kth.sePublications KTH
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
The Role of Artificial Intelligence and its Capabilities in the Process of Conceptualizing a Lighting Design
KTH, School of Architecture and the Built Environment (ABE), Architecture, Lighting Design.
2023 (English)Independent thesis Advanced level (degree of Master (One Year)), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

Artificial Intelligence (AI) has been developing rapidly and is currently being used in many industries, including design and architecture. Lighting design is one of these industries where AI can be a valuable tool for developing concepts and designs. This study focuses on the available AI platforms that can be used for the conceptualization of lighting designs and explores the role that AI can play in the design process of a lighting designer.

To evaluate this, ChatGPT was trained to provide image generation prompts which can be used in Midjourney to achieve lighting design concepts as an image. This image was then evaluated and modelled in 3D using DIALux to achieve quantitative parameters, such as illuminance levels, uniformity, unified glare ratings, and other standards mentioned in the EN 12464-1:2021.

In conclusion, although the AI-generated design may appear traditional and outdated, the study highlights that AI can be a valuable tool for conceptualizing lighting designs and can serve as a source of inspiration for designers. However, it is important to note that significant groundwork is still required from the designer. The research further investigates the various capabilities and limitations of AI in the context of lighting design, aiming to identify its true potential in the field.

Place, publisher, year, edition, pages
2023.
Series
TRITA-ABE-MBT-23194
Keywords [en]
Artificial Intelligence, Artificial Lighting, Lighting Concepts and Designs, Midjourney, ChatGPT
National Category
Architecture
Identifiers
URN: urn:nbn:se:kth:diva-342947OAI: oai:DiVA.org:kth-342947DiVA, id: diva2:1833764
Subject / course
Architectural Lighting Design
Educational program
Master of Science - Architectural Lighting Design
Supervisors
Examiners
Available from: 2024-02-01 Created: 2024-02-01 Last updated: 2025-02-24

Open Access in DiVA

fulltext(5656 kB)1450 downloads
File information
File name FULLTEXT01.pdfFile size 5656 kBChecksum SHA-512
eaa93b27df5a5702d5a72b5bcbb7c9932fdffe5c5be565208701b051236cac4045bc66dae30ab34ac554ec207463fd1ec36fdc89d42135587a34f224889e9085
Type fulltextMimetype application/pdf

By organisation
Lighting Design
Architecture

Search outside of DiVA

GoogleGoogle Scholar
Total: 1450 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 1199 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf