pith. sign in

arxiv: 2606.20991 · v1 · pith:6V7XSEVVnew · submitted 2026-06-18 · 💻 cs.ET · cs.AI

Text-to-Image Generative AI for Modeling and Simulation: Methods, Opportunities, and Applications

Philippe J. Giabbanelli This is my paper

Pith reviewed 2026-06-26 14:40 UTC · model grok-4.3

classification 💻 cs.ET cs.AI
keywords text-to-image generationgenerative AImodeling and simulationvisualizationprompt engineeringeducational materialsmulti-scale simulations
0
0 comments X

The pith

Text-to-image generation supports modeling and simulation by turning descriptions into visuals for models and outcomes.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents text-to-image generative AI as a tool for the modeling and simulation community, distinct from the more common use of large language models. It details applications including communicating conceptual models, visualizing simulation outcomes, generating educational materials, and interfacing models across scales. The work provides conceptual explanations of how image generators work alongside practical steps for turning prompts or simulation outputs into scenes and embedding the process in local reproducible pipelines.

Core claim

Text-to-image generation converts textual descriptions into images and can support M&S tasks by translating prompts from conceptual models or simulation outputs into visual scenes, with workflows that integrate these tools into reproducible pipelines while emphasizing transferable principles over specific software.

What carries the argument

Translation of prompts derived from simulation outputs or conceptual models into visual scenes via modern image generators, integrated into local pipelines.

If this is right

  • Conceptual models become easier to communicate through generated images.
  • Simulation outcomes gain visual representations that aid analysis.
  • Educational materials can be produced directly from model descriptions.
  • Heterogeneous models in multi-scale simulations can be interfaced visually.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • M&S workflows might shift toward hybrid text-and-image pipelines for documentation and review.
  • Accuracy validation steps could become a standard addition to image-generation stages in simulation practice.

Load-bearing premise

Prompts from simulation outputs or conceptual models translate into visual scenes that remain accurate and useful without introducing misleading artifacts or requiring heavy validation.

What would settle it

A controlled test in which M&S practitioners make systematic errors in model interpretation or decisions after viewing only the generated images instead of the original data.

Figures

Figures reproduced from arXiv: 2606.20991 by Philippe J. Giabbanelli.

Figure 1
Figure 1. Figure 1: This visualization of the options for text-to-image generation was automatically produced from [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: We populated Listing 1 with agent attributes (adult, single parent, stage ‘moving to shelter’) [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: For four generators, we show a pair of outputs where the first (left or top) uses a long narrative [PITH_FULL_IMAGE:figures/full_fig_p011_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: This high-resolution figure in the style of a ComfyUI workflow summarizes the core of the [PITH_FULL_IMAGE:figures/full_fig_p012_4.png] view at source ↗
read the original abstract

Text-to-image generation is a form of generative artificial intelligence (GenAI) that converts textual descriptions into images. Most applications of GenAI in modeling and simulation (M&S) have focused on large language models for documentation, coding, or explanation. By contrast, the potential of image generation remains largely unexplored. This tutorial introduces text-to-image generation to the M&S community and details how it can support several M&S tasks, including communicating conceptual models, visualizing simulation outcomes, generating educational materials, and interfacing heterogeneous models in multi-scale simulations. The tutorial combines conceptual guidance with practical workflows, explaining how modern image generators operate, how prompts and simulation outputs can be translated into visual scenes, and how practitioners can integrate these tools into reproducible local pipelines. By focusing on transferable principles rather than specific tools, the tutorial equips M&S practitioners with the knowledge needed to evaluate, adopt, and adapt text-to-image generation in their simulation workflows.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 2 minor

Summary. The manuscript is a tutorial paper introducing text-to-image generative AI to the modeling and simulation (M&S) community. It claims that this technology can support several M&S tasks, including communicating conceptual models, visualizing simulation outcomes, generating educational materials, and interfacing heterogeneous models in multi-scale simulations. The tutorial combines conceptual guidance with practical workflows, explaining how modern image generators operate, how prompts and simulation outputs can be translated into visual scenes, and how to integrate these tools into reproducible local pipelines, with emphasis on transferable principles rather than specific tools.

Significance. If the described approaches hold, the tutorial could meaningfully expand the GenAI toolkit for M&S practitioners beyond language models, facilitating improved communication of conceptual models and visualization of outcomes. A clear strength is the explicit focus on reproducible local pipelines and transferable principles, which equips readers to adapt methods independently without reliance on proprietary tools.

minor comments (2)
  1. [Abstract] Abstract: The phrasing 'details how it can support' several tasks could be clarified to more explicitly frame these as opportunities rather than established capabilities, to better align with the tutorial's scope.
  2. [Methods section] The manuscript would benefit from additional references to existing work on prompt engineering best practices or image fidelity metrics in related domains to strengthen the methods discussion.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive summary and significance assessment of our tutorial manuscript. The recommendation of minor revision is noted. However, the report lists no specific major comments.

Circularity Check

0 steps flagged

No significant circularity

full rationale

The manuscript is a tutorial paper introducing text-to-image generation to the M&S community. It describes external tools, general principles, and potential applications (communication of models, visualization, education, multi-scale interfacing) without any derivations, equations, fitted parameters, predictions, or self-referential loops. The central content consists of transferable principles and reproducible workflows drawn from existing GenAI methods rather than any claim that reduces to the paper's own inputs by construction. No load-bearing self-citations or ansatzes are invoked.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The tutorial rests on standard assumptions about the capabilities of current text-to-image models and the needs of the M&S community; no free parameters, invented entities, or ad-hoc axioms are introduced in the abstract.

axioms (1)
  • domain assumption Text-to-image generators can produce useful visualizations from textual descriptions of models and simulation outputs.
    Invoked in the description of how prompts and simulation outputs translate into visual scenes.

pith-pipeline@v0.9.1-grok · 5687 in / 1130 out tokens · 16586 ms · 2026-06-26T14:40:49.130626+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

70 extracted references · 8 canonical work pages

  1. [1]

    2025 Winter Simulation Conference (WSC) , pages=

    On the Use of Generative AI in Simulation Studies: A Review of Techniques, Applications and Opportunities , author=. 2025 Winter Simulation Conference (WSC) , pages=. 2025 , organization=

    2025

  2. [2]

    2025 , url =

    Media Guidelines for Talking About Suicide , author =. 2025 , url =

    2025

  3. [3]

    IEEE Transactions on Image Processing , year=

    Characterfactory: Sampling consistent characters with gans for diffusion models , author=. IEEE Transactions on Image Processing , year=

  4. [4]

    ACM SIGGRAPH 2024 conference papers , pages=

    The chosen one: Consistent characters in text-to-image diffusion models , author=. ACM SIGGRAPH 2024 conference papers , pages=

    2024

  5. [5]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

    High-Resolution Image Synthesis with Latent Diffusion Models , author=. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

  6. [6]

    Journal of computer-mediated communication , volume=

    At the heart of it all: The concept of presence , author=. Journal of computer-mediated communication , volume=. 1997 , publisher=

    1997

  7. [7]

    , author=

    The role of transportation in the persuasiveness of public narratives. , author=. Journal of personality and social psychology , volume=. 2000 , publisher=

    2000

  8. [8]

    ICLR Workshop on AI for Social Good , year=

    Visualizing the Consequences of Climate Change Using Cycle-Consistent Adversarial Networks , author=. ICLR Workshop on AI for Social Good , year=

  9. [9]

    Weather and Climate Extremes , volume=

    Superimposing height-controllable and animated flood surfaces into street-level photographs for risk communication , author=. Weather and Climate Extremes , volume=. 2021 , publisher=

    2021

  10. [10]

    Environment and Planning B: Urban Analytics and City Science , pages=

    Enhancing digital twin technology with community-led, science-driven participatory modeling: A case in green infrastructure planning , author=. Environment and Planning B: Urban Analytics and City Science , pages=. 2025 , publisher=

    2025

  11. [11]

    Scientific Reports , volume=

    A causal link between mental imagery and affect-laden perception of climate change related risks , author=. Scientific Reports , volume=. 2023 , publisher=

    2023

  12. [12]

    Big Data and Cognitive Computing , year =

    Distilling the Complexity of Agent-Based Simulations Into Textual Explanations via Large Language Models , author =. Big Data and Cognitive Computing , year =

  13. [13]

    Fire , volume=

    A Review of Two-Dimensional Cellular Automata Models for Wildfire Simulation: Methods, Capabilities, and Limitations , author=. Fire , volume=. 2026 , publisher=

    2026

  14. [14]

    International Conference on Conceptual Modeling , pages=

    Can large language models learn conceptual modeling by looking at slide decks and pass graduate examinations? an empirical study , author=. International Conference on Conceptual Modeling , pages=. 2024 , organization=

    2024

  15. [15]

    2017 Winter Simulation Conference (WSC) , pages=

    A tutorial on simulation conceptual modeling , author=. 2017 Winter Simulation Conference (WSC) , pages=. 2017 , organization=

    2017

  16. [16]

    2019 Winter Simulation Conference (WSC) , pages=

    Simulation education: a survey of faculty and practitioners , author=. 2019 Winter Simulation Conference (WSC) , pages=. 2019 , organization=

    2019

  17. [17]

    Proceedings of the 2010 winter simulation conference , pages=

    Panel discussion: Education on conceptual modeling for simulation-Challenging the art , author=. Proceedings of the 2010 winter simulation conference , pages=. 2010 , organization=

    2010

  18. [18]

    arXiv preprint arXiv:2601.10527 , year=

    A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5 , author=. arXiv preprint arXiv:2601.10527 , year=

    work page arXiv

  19. [19]

    2020 , url =

    Guidelines for Media Portrayals of Individuals Affected by Obesity , author =. 2020 , url =

    2020

  20. [20]

    2024 winter simulation conference (wsc) , pages=

    Broadening access to simulations for end-users via large language models: Challenges and opportunities , author=. 2024 winter simulation conference (wsc) , pages=. 2024 , organization=

    2024

  21. [21]

    Proceedings of the AAAI Symposium Series , volume=

    Towards Personalized Explanations for Health Simulations: A Mixed-Methods Framework for Stakeholder-Centric Summarization , author=. Proceedings of the AAAI Symposium Series , volume=

  22. [22]

    arXiv preprint arXiv:2306.13679 , year=

    GPT-based models meet simulation: How to efficiently use large-scale pre-trained language models across simulation tasks , author=. arXiv preprint arXiv:2306.13679 , year=

    work page arXiv

  23. [23]

    2022 Winter simulation conference (WSC) , pages=

    Automatically explaining a model: Using deep neural networks to generate text from causal maps , author=. 2022 Winter simulation conference (WSC) , pages=. 2022 , organization=

    2022

  24. [24]

    Nature , volume=

    Five ways to ensure that models serve society: a manifesto , author=. Nature , volume=. 2020 , publisher=

    2020

  25. [25]

    Safety science , volume=

    Modelling aerosol transport and virus exposure with numerical simulations in relation to SARS-CoV-2 transmission by inhalation indoors , author=. Safety science , volume=. 2020 , publisher=

    2020

  26. [26]

    ACM Transactions on Intelligent Systems and Technology , volume=

    Disease Simulation in Airport Scenario Based on Individual Mobility Model , author=. ACM Transactions on Intelligent Systems and Technology , volume=. 2023 , publisher=

    2023

  27. [27]

    Enabling new interactions with library digital collections: automatic gender recognition in historical postcards via deep learning , author=. J. Acad. Librariansh. , volume=. 2023 , publisher=

    2023

  28. [28]

    arXiv preprint arXiv:2602.14582 , year=

    YOLO26: A Comprehensive Architecture Overview and Key Improvements , author=. arXiv preprint arXiv:2602.14582 , year=

    work page arXiv

  29. [29]

    arXiv preprint arXiv:2503.18886 , year=

    Cfg-zero*: Improved classifier-free guidance for flow matching models , author=. arXiv preprint arXiv:2503.18886 , year=

    work page arXiv

  30. [30]

    arXiv preprint arXiv:2603.03281 , year=

    CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance , author=. arXiv preprint arXiv:2603.03281 , year=

    work page arXiv

  31. [31]

    2013 winter simulations conference (WSC) , pages=

    Distributed hybrid agent-based discrete event emergency medical services simulation , author=. 2013 winter simulations conference (WSC) , pages=. 2013 , organization=

    2013

  32. [32]

    Companion Proceedings of the ACM Web Conference 2024 , pages=

    Prompt optimizer of text-to-image diffusion models for abstract concept understanding , author=. Companion Proceedings of the ACM Web Conference 2024 , pages=

    2024

  33. [33]

    Advances in Neural Information Processing Systems , volume=

    Adapting diffusion models for improved prompt compliance and controllable image synthesis , author=. Advances in Neural Information Processing Systems , volume=

  34. [34]

    Advances in Neural Information Processing Systems , volume=

    Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery , author=. Advances in Neural Information Processing Systems , volume=

  35. [35]

    Advances in neural information processing systems , volume=

    Laion-5b: An open large-scale dataset for training next generation image-text models , author=. Advances in neural information processing systems , volume=

  36. [36]

    2025 Winter Simulation Conference (WSC) , pages=

    Tutorial: Concepts of Conceptual Modeling , author=. 2025 Winter Simulation Conference (WSC) , pages=. 2025 , organization=

    2025

  37. [37]

    Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL) , pages =

    DiffusionDB: A Large-Scale Prompt Gallery Dataset for Text-to-Image Generative Models , author =. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL) , pages =. 2023 , publisher =

    2023

  38. [38]

    2020 , institution =

    2020

  39. [39]

    PNAS nexus , volume=

    Mitigating the harms of manipulated media: Confronting deepfakes and digital deception , author=. PNAS nexus , volume=. 2025 , publisher=

    2025

  40. [40]

    Social Sciences & Humanities Open , volume=

    Social, legal, and ethical implications of AI-Generated deepfake pornography on digital platforms: A systematic literature review , author=. Social Sciences & Humanities Open , volume=. 2025 , publisher=

    2025

  41. [41]

    arXiv preprint arXiv:2505.20692 , year=

    Can we Debias Social Stereotypes in AI-Generated Images? Examining Text-to-Image Outputs and User Perceptions , author=. arXiv preprint arXiv:2505.20692 , year=

    work page arXiv

  42. [42]

    stability ai and its importance in the landscape of modern copyright law , author=

    Aiming for fairness: an exploration into getty images v. stability ai and its importance in the landscape of modern copyright law , author=. DePaul J. Art Tech. & Intell. Prop. L , volume=. 2024 , publisher=

    2024

  43. [43]

    Neurocomputing , pages=

    Creation, evaluation and self-validation of simulation models with large language models , author=. Neurocomputing , pages=. 2025 , publisher=

    2025

  44. [44]

    Neural Computing and Applications , volume=

    Guiding evolutionary algorithms with large language models to learn fuzzy cognitive maps , author=. Neural Computing and Applications , volume=. 2025 , publisher=

    2025

  45. [45]

    Journal of the Operational Research Society , pages=

    Unlocking the potential of past research: using generative AI to reconstruct healthcare simulation models , author=. Journal of the Operational Research Society , pages=. 2025 , publisher=

    2025

  46. [46]

    International Journal of Production Research , volume=

    From natural language to simulations: applying AI to automate simulation modelling of logistics systems , author=. International Journal of Production Research , volume=. 2024 , publisher=

    2024

  47. [47]

    Proceedings of the AAAI Symposium Series , volume=

    Emerging Uses of AI-Generated Images for Equitable and Transparent Simulations , author=. Proceedings of the AAAI Symposium Series , volume=

  48. [48]

    System Dynamics Review , volume=

    Building and Learning With Models Using AI , author=. System Dynamics Review , volume=. 2026 , publisher=

    2026

  49. [49]

    2025 Winter Simulation Conference (WSC) , pages=

    AI-Empowered Data-Driven Agent-Based Modeling and Simulation: Challenges, Methodologies, and Future Perspectives , author=. 2025 Winter Simulation Conference (WSC) , pages=. 2025 , organization=

    2025

  50. [50]

    Machine Learning and Knowledge Extraction , volume=

    Faithful Narratives from Complex Conceptual Models: Should Modelers or Large Language Models Simplify Causal Maps? , author=. Machine Learning and Knowledge Extraction , volume=. 2025 , publisher=

    2025

  51. [51]

    2022 Winter Simulation Conference (WSC) , pages=

    Using generative adversarial networks to validate discrete event simulation models , author=. 2022 Winter Simulation Conference (WSC) , pages=. 2022 , organization=

    2022

  52. [52]

    Journal of Simulation , pages=

    Promoting empathy in decision-making by turning agent-based models into stories using large-language models , author=. Journal of Simulation , pages=. 2025 , publisher=

    2025

  53. [53]

    ACM Transactions on Modeling and Computer Simulation (TOMACS) , volume=

    A method using generative adversarial networks for robustness optimization , author=. ACM Transactions on Modeling and Computer Simulation (TOMACS) , volume=. 2022 , publisher=

    2022

  54. [54]

    Journal of Computational Social Science , volume=

    A comprehensive investigation of variational auto-encoders for population synthesis , author=. Journal of Computational Social Science , volume=. 2025 , publisher=

    2025

  55. [55]

    2021 Winter Simulation Conference (WSC) , pages=

    Input data modeling: an approach using generative adversarial networks , author=. 2021 Winter Simulation Conference (WSC) , pages=. 2021 , organization=

    2021

  56. [56]

    write newline

    " write newline "" before.all 'output.state := FUNCTION article output.bibitem format.authors "author" output.check author format.key output output.year.check new.block format.title "title" output.check new.block crossref missing format.jour.vol output format.article.crossref output.nonnull format.pages output if new.block note output fin.entry format.ann...

  57. [57]

    Banks, J., J. S. Carson, B. L. Nelson, and D. M. Nicol. 2000. D iscrete- E vent S ystem S imulation\/ . 3rd ed. Upper Saddle River, New Jersey: Prentice-Hall, Inc

    2000

  58. [58]

    Cheng, R. C. H. 1994. ``Selecting Input Models''. In 1994 Winter Simulation Conference (WSC) , 184--191 https://doi.org/10.1109/WSC.1994.717117

    work page doi:10.1109/wsc.1994.717117 1994

  59. [59]

    Chien, C. 1989. ``Small Sample Theory for Steady State Confidence Intervals''. Technical Report No. 37, Department of Operations Research, Stanford University, Stanford, California

    1989

  60. [60]

    Gupta, S. S., K. Nagel, and S. Panchapakesan. 1973. ``On the Order Statistics from Equally Correlated Normal Random Variables''. Biometrika\/ 60(2):403--413

    1973

  61. [61]

    M., and D

    Hammersley, J. M., and D. C. Handscomb. 1964. Monte Carlo Methods . London: Methuen

    1964

  62. [62]

    In: 2022 Winter Simulation Conference (WSC)

    Hunter, S. R., and R. Pasupathy. 2022. ``Central Limit Theorems for Constructing Confidence Regions in Strictly Convex Multi-Objective Simulation Optimization''. In 2022 Winter Simulation Conference (WSC) , 3015--3026 https://doi.org/10.1109/WSC57314.2022.10015390

    work page doi:10.1109/wsc57314.2022.10015390 2022

  63. [63]

    M., and W

    Law, A. M., and W. D. Kelton. 2000. Simulation Modeling & Analysis\/ . 3rd ed. New York: McGraw-Hill, Inc

    2000

  64. [64]

    Paszek, P., S. Ryan, L. Ashall, K. Sillitoe, C. V. Harper, D. G. Spiller et al . 2010. ``Population Robustness Arising from Cellular Heterogeneity''. Proceedings of the National Academy of Sciences\/ 107(25):11644--11649

    2010

  65. [65]

    H., and N

    Powell, J. H., and N. Mustafee. 2017. ``Widening Requirements Capture with Soft Methods: An Investigation of Hybrid M&S Studies in Health Care''. Journal of the Operational Research Society\/ 68(10):1211--1222

    2017

  66. [66]

    Dross, and A

    Rabe, M., F. Dross, and A. Wuttke. 2017. ``Combining a Discrete-event Simulation Model of a Logistics Network with Deep Reinforcement Learning''. In Proceedings of the MIC and MAEB 2017 Conferences . July 4 th -7 th , Barcelona, Spain, 765-774

    2017

  67. [67]

    Schruben, L. W. 1979. ``Designing Correlation Induction Strategies for Simulation Experiments''. In Current Issues in Computer Simulation , edited by\ N. R. Adam and A. Dogramaci, 235--256. New York: Academic Press

    1979

  68. [68]

    Steiger, N. M. 1999. Improved Batching for Confidence Interval Construction in Steady-State Simulation . Ph.D. thesis, Department of Industrial Engineering, North Carolina State University, Raleigh, North Carolina. http://www.lib.ncsu.edu/resolver/1840.16/4713, accessed 12th February 2019

    1999

  69. [69]

    The Chicago Manual of Style\/

    The University of Chicago Press 2010. The Chicago Manual of Style\/ . 16th ed. Chicago: The University of Chicago Press. http://www.chicagomanualofstyle.org

    2010

  70. [70]

    ``Winter Simulation Conference''

    WSC 2026. ``Winter Simulation Conference''. Accessed 25 th January 2026

    2026