<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">uprinmatus</journal-id><journal-title-group><journal-title xml:lang="ru">Известия Юго-Западного государственного университета. Серия: Управление, вычислительная техника, информатика. Медицинское приборостроение</journal-title><trans-title-group xml:lang="en"><trans-title>Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2223-1536</issn><publisher><publisher-name>Юго-Западный государственный университет</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.21869/2223-1536-2025-15-4-35-49</article-id><article-id custom-type="elpub" pub-id-type="custom">uprinmatus-375</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ИНФОРМАЦИОННЫЕ И ИНТЕЛЛЕКТУАЛЬНЫЕ СИСТЕМЫ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>INFORMATION AND INTELLIGENT SYSTEMS</subject></subj-group></article-categories><title-group><article-title>Семантически-инвариантное кондиционирование диффузионных моделей: унифицированный фреймворк для кросс-модельного позитивного промптинга</article-title><trans-title-group xml:lang="en"><trans-title>Semantically invariant conditioning of diffusion models: a unified framework for cross-model positive prompting</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-2497-6433</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Зоткина</surname><given-names>А. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Zotkina</surname><given-names>A. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Зоткина Алена Александровна, кандидаттехнических наук, доцент кафедры программирования</p><p>пр. Байдукова / ул. Гагарина, д. 1а/11, г. Пенза 440039</p></bio><bio xml:lang="en"><p>Alena A. Zotkina, Candidate of Sciences (Engineering), Associate Professor at the Department of Programming</p><p>1a/11 Baidukova Pass. / Gagarina Str., Penza 440039</p></bio><email xlink:type="simple">alena.zotkina.97@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-3358-4394</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Мартышкин</surname><given-names>А. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Martyshkin</surname><given-names>A. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Мартышкин Алексей Иванович, кандидат технических наук, доцент, заведующий кафедрой программирования</p><p>Researcher ID: S-7452-2016</p><p>пр. Байдукова / ул. Гагарина, д. 1а/11, г. Пенза 440039</p></bio><bio xml:lang="en"><p>Alexey I. Martyshkin, Candidate of Sciences (Engineering), Associate Professor, Head of the Department of Programming</p><p>Researcher ID: S-7452-2016</p><p>1a/11 Baidukova Pass. / Gagarina Str., Penza 440039</p></bio><email xlink:type="simple">alexey314@yandex.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0007-9646-2064</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Павлов</surname><given-names>А. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Pavlov</surname><given-names>A. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Павлов Аким Алексеевич, студент кафедры программирования</p><p>пр. Байдукова / ул. Гагарина, д. 1а/11, г. Пенза 440039</p></bio><bio xml:lang="en"><p>Akim A. Pavlov, Student at the Department of Programming</p><p>1a/11 Baidukova Pass. / Gagarina Str., Penza 440039</p></bio><email xlink:type="simple">akimpavlov03@yandex.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0007-8125-8167</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Ткаченко</surname><given-names>А. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Tkachenko</surname><given-names>A. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Ткаченко Александра Васильевна, студент кафедры программирования</p><p>пр. Байдукова / ул. Гагарина, д. 1а/11, г. Пенза 440039</p></bio><bio xml:lang="en"><p>Alexandra V. Tkachenko, Student at the Department of Programming</p><p>1a/11 Baidukova Pass. / Gagarina Str., Penza 440039</p></bio><email xlink:type="simple">Aleksandratka4@yandex.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Пензенский государственный технологический университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Penza State Technological University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>28</day><month>01</month><year>2026</year></pub-date><volume>15</volume><issue>4</issue><fpage>35</fpage><lpage>49</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Зоткина А.А., Мартышкин А.И., Павлов А.А., Ткаченко А.В., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Зоткина А.А., Мартышкин А.И., Павлов А.А., Ткаченко А.В.</copyright-holder><copyright-holder xml:lang="en">Zotkina A.A., Martyshkin A.I., Pavlov A.A., Tkachenko A.V.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://uprinmatus.elpub.ru/jour/article/view/375">https://uprinmatus.elpub.ru/jour/article/view/375</self-uri><abstract><p>Цель исследования – разработка универсальной методологии позитивного промпт-инжиниринга для генерации изображений диффузионными моделями, основанной на глубоком лингво-семантическом анализе взаимодействия «человек – искусственный интеллект» и выявлении кросс-модельных инвариантов.</p><sec><title>Методы</title><p>Методы. В рамках данного исследования применялся междисциплинарный научный подход, объединяющий методы когнитивного анализа и эмпирической верификации.</p></sec><sec><title>Результаты</title><p>Результаты. Результаты исследования подтвердили высокую эффективность предложенной универсальной методологии позитивного промпт-инжиниринга, которая значительно повысила качество генерации изображений диффузионными моделями. Экспериментальные данные показали, что промпты, сформированные по разработанной структуре и стратегиям лексической оптимизации, обеспечивают лучшее соответствие заданным характеристикам и более стабильные результаты across различных моделей, при этом статистически значимо превышая качество неструктурированных промптов (p &lt; 0,01). Использование многоуровневой системы компонентов и имплицитных методов контроля позволило снизить вариативность нежелательных артефактов, повысить точность передачи визуальных характеристик и упростить процесс формирования промптов, делая его более предсказуемым, воспроизводимым и универсальным для различных платформ. В целом внедрение этой методологии способствует улучшению взаимодействия человека с искусственный интеллект, повышению стабильности и качества визуальных результатов, а также облегчает адаптацию промптов под разные модели и задачи.</p></sec><sec><title>Заключение</title><p>Заключение. Проведенное исследование подтвердило эффективность предложенной универсальной методологии позитивного промпт-инжиниринга для генерации изображений диффузионными моделями. Внедрение структурированного подхода и стратегий лексической оптимизации позволяет значительно повысить качество, стабильность и предсказуемость результатов, а также снизить количество нежелательных артефактов. Такой подход способствует более управляемому и универсальному взаимодействию человека с искусственный интеллект, облегчая создание высококачественных изображений в различных моделях и условиях. В дальнейшем использование разработанной методологии может стать основой для повышения эффективности автоматизированных систем генерации визуального контента и расширения их практических возможностей.</p></sec></abstract><trans-abstract xml:lang="en"><p>The purpose of research is development of a universal methodology of positive industrial engineering for image generation by diffusion models based on a deep linguistic and semantic analysis of Human-AI interaction and identification of cross-model invariants.</p><sec><title>Methods</title><p>Methods. Within the framework of this study, an interdisciplinary scientific approach was applied, combining methods of cognitive analysis and empirical verification.</p></sec><sec><title>Results</title><p>Results. The results of the study confirmed the high efficiency of the proposed universal methodology of positive industrial engineering, which significantly improved the quality of image generation by diffusion models. Experimental data have shown that promptas formed according to the developed structure and lexical optimization strategies provide better compliance with the specified characteristics and more stable results across different models, while statistically significantly exceeding the quality of unstructured promptas (p &lt; 0,01). The use of a multi-level system of components and implicit control methods has made it possible to reduce the variability of unwanted artifacts, increase the accuracy of visual characteristics, and simplify the process of creating designs, making it more predictable, reproducible, and universal for various platforms. In general, the implementation of this methodology improves human interaction with AI, increases the stability and quality of visual results, and facilitates the adaptation of products to different models and tasks.</p></sec><sec><title>Conclusion</title><p>Conclusion. The conducted research has confirmed the effectiveness of the proposed universal methodology of positive industrial engineering for image generation by diffusion models. The introduction of a structured approach and lexical optimization strategies can significantly improve the quality, stability and predictability of results, as well as reduce the number of unwanted artifacts. This approach promotes more manageable and universal human-AI interaction, making it easier to create high-quality images in various models and conditions. In the future, the use of the developed methodology can become the basis for improving the efficiency of automated visual content generation systems and expanding their practical capabilities.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>диффузионная модель</kwd><kwd>генерация изображений</kwd><kwd>искусственный интеллект</kwd><kwd>промпт-инжиниринг</kwd><kwd>обработка естественного языка</kwd><kwd>семантический анализ</kwd></kwd-group><kwd-group xml:lang="en"><kwd>diffusion model</kwd><kwd>image generation</kwd><kwd>artificial intelligence</kwd><kwd>industrial engineering</kwd><kwd>natural language processing</kwd><kwd>semantic analysis</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Opportunities and challenges of diffusion models for generative AI / C. Cao, C. Tan, J. Gao [et al.] // National Science Review. 2024. Vol. 11, N 12. P. Nwae348. https://doi.org/10.1093/nsr/nwae348</mixed-citation><mixed-citation xml:lang="en">Cao C., Tan C., Gao J., et al. Opportunities and challenges of diffusion models for generative AI. National Science Review. 2024;11(12):Nwae348. https://doi.org/10.1093/nsr/nwae348</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">A state-of-the-art review of diffusion model applications for microscopic image and microalike image analysis / Yan Liu, Tao Jiang, Rui Li [et al.] // Frontiers in Medicine. 2025. Vol. 12. P. 1551894. https://doi.org/10.3389/fmed.2025.1551894</mixed-citation><mixed-citation xml:lang="en">Yan Liu, Tao Jiang, Rui Li, et al. A state-of-the-art review of diffusion model applications for microscopic image and micro-alike image analysis. Frontiers in Medicine. 2025;12:1551894. https://doi.org/10.3389/fmed.2025.1551894</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">What is Prompt Engineering? // Google Cloud. URL: https://cloud.google.com/discover/what-is-prompt-engineering (дата обращения: 15.09.2025).</mixed-citation><mixed-citation xml:lang="en">What is Prompt Engineering? Google Cloud. Available at: https://cloud.google.com/discover/what-is-prompt-engineering (accessed 15.09.2025).</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Prompt engineering concepts // Amazon Bedrock. URL: https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-engineering-guidelines.html (дата обращения: 20.09.2025).</mixed-citation><mixed-citation xml:lang="en">Prompt engineering concepts. Amazon Bedrock. Available at: https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-engineering-guidelines.html (accessed 20.09.2025).</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Промпт-инжиниринг: создание эффективных запросов для GigaChat // Sber Developers. URL: https://developers.sber.ru/docs/ru/gigachat/prompts-hub/prompt-engineering (дата обращения: 22.09.2025).</mixed-citation><mixed-citation xml:lang="en">Industrial engineering: creating effective queries for GigaChat. Sber Developers. Available at: https://developers.sber.ru/docs/ru/gigachat/prompts-hub/prompt-engineering (accessed 22.09.2025).</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Stable Diffusion 3.5 Prompt Guide // Stability AI. URL: https://stability.ai/learninghub/stable-diffusion-3-5-prompt-guide (дата обращения: 25.09.2025).</mixed-citation><mixed-citation xml:lang="en">Stable Diffusion 3.5 Prompt Guide. Stability AI. Available at: https://stability.ai/learninghub/stable-diffusion-3-5-prompt-guide (дата обращения: 25.09.2025).</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Chain-of-Thought Prompting // Anthropic. URL: https://docs.anthropic.com/ru/docs/buildwith-claude/prompt-engineering/chain-prompts (дата обращения: 27.09.2025).</mixed-citation><mixed-citation xml:lang="en">Chain-of-Thought Prompting. Anthropic. Available at: Available at: https://docs.anthropic.com/ru/docs/build-with-claude/prompt-engineering/chain-prompts (accessed 27.04.2025).</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Imagen prompt guide. Gemini API // Google AI for Developers. URL: https://ai.google.dev/gemini-api/docs/imagen-prompt-guide (дата обращения: 30.09.2025).</mixed-citation><mixed-citation xml:lang="en">Imagen prompt guide | Gemini API. Google AI for Developers. Available at: https://ai.google.dev/gemini-api/docs/imagen-prompt-guide (accessed 30.09.2025).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Collection of Dall-E 3 prompting tips, issues and bugs, Simplified // OpenAI. URL: https://community.openai.com/t/collection-of-dall-e-3-prompting-tips-issues-and-bugs-simplified/994822 (дата обращения: 03.09.2025).</mixed-citation><mixed-citation xml:lang="en">Collection of Dall-E 3 prompting tips, issues and bugs, Simplified. OpenAI. Available at: https://community.openai.com/t/collection-of-dall-e-3-prompting-tips-issues-and-bugs-simplified/994822 (accessed 03.09.2025).</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">How to Design Prompts for Flux 1.1 Pro. URL: https://fluxproweb.com/blog/detail/Howto-Design-Prompts-for-Flux-1-1-Pro-0a16b61b16e6/ (дата обращения: 05.09.2025).</mixed-citation><mixed-citation xml:lang="en">How to Design Prompts for Flux 1.1 Pro. Available at: https://fluxproweb.com/blog/detail/How-to-Design-Prompts-for-Flux-1-1-Pro-0a16b61b16e6/ (accessed 05.09.2025).</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Version // Midjourney Docs. URL: https://docs.midjourney.com/hc/en-us/articles/32199405667853-Version (дата обращения: 07.09.2025).</mixed-citation><mixed-citation xml:lang="en">Version. Midjourney Docs. Available at: https://docs.midjourney.com/hc/en-us/articles/32199405667853-Version (accessed 07.09.2025).</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Ideogram 3.0 // Ideogram. URL: https://about.ideogram.ai/3.0 (дата обращения: 10.09.2025).</mixed-citation><mixed-citation xml:lang="en">Ideogram 3.0. Ideogram. Available at: https://about.ideogram.ai/3.0 (accessed 10.09.2025).</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Kandinsky 3.0 // AI Forever. URL: https://ai-forever.github.io/Kandinsky-3/ (дата обращения: 12.09.2025).</mixed-citation><mixed-citation xml:lang="en">Kandinsky 3.0. AI Forever. Available at: https://ai-forever.github.io/Kandinsky-3/ (accessed 12.09.2025).</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">How to Craft Prompts for Accurate, AI-Generated Images // Recraft. URL: https://www.recraft.ai/blog/how-to-craft-prompts-for-accurate-ai-generated-images (дата обращения: 15.09.2025).</mixed-citation><mixed-citation xml:lang="en">How to Craft Prompts for Accurate, AI-Generated Images. Recraft. Available at: https://www.recraft.ai/blog/how-to-craft-prompts-for-accurate-ai-generated-images (accessed 15.09.2025).</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Navigating the Alignment Challenges of Diffusion Models: Insights and Innovations // Preprints.org. 2025. N 1502 // URL: https://www.preprints.org/manuscript/202501.1502/v1 (дата обращения: 18.09.2025).</mixed-citation><mixed-citation xml:lang="en">Navigating the Alignment Challenges of Diffusion Models: Insights and Innovations. Preprints.org. 2025;(1502). Available at: https://www.preprints.org/manuscript/202501.1502/v1 (accessed 18.09.2025).</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Recraft introduces a revolutionary AI model that thinks in design language // Recraft. URL: https://www.recraft.ai/blog/recraft-introduces-a-revolutionary-ai-model-that-thinks-in-design-language (дата обращения: 20.09.2025).</mixed-citation><mixed-citation xml:lang="en">Recraft introduces a revolutionary AI model that thinks in design language. Recraft. Available at: https://www.recraft.ai/blog/recraft-introduces-a-revolutionary-ai-model-that-thinksin-design-language (accessed 20.09.2025).</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Hierarchical Text-Conditional Image Generation with CLIP Latents // A. Ramesh, P. Dhariwal, A. Nichol [et al.] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022. URL: https://arxiv.org/abs/2204.06125 (дата обращения: 18.09.2025).</mixed-citation><mixed-citation xml:lang="en">Ramesh A., Dhariwal P., Nichol A., et al. Hierarchical Text-Conditional Image Generation with CLIP Latents. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022. Available at: https://arxiv.org/abs/2204.06125 (accessed 18.09.2025).</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Ho J., Jain A., Abbeel P. Denoising Diffusion Probabilistic Models // Advances in Neural Information Processing Systems (NeurIPS). 2020. Vol. 33. URL: https://proceedings.neurips.cc/paper/2020/hash/4c5bcfec8584af0d967f1ab10179ca4b-Abstract.html (дата обращения: 11.09.2025).</mixed-citation><mixed-citation xml:lang="en">Ho J., Jain A., Abbeel P. Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems (NeurIPS). 2020;33. Available at: https://proceedings.neurips.cc/paper/2020/hash/4c5bcfec8584af0d967f1ab10179ca4b-Abstract.html (accessed 11.09.2025).</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Rombach R., Blattmann A., Lorenz D., et al. High-Resolution Image Synthesis with Latent Diffusion Models // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022. URL: https://openaccess.thecvf.com/content/CVPR2022/papers/Rombach_High-Resolution_Image_Synthesis_With_Latent_Diffusion_Models_CVPR_2022_paper.pdf (дата обращения: 11.09.2025).</mixed-citation><mixed-citation xml:lang="en">Rombach R., Blattmann A., Lorenz D., et al. High-Resolution Image Synthesis with Latent Diffusion Models. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022. Available at: https://openaccess.thecvf.com/content/CVPR2022/papers/Rombach_High-Resolution_Image_Synthesis_With_Latent_Diffusion_Models_CVPR_2022_paper.pdf (accessed 11.09.2025).</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
