Relation-Aware and Constraint-Guided Discrete Diffusion for Design Color Scheme Generation Siyuan Xie1 , Qiao He2* 1 School of Music, Guangzhou Xinhua University, Guangzhou, China 2 College of Art and Design, Beijing City University, Beijing, China * Corresponding author: Qiao He. Email: qhe856006@gmail.com Journal of Discovery Core 2026, Vol. 1, No. 2, pp. 80-109 DOI: 10.67541/jdc2610 Received: 21 August 2026; Revised: 23 September 2026; Accepted: 18 October 2026; Published: 28 October 2026 Abstract <p>The color collocation of the design scheme should meet multiple constraints such as functional semantics, visual harmony, accessibility and style consistency at the same time. The existing rule template, image extraction and condition generation methods have structural contradictions between constraint controllability and combination diversity, and the color relationship is always outside the generation process, only for post-output screening. In this paper, the problem is formulated as a sequential decision problem of discrete color combinations under multiple constraints, and the relation-aware diffusion generation framework ColorRel-Diff is proposed. The discrete color token sequence is used as the generation unit, and the mask discrete diffusion is used to make each denoising step explicitly masked discrete diffusion. The color relationship coding module is constructed, and the harmony and contrast relationships are encoded as the edge features of the relationship graph and aggregated into the relationship perception embedding through the graph attention. A constraining-guided denoising mechanism is designed to guide the sampling trajectory by the gradient of relational consistency score, and the feasibility mask is used to impose inviolable token-level restrictions on the hard constraints, and the grading softening strategy is used to deal with constraint conflicts. A three-layer inspection system of distribution level, constraint level and design availability level is constructed, and experiments and ablation are carried out on the basis of increasing constraint strictness. The results show that the proposed method occupies a Pareto-dominant position in the diversity-harmony plane, and the satisfaction rate of accessibility hard constraints remains above 95% under pressure, which is significantly better than the baseline without explicit modeling constraints. The ablation confirms that relational coding and constraint guidance dominate the gains of harmony and constraint compliance respectively.</p> Keywords Color collocation generation Discrete diffusion model Relation-aware coding Constraint guided denoising Design usability assessment References Feng, L., Yu, G., Miao, M., &amp; Sun, J. (2025). Sustainable Color Development Strategies for Ancient Chinese Historical Commercial Areas: A Case Study of Suzhou's Xueshi Street–Wuzounfang Street. Sustainability, 17(11), 4756. DOI: 10.3390/su17114756 Kim, B., Lee, G., &amp; Suk, H. J. (2026). Color adjustment of brand logos for dark mode display. PLoS One, 21(1), e0339392. DOI: 10.1371/journal.pone.0339392 Zhou, X., Xiao, C., Yoon, S., &amp; Zhu, H. (2026). The color of status: color saturation, brand heritage, and perceived status of luxury brands. Journal of Consumer Research, 52(6), 1232-1252. DOI: 10.1093/jcr/ucaf029 Zhang, H., Song, H., Li, S., Zhou, M., &amp; Song, D. (2023). A survey of controllable text generation using transformer-based pre-trained language models. ACM Computing Surveys, 56(3), 1-37. DOI: 10.1145/3617680 Luo, J., Tian, Y., &amp; Wang, Z. (2024). Research on unmanned aerial vehicle path planning. Drones, 8(2), 51. DOI: 10.3390/drones8020051 Museros, L., Sanz, I., Falomir, Z., &amp; Gonzalez-Abril, L. (2020). Creating, interpreting and rating harmonic colour palettes using a cognitively inspired model. Cognitive Computation, 12(2), 442-459. DOI: 10.1007/s12559-018-9589-2 Zhang, Y., Lin, C., Tang, S., Chen, H., Zhou, S., Ma, Y., &amp; Tresp, V. (2025). Swarmagentic: Towards fully automated agentic system generation via swarm intelligence. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (pp. 1778-1818). DOI: 10.18653/v1/2025.emnlp-main.93 Liu, S., Tao, M., Huang, Y., Wang, C., &amp; Li, C. (2022). Image-driven harmonious color palette generation for diverse information visualization. IEEE Transactions on Visualization and Computer Graphics, 30(7), 3089-3103. DOI: 10.1109/tvcg.2022.3226218 Gao, Y., Liang, J., &amp; Yang, J. (2025). Color palette generation from digital images: A review. Color Research &amp; Application, 50(3), 250-265. DOI: 10.1002/col.22975 Sun, M. H., &amp; Chou, T. R. (2026). Disentangled Emotion-Controllable Color Palette Generation via β-CVAE with Conditional Prior. In 2026 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) (pp. 605-610). IEEE. DOI: 10.1109/icaiic68212.2026.11454419 Wang, K., Jiang, Z., Feng, H., Zhao, W., Liu, L., Li, J., ... &amp; Lin, W. (2026). CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credit. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 11105-11123). DOI: 10.18653/v1/2026.acl-long.509 Araujo Oliveira, R. M., Oliveira Sant'Anna, Â. M., Ferreira, P. H., &amp; Purcino de Souza, E. E. (2026). Fuzzy hybrid system based on ensemble learning for classification in intelligent manufacturing processes. The International Journal of Advanced Manufacturing Technology, 1-29. DOI: 10.1007/s00170-026-18928-3 Hristov, H., Glushkova, T., Cheresharov, S., &amp; Stoeva, M. (2022). A model for designing accessible color and contrast for users with visual deficiency and color blindness. In 2022 IEEE 11th International Conference on Intelligent Systems (IS) (pp. 1-7). IEEE. DOI: 10.1109/is57118.2022.10019637 Lewandowska, A., Olejnik-Krugly, A., Jankowski, J., &amp; Dziśko, M. (2021). Subjective and objective user behavior disparity: Towards balanced visual design and color adjustment. Sensors, 21(24), 8502. DOI: 10.3390/s21248502 Sun, C., Li, C., Lin, X., Zheng, T., Meng, F., Rui, X., &amp; Wang, Z. (2023). Attention-based graph neural networks: a survey. Artificial Intelligence Review, 56(Suppl 2), 2263-2310. DOI: 10.1007/s10462-023-10577-2 Guo, X., Yu, Z., &amp; Yin, J. (2026). Fusion of Radiomics and Gated Graph Attention Network for Pulmonary Nodule Malignancy Classification. Journal of Imaging, 12(9), 408. DOI: 10.3390/jimaging12090408 Höllerer, S., Papaxanthos, L., Gumpinger, A. C., Fischer, K., Beisel, C., Borgwardt, K., ... &amp; Jeschek, M. (2020). Large-scale DNA-based phenotypic recording and deep learning enable highly accurate sequence-function mapping. Nature Communications, 11(1), 3551. DOI: 10.1038/s41467-020-17222-4 Elfmann, C., &amp; Stülke, J. (2023). PAE viewer: a webserver for the interactive visualization of the predicted aligned error for multimer structure predictions and crosslinks. Nucleic Acids Research, 51(W1), W404-W410. DOI: 10.1093/nar/gkad350 Meng, C., Gao, J., Tian, Y., Chen, H., Zhang, W., &amp; Luo, R. (2024). Stochastic solutions for simultaneous seismic data denoising and reconstruction via score-based generative models. IEEE Transactions on Geoscience and Remote Sensing, 62, 1-15. DOI: 10.1109/tgrs.2024.3421597 Garber, T., &amp; Tirer, T. (2024). Image restoration by denoising diffusion models with iteratively preconditioned guidance. In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 25245-25254). IEEE. DOI: 10.1109/cvpr52733.2024.02385 Valenko, S. I., Čačić, M., Stanimirović, I. Ž., &amp; Zorko, A. (2025). Visual Perception of Peripheral Screen Elements: The Impact of Text and Background Colors. Applied Sciences, 15(14), 7636. DOI: 10.3390/app15147636 Jakovljević, T., Janković, M. M., Savić, A. M., Soldatović, I., Todorović, P., Jere Jakulin, T., ... &amp; Ković, V. (2021). The sensor hub for detecting the developmental characteristics in reading in children on a white vs. colored background/colored overlays. Sensors, 21(2), 406. DOI: 10.3390/s21020406 Collins, M., Vice, J., French, T., &amp; Mian, A. (2026). Natadiff: Adversarial boundary guidance for natural adversarial diffusion. In International Conference on Learning Representations (Vol. 2026, pp. 12099-12145). DOI: 10.48550/arXiv.2505.20934 Kabir, A. M., Thakar, S., Malhan, R. K., Shembekar, A. V., Shah, B. C., &amp; Gupta, S. K. (2021). Generation of synchronized configuration space trajectories with workspace path constraints for an ensemble of robots. The International Journal of Robotics Research, 40(2-3), 651-678. DOI: 10.1177/0278364920988087 Wainer, J. (2023). A Bayesian Bradley-Terry model to compare multiple ML algorithms on multiple data sets. Journal of Machine Learning Research, 24(341), 1-34. DOI: 10.48550/arXiv.2208.04935 Fayomi, A., Majeed, R., Algarni, A., Akhtar, S., Jamal, F., &amp; Nasir, J. A. (2022). Forecasting tennis match results using the Bradley‐Terry model. International Journal of Photoenergy, 2022(1), 1898132. DOI: 10.1155/2022/1898132 Fageot, J., Farhadkhani, S., Hoang, L. N., &amp; Villemaud, O. (2024). Generalized bradley-terry models for score estimation from paired comparisons. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 38, No. 18, pp. 20379-20386). DOI: 10.1609/aaai.v38i18.30020 <p>© 2026 The Author(s). Published by Digital Intelligence Press Limited. This is an open access article under the CC BY 4.0 license.</p> <p>How to cite: Xie, S., &amp; He, Q. (2026). Relation-Aware and Constraint-Guided Discrete Diffusion for Design Color Scheme Generation. Journal of Discovery Core, 1(2), 80-109. https://doi.org/10.67541/jdc2610</p>