TY - GEN

T1 - Towards a Generative AI Design Dialogue

AU - Owen, Aron

AU - Roberts, Jonathan C.

N1 - Conference code: 42

PY - 2024/8/28

Y1 - 2024/8/28

N2 - Traditional visualisation designers often start with sketches before implementation. With generative AI, these sketches can be turned into AI-generated visualisations using specific prompts. However, guiding AI to create compelling visuals can be challenging. We propose a new design process where designers verbalise their thoughts during work, later converting these narratives into AI prompts. This approach helps AI generate accurate visuals and assists designers in refining their concepts, enhancing the overall design process. Blending human creativity with AI capabilities enables rapid iteration, leading to higher quality and more innovative visualisations, making design more accessible and efficient.

AB - Traditional visualisation designers often start with sketches before implementation. With generative AI, these sketches can be turned into AI-generated visualisations using specific prompts. However, guiding AI to create compelling visuals can be challenging. We propose a new design process where designers verbalise their thoughts during work, later converting these narratives into AI prompts. This approach helps AI generate accurate visuals and assists designers in refining their concepts, enhancing the overall design process. Blending human creativity with AI capabilities enables rapid iteration, leading to higher quality and more innovative visualisations, making design more accessible and efficient.

KW - Visualisation

KW - Information Visualisation

KW - Visualisation design

KW - Visualisation theory

KW - Text to Image

KW - Design Dialogue

KW - Generative AI

KW - Artificial Intelligence

M3 - Conference contribution

BT - Computer Graphics and Visual Computing (CGVC) 2024, United Kingdom

PB - The Eurographics Association

T2 - Computer Graphics & Visual Computing (2024)

Y2 - 12 September 2024 through 13 September 2024

ER -