DesignWeaver: Dimensional Scaffolding for Text-to-Image Product Design

Tao, Sirui; Liang, Ivan; Peng, Cindy; Wang, Zhiqing; Palani, Srishti; Dow, Steven

doi:10.1145/3706598.3714211

CHI 2025 · First author

DesignWeaver

A workspace for turning vague product ideas into inspectable design dimensions, richer prompts, and better comparison across generated concepts.

52-participant study Prompt scaffolding Text-to-image product design

Paper Talk Code Slides

Diagram of DesignWeaver connecting a design specification to a tag-based prompt box and image gallery

Question

How can an interface help novices see the design dimensions hidden inside prompts and generated images?

Contribution

DesignWeaver makes comparison explicit by letting designers collect, revise, and reuse visual dimensions during iteration.

Evidence

In a controlled study, participants wrote richer prompts and produced more diverse, expert-aligned chair concepts.

Sirui Tao Ivan Liang Cindy Peng Zhiqing Wang Srishti Palani Steven P. Dow

What is DesignWeaver?

DesignWeaver is an interface for making prompt decisions visible. Instead of asking novices to invent the right design vocabulary from a blank text box, it surfaces dimensions such as style, material, ergonomics, and form from briefs, images, and generated concepts. In a controlled study (n = 52), participants wrote more nuanced prompts and produced more diverse, novel designs than with a standard text-only interface (Tao et al., 2025).

DesignWeaver interface overview showing a prompt box, dimension palette, image gallery, and favorite folder

Figure 1: DesignWeaver: An AI-enabled product design interface for novices. The components include (A) Prompt Box, (B) Dimension Palette, (C) Image Gallery, and (D) Favorite Folder

How DesignWeaver Works

Upload Design Brief
Client persona, requirements, and moodboard go in; the system extracts three initial dimensions.
Build AI Prompt
Designers click tags or type text, then the prompt is formatted into a more complete design request.
Generate And Inspect Designs Designers compare three rendered images and use Info to surface new tags from the outputs.
Iterate And Refine Designers add or remove dimensions, regenerate, and collect favorites for side-by-side comparison.

System diagram showing how DesignWeaver ingests design documents, recommends dimensions, generates images, and supports iteration

Figure 2: Overview of the iterative design process using DesignWeaver. The process involves four main stages: (1) Ingest the design document to extract initial dimensions and tags, (2) Refine and recommend dimensions to generate prompts, (3) Use prompts to render and refine images, and (4) Iterate based on new dimensions and tags inspired by the generated images.

Key Features of DesignWeaver

Dimension Palette
- Extracts dimensions (style, color, form) from an uploaded brief
- Lets users toggle tags (e.g., “minimalist,” “sustainable”) to build prompts
Interactive Prompt Box
- Merges user text with activated tags
- Completes and reformats prompts via GPT-4
Image Gallery & Feedback
- Generates three DALL-E 3 images per prompt
- Info buttons surface new tags from generated images via GPT-4o-mini
- Favorites support side-by-side comparison

Full DesignWeaver interface with the design document, prompt box, dimension palette, image panel, and favorite selection tools

Figure 3: User Interface of DesignWeaver. The UI facilitates structured dimensional tagging and interactive exploration of AI-generated designs. Key features include a design document for guidance, a prompt box for input, a dimension palette for organizing and modifying design aspects, and an image panel displaying generated outputs. Users can add or delete dimensions, tag designs, view detailed image information, and curate favorite designs for final selection. This workflow supports iterative refinement and creativity.

DesignWeaver Implementation Details

Frontend: React
Backend: Python + Firebase / Firestore
AI Models: GPT‑4o (prompting), DALL·E 3 (image generation), GPT‑4o‑mini (tag extraction)

Baseline study workflow showing participants creating product design prompts without dimensional scaffolding

Figure 4: The baseline interface mimics a standard text-to-image setup, excluding scaffolding components.

DesignWeaver Research Results

A user study involving 52 novice designers revealed that DesignWeaver:

Prompt Quality: Encouraged longer and more nuanced text prompts.
Design Diversity: Led to the creation of more diverse and innovative images.
Creative Exploration: Rated higher on creative exploration and continuous improvement of design ideas

DesignWeaver study workflow showing how participants use extracted dimensions, prompts, generated images, and favorites

Figure 5: Workflow of the user study.

DesignWeaver Impact & Conclusion

DesignWeaver bridges the gap between novice and expert design approaches by:

Providing structured guidance in prompt engineering.
Enabling a deeper exploration of design spaces through iterative feedback.
Enhancing the overall quality and novelty of design outputs.

Distribution plot comparing image similarity scores for generated chair concepts

Figure 6: Participants rated DesignWeaver higher than the Baseline on ease of idea-to-prompt conversion, design space exploration, prompt generation, concept refinement, and iterative design improvement (Left).
DesignWeaver participants created semantically more diverse images than the Baseline (Right).

Gallery comparing the novelty and diversity of chair concepts created with DesignWeaver and baseline workflows

Figure 7: Top 5 expert rated chair on novelty.

Conclusion

DesignWeaver’s dimensional scaffolding bridges novice‑expert gaps by making domain vocabulary explicit and enabling rapid, structured exploration of design spaces—ultimately fostering more innovative, user‑aligned product concepts.

BibTeX

@inproceedings{tao2024designweaver, title = {DesignWeaver: Dimensional Scaffolding for Text-to-Image Product Design}, author = {Tao, Sirui and Liang,
Ivan and Peng, Cindy and Wang, Zhiqing and Palani, Srishti and Dow, Steven}, booktitle = {Conference on Human Factors in Computing Systems}, year =
{2025} }