- 1324.

[151] Xu ZY , Duan KS , Shen XL , et al., 2025. PixelHacker: image inpainting with structural and semantic consistency.https://arxiv.org/abs/2504.20438

[152] Yang BX , Gu SY , Zhang B , et al., 2023. Paint by Example:exemplar-based image editing with diffusion models. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.18381- 18391.

[153] Yang JY , Huang QR , Ding TT , 2023. EmoSet:a large-scale visual emotion dataset with rich attributes. Proc IEEE/CVF Int Conf on Computer Vision, p.20326- 20337.

[154] Yang JY , Feng JW , Huang H , 2024. EmoGen:emotional image content generation with text-to-image diffusion models. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.6358- 6368.

[155] Yang ZY , Wang JF , Li LJ , et al., 2024. Idea2Img: iterative self-refinement with GPT-4V(ision) for automatic image design and generation.https://arxiv.org/abs/2310.08541

[156] Zeiler MD , Fergus R , 2014. Visualizing and understanding convolutional networks. Proc 13^th European Conf on Computer Vision, p.818- 833.

[157] Zhang JS , Li K , Lai YK , et al., 2021. PISE:person image synthesis and editing with decoupled GAN. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.7978- 7986.

[158] Zhang L , Rao AY , Agrawala M , 2023. Adding conditional control to text-to-image diffusion models. Proc IEEE/CVF Int Conf on Computer Vision, p.3813- 3824.

[159] Zhang SF , Huang JF , Zhou Q , et al., 2024. Continuous-multiple image outpainting in one-step via positional query and a diffusion-based approach. Proc 12^th Int Conf on Learning Representations.

[160] Zhang TY , Xie XX , Du XS , et al., 2024. Sketch-guided scene image generation.https://arxiv.org/abs/2407.06469

[161] Zhao SH , Chen DD , Chen YC , et al., 2023. Uni-ControlNet: all-in-one control to text-to-image diffusion models. Proc 37^th Int Conf on Neural Information Processing Systems, Article 491.

[162] Zhao SY , Cui J , Sheng YL , et al., 2021. Large scale image completion via co-modulated generative adversarial networks. Proc 9^th Int Conf on Learning Representations.

[163] Zheng HZ , 2025. Translation methods of AIGC in graphic creativity of intangible cultural heritage and art design strategies. East China Pulp Pap Ind, 55 (10): p.82- 84 (in Chinese).

[164] Zheng QH , Liu H , Zhang XQ , et al., 2025. Machine memory intelligence:inspired by human memory mechanisms. Engineering, 55: 24- 35.

[165] Zhu JY , Park T , Isola P , et al., 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. Proc IEEE Int Conf on Computer Vision, p.2242- 2251.

[166] Zhu RJ , Zhao QH , Li GQ , et al., 2024. SpikeGPT: generative pretrained language model with spiking neural networks.https://arxiv.org/abs/2302.13939

Rights & permissions

The Authors. Published by Zhejiang University Press Co., Ltd.