Examining the Text-to-Image Community of Practice: Why and How do People Prompt Generative AIs?
Open accessThe DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
Image generation gained popularity with machine learning (ML) models generating images from text, fuelling new online communities of practices. This work explores the sociology, motivations, and usages of AI art hobbyists. We analyzed an online questionnaire answered by 64 practitioners and a dataset of user prompts sent to the Stable Diffusion generative model. Our findings suggest that TTI generation is a recreational activity mainly conducted by narrow socio-demographic groups who use auxiliary techniques across platforms and beyond request-response interactions. Inherent model limitations and finding suitable prompt formulation are the main obstacles practitioners face. A taxonomy and a corresponding ML model capable of recognizing the semantic content of unseen prompts were created to conduct the user prompt analysis. The prompt analysis revealed that artist names are the main specifier used beside the main subject, often in sequences. We finally discuss the design and socio-technical implications of our work for creativity support.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Braun, V., & Clarke, V. (2012) · APA handbook of research methods in psychology, Vol 2: Research designs: Quantitative, qualitative, neuropsychological, and biological. · doi:10.1037/13620-004 · Cited by 10,299
Denoising Diffusion Probabilistic Models
Ho, J., Jain, A., & Abbeel, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11239 · Cited by 8,712
Neural Architectures for Named Entity Recognition
Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K., & Dyer, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1030 · Cited by 4,401 · cited 1×
“The NER model chosen relies on a transition-based parsing approach [33], which builds state transitions to condition the predictions.”
MethodDeep Unsupervised Learning using Nonequilibrium Thermodynamics
Sohl-Dickstein, J., Weiss, E. A., Maheswaranathan, N., & Ganguli, S. (2015) · arXiv · doi:10.48550/arxiv.1503.03585 · Cited by 2,637 · cited 1×
“Second, the quality and coherence of generated images were improved by diffusion models [28, 29, 49, 50].”
BackgroundDreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2022) · arXiv · doi:10.48550/arxiv.2208.12242 · Cited by 2,442
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.02155 · Cited by 2,295
Generative Modeling by Estimating Gradients of the Data Distribution
Song, Y., & Ermon, S. (2019) · arXiv · doi:10.48550/arxiv.1907.05600 · Cited by 1,453 · cited 1×
“Second, the quality and coherence of generated images were improved by diffusion models [28, 29, 49, 50].”
BackgroundBERTopic: Neural topic modeling with a class-based TF-IDF procedure
Grootendorst, M. (2022) · arXiv · doi:10.48550/arxiv.2203.05794 · Cited by 1,423 · cited 2×
“The topic modeling analysis follows the approach described by Grootendorst [26].”
BackgroundMethodLAION-5B: An open large-scale dataset for training next generation image-text models
Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.08402 · Cited by 1,022
Design Guidelines for Prompt Engineering Text-to-Image Generative Models
Liu, V., & Chilton, L. B. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3501825 · Cited by 639 · cited 3×
“Liu and Chilton [34] examined the impact of various prompt specifiers and model hyperparameters (i.”
BackgroundMethod
Cited by
Liu, M., Zhang, L. J., & Zhang, D. (2025) · Computers in Human Behavior · doi:10.1016/j.chb.2025.108569 · Cited by 43
Towards a Diffractive Analysis of Prompt-Based Generative AI
Rajcic, N., Llano Rodriguez, M. T., & McCormack, J. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3641971 · Cited by 37
Understanding Visual Artists’ Values and Attitudes towards Collaboration, Technology, and AI
Johnston, H., & Thue, D. (2024) · Graphics Interface · doi:10.1145/3670947.3670973 · Cited by 12
“Sanchez studied 64 AI art hobbyists to understand their motivations for text-to-image generator use and the problems they encountered [26].”
Creative ML Assemblages: The Interactive Politics of People, Processes, and Products
Shelby, R., Srinivasan, R., Burgdorf, K., Lena, J. C., & Rostamzadeh, N. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3637315 · Cited by 6
Metadata
- Authors
- Sanchez, T.
- Venue
- Creativity and Cognition
- Publisher
- ACM
- Published
- 2023-06-19
- Pages
- 43-61
- OpenAlex
- W4381104252
- Cited by
- 50
- References
- 15
- FWCI
- 15.06
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Examining the Text-to-Image Community of Practice: Why and How do People Prompt Generative AIs? https://app.cochat.ai/papers/10.1145/3591196.3593051
- The paper
- Sanchez, T. (2023). Examining the Text-to-Image Community of Practice: Why and How do People Prompt Generative AIs? Creativity and Cognition. https://doi.org/10.1145/3591196.3593051
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.