Collaborative Diffusion: Boosting Designerly Co-Creation with Generative AI
Open accessAbstract
Visual communication in collaborative design provides common ground and a tangible trace of thoughts. Yet, it is often underused due to a lack of visualization skills and time needed to sketch and detail. Current visual co-creation tools can support this with existing images, whereas generative AI can produce entirely new images from textual prompts, allowing for highly specific, personalized results. In this paper, we explore how AI image generation can be used to enhance inspiration and communication throughout collaborative design. We introduce BrainFax, a tool that facilitates generating, editing, and sharing images with AI through a chat bot and online whiteboard. Through co-creation with designers in the field, we found that AI image generation can boost designerly co-creation, yet needs careful embedding into a workflow to leverage inspirational and communicative creations. We close with a critical perspective on the implications of this technology for design and discuss limitations and future work.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Human agency often pivots towards execution, integration, and fine-grained control during the Build stage, materializing the co-created vision.
“Human agency often pivots towards execution, integration, and fine-grained control [178] during this stage, materializing the co-created vision.”
From Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature (2025) · cites this paper as [178]
The Discussion says the human designer should direct the generative-AI loop and make informed design decisions. But the paper’s workflow in §5.1 describes definition, generation, and reflection—not a Build stage—and does not establish a shift toward execution and integration to materialize a co-created vision. Page numbers are unavailable in our copy. (LLM, conf=0.76)
Experimental — accuracy not yet measuredCreative industries (entertainment) employ vision-aligned proactive and semi-proactive agency.
“Creative industries employ vision-aligned proactive and semiproactive agency.”
From Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature (2025) · cites this paper as [178]
The Discussion (section 5; page unavailable) says the human designer should direct the AI-assisted creative process, which supports the idea of aligning the tool with a human vision. The paper does not describe proactive or semiproactive agency, or establish that these modes are employed in entertainment. (LLM, conf=0.79)
Experimental — accuracy not yet measuredThe process of character creation involves an iterative prototyping approach, progressing through initial concept development, environment creation, and final visualization.
“The process of character creation, often perceived as linear, though actually involves an iterative prototyping approach, progressing through initial concept development, environment creation, and final visualization [21, 56, 72].”
From Sketchar: Supporting Character Design and Illustration Prototyping Using Generative AI (2024) · cites this paper as [72]
Section 5.1 describes a repeating definition, generation, and reflection workflow, and the Conclusion says reflection guides further iterations. That supports the iterative aspect, but the paper discusses collaborative image generation, not character creation or the claimed sequence of initial concept development, environment creation, and final visualization. No page numbers are available in our copy. (LLM, conf=0.86)
Experimental — accuracy not yet measuredSketchar allows designers to prototype game characters and generate images based on conceptual input, providing visual outcomes that can give immediate feedback and enhance communication with illustrators' next step in the design cycle.
“we created Sketchar, a Generative AI (GenAI) tool that allows designers to prototype game characters and generate images based on conceptual input, providing visual outcomes that can give immediate feedback and enhance communication with illustrators' next step in the design cycle.”
From Sketchar: Supporting Character Design and Illustration Prototyping Using Generative AI (2024) · cites this paper as [71]
Section 3.1 describes generating images from text prompts, and Section 5.1 says generated images can help communicate ideas to others. The paper does not identify the tool as Sketchar or address game-character prototyping, immediate feedback, or illustrators’ next steps. Page numbers are unavailable in our copy. (LLM, conf=0.84)
Experimental — accuracy not yet measuredThis domain suffers from the issue of created characters becoming stereotypes when lacking originality from their creators.
“This domain suffers from the issue of created characters becoming stereotypes when lacking originality from their creators [72].”
From Sketchar: Supporting Character Design and Illustration Prototyping Using Generative AI (2024) · cites this paper as [72]
The Testing Session (§4.1) discusses limited inspiration when designers use AI to generate designs they already have in mind, and the Discussion (§5) emphasizes human direction of the design process. Neither section addresses created characters becoming stereotypes because their creators lack originality; searches for character stereotypes and originality found no passage making that connection. (LLM, conf=0.74)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 15,880 · see citing works
Generative Adversarial Networks: An Overview
Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., & Bharath, A. A. (2018) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2765202 · Cited by 4,540 · see citing works
Hierarchical Text-Conditional Image Generation with CLIP Latents
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022) · arXiv · doi:10.48550/arxiv.2204.06125 · Cited by 2,511 · cited 1× · see citing works
“With the introduction of DALL-E 2 [18, 23] and MidJourney [15], high-quality AI image generation became available to the public.”
BackgroundHigh-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2021) · arXiv · doi:10.48550/arxiv.2112.10752 · Cited by 737 · see citing works
The Values Encoded in Machine Learning Research
Birhane, A., Kalluri, P., Card, D., Agnew, W., Dotan, R., & Bao, M. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533083 · Cited by 317 · see citing works
The Oxford Handbook of Group Creativity and Innovation
Paulus, P. B., & Nijstad, B. A. (2019) · Oxford University Press eBooks · doi:10.1093/oxfordhb/9780190648077.001.0001 · Cited by 168 · see citing works
FashionQ: An AI-Driven Creativity Support Tool for Facilitating Ideation in Fashion Design
Jeon, Y., Jin, S., Shih, P. C., & Han, K. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445093 · Cited by 145 · see citing works
Wang, H., Cosley, D., & Fussell, S. R. (2010) · ACM Conference on Computer Supported Cooperative Work (CSCW) · doi:10.1145/1718918.1718938 · Cited by 138 · see citing works
Koch, J., Taffin, N., Beaudouin-Lafon, M., Laine, M., Lucero, A., & Mackay, W. E. (2020) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3392850 · Cited by 81 · see citing works
Chandrasegaran, S. K., Bryan, C., Shidara, H., Chuang, T.-Y., & Ma, K. (2019) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300807 · Cited by 63 · see citing works
Shi, Y., Wang, Y., Qi, Y., Chen, J., Xu, X., & Ma, K. (2017) · ACM Conference on Computer Supported Cooperative Work (CSCW) · doi:10.1145/2998181.2998208 · Cited by 57 · see citing works
Visual representation of information as communicative practice
Snyder, J. (2014) · Journal of the Association for Information Science and Technology · doi:10.1002/asi.23103 · Cited by 33 · see citing works
Drawing practices in image-enabled collaboration
Snyder, J. (2013) · Conference on Computer Supported Cooperative Work · doi:10.1145/2441776.2441858 · Cited by 15 · see citing works
Snyder, J., Baumer, E. P. S., Voida, S., Adams, P., Halpern, M. K., Choudhury, T., & Gay, G. K. (2013) · Human-Computer Interaction · doi:10.1080/07370024.2013.870384 · Cited by 10 · see citing works
Ozcelik, D., Terken, J. M. B., Eggen, J. H., & Loenen, V. E. J. (2015) · TU/e Research Portal · Cited by 5 · see citing works
Towards an automatic interior design system using GAN
Dang, Q.-V., Pham, T.-H., Tran, M.-L., Dang, M.-H., Nguyen, Q.-K., & Nguyen, A.-N. (2021) · International Conference on Data Science and Information Technology (DSIT) · doi:10.1145/3478905.3478939 · Cited by 4 · see citing works
Recognizing Artificial Intelligence: The Key to Unlocking Human AI Teams
Cummings, P., Schurr, N., Naber, A. M., Charlie, & Serfaty, D. (2021) · Springer eBooks · doi:10.1007/978-3-030-77283-3_2 · Cited by 4 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- [4]4. Williemien Brand. 2017. Visual Thinking. Vol. 9. Van Haren Publishing.
Cited by
Sorted by citations
The Effects of Generative AI on Design Fixation and Divergent Thinking
Wadinambiarachchi, S., Kelly, R. M., Pareek, S., Zhou, Q., & Velloso, E. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642919 · Cited by 187 · see citing works
“In the case of AI image generators — the focus of our study — the output comes from the latent space of a deep learning model, arising from an iterated diffusion process that involves the model arranging pixels into a composition that makes sense to humans [66].”
Yin, H., Zhang, Z., & Liu, Y. (2023) · Systems · doi:10.3390/systems11120566 · Cited by 131 · see citing works
AI-Augmented Brainwriting: Investigating the use of LLMs in group ideation
Shaer, O., Cooper, A., Mokryn, O., Kun, A. L., & Ben Shoshan, H. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642414 · Cited by 130 · see citing works
When and How to Use AI in the Design Process? Implications for Human-AI Design Collaboration
Lee, S.-Y., Law, M., & Hoffman, G. (2025) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2024.2353451 · Cited by 97 · see citing works
"I look at it as the king of knowledge": How Blind People Use and Understand Generative AI Tools
Adnin, R., & Das, M. (2024) · The 26th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663548.3675631 · Cited by 73 · see citing works
Sketchar: Supporting Character Design and Illustration Prototyping Using Generative AI
Ling, L., Chen, X., Wen, R., Li, T. J.-J., & LC, R. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3677102 · Cited by 52 · see citing works
Liu, Y.-L. E., & Huang, Y.-M. (2025) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2024.2311975 · Cited by 47 · see citing works
Zhang, S., Wang, H., & Yi, X. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757594 · Cited by 36 · see citing works
“Within these applications, systems regulate agency through strategies like combining modalities for user choice [178], integrating multiple sensory channels [11], mapping physical actions directly to controls [207], and adapting interaction methods based on context [51].”
InfluentialIdeationWeb: Tracking the Evolution of Design Ideas in Human-AI Co-Creation
Shen, H., Shen, L., Wu, W., & Zhang, K. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713375 · Cited by 24 · see citing works
The Impact of Generative AI on Creativity in Software Development: A Research Agenda
Jackson, V., Vasilescu, B., Russo, D., Ralph, P., Prikladnicki, R., Izadi, M., D’Angelo, S., Inman, S., Andrade, A., & van der Hoek, A. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3708523 · Cited by 23 · see citing works
- Authors
- Verheijden, M. P., & Funk, M.
- Affiliations
- Eindhoven University of Technology (NL)
- Venue
- Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2023-04-19
- Pages
- 1-8
- OpenAlex
- W4366550857
- Semantic Scholar
- 0e95fe89d1ebdd6e857bd4e7e0497beac66a4283
- Cited by
- 83
- References
- 18
- Citations by year
- 2026: 16 · 2025: 35 · 2024: 29 · 2023: 3
- FWCI
- 24.29
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) (publishedVersion)
- TU/e Research Portal (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Digital Media and Visual Art
- Physical Sciences › Engineering › Mechanical Engineering › Design Education and Practice
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Keywords
- generative AI image generation, co-design, chatbots, online whiteboard, design inspiration, design communication, design workflow
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
