LCA-GCS: Large City Architecture - Generated Cityscape Set
The Large City Architecture - Generated Cityscape dataset (LCA-GCS) is a comprehensive collection of 1,060,166 AI-generated images representing architectural features of 5,856 global cities. Created using advanced diffusion models, this dataset offers over 200 samples of various architectural types for each city with a population exceeding 100,000. LCA-GCS aims to facilitate comparative analysis, synthesis, and learning from AI-represented architecture, providing a unique resource for researchers, urban planners, and AI developers interested in global architectural trends and urban design.
Dataset Description
The LCA-GCS-set represents cities by situating architectural features from details to interiors to urban forms uncommon for existing databases in a flat ontology that allows to search and compare architectural representations in various ways. We hope that the LCA-set benefits future research that could identify recurring spatial configurations, material palettes, and design elements characteristic of specific regions, cultures, or building typologies. Building on it, the synthetic dataset can contribute to e.g., training site-specific models, identifying commonalities, or extracting features that are difficult to access in existing data.
You can find a machine-readable version to download here: https://huggingface.co/datasets/Punktiert/LCA-GCS
Methodology
Prompts: "Type in City." Where type iterates through the list of types below, and city iterates through the list of cities above 100,000 inhabitants listed at https://simplemaps.com/data/world-cities
Types: Apartment, Apartment Building, Arch, Atrium, Auditorium, Balcony, Bathhouse, Boulevard, Breezeways, Bridge, Brise Soleil, Bungalow, Bus Stop, Cafe, Campus, Canopies, Cityscape, Column, Communal Living Space, Courtyard, Door, Eaves, Enfilade, Entrance, Farm, Flat, Foyer, Forest, Garden, Hall, Habitat, House, Housing, Indoor Market, Indoor Plaza, Kitchen, Kiosk, Large Building, Large House, Living Room, Loft, Loggia, Lobby, Office, Park, Patio, Photo of the City, Piazza, Place, Playhouse, Porch, Rondavel, Roof, Roof Garden, Roof Terrace, Room, Row House, Semi-Detached House, Siedlung, Square, Staircase, Street, Terrace, Tower, Townhouse, Tree, Urban Block, Urban Forest, Urban House, Vegetation, Veranda, Vertical Garden, Villa, Window, Workshop Space.
Technical Details
Generated with Stability SD2.1, SDXL 1.0, SD3, Blackforest Flux Dev (model name listed in caption) using random seeds.
- SD2.1: Sampler DPMPP, Scheduler Karras, CFG: 9.0, Steps: 30.
- SDXL: Sampler DPMPP +2M, Scheduler Karras, CFG: 9.0, Steps: 30.
- SD3: Sampler SGM_Uniform, Scheduler Euler, CFG: 9.0, Steps: 30.
- Blackforest Flux Dev: Sampler XLabs, guidance: 4.3, Steps: 20.
Citation
If you use the LCA dataset in your research, please cite it as follows:
Koehler, D. (2024). Large City Architecture (LCA): A Synthetic Dataset of Global Urban Architecture [Data set]. Huggingface. https://huggingface.co/datasets/Punktiert/LCA-GCS, https://doi.org/10.57967/hf/3111
Disclaimer of Warranties and Liability
Accuracy and Reliability
The webpage "Large City Architecture" and its authors provide the data 'as is' and do not guarantee the accuracy, completeness, or usefulness of the data. No warranties are provided.
Limitation of Liability
To the fullest extent permitted by law, in no event will [Your Data/Website Name] or its authors be liable for any claims, damages, or other liabilities, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the data or the use or other dealings in the data.
License
by Daniel Koehler @punktiert School of Architecture, University of Texas at Austin (2022-24).
This webpage and all containting data is licensed under Creative Commons Attribution-NonCommercial 4.0 International.
UT Austin Web Privacy Policy
UT Austin Web Accessibility Policy
