Skip to content

lucianoambrosini.it

Chapter 
Official Ambrosinus Toolkit research in “CODING ARCHITECTURE – Designing Toolkits, Workflows, Industry” Book

This chapter represents the official document in which I introduce the “Ambrosinus Toolkit”. Although from this publication to date I have significantly implemented its capabilities, I invite the reader, researcher, scholar and Computational Designer to take this document as an official source to cite it as part of the effective toolkits available in the  AEC industry.

indexlab_banner_03
springer-logo-transparent

Abstract. Large-scale Text Generative Models known as DALL-E and Stable Diffusion offer incredible opportunities to improve and enhance the creation and manipulation of design communication through images. The toolkit developed by the author shows how to integrate the LTGMs technology introduced by the OpenAI and StabilityAI platforms into the creative design process as well as the Dense Prediction Transformers (DPT) technology capable to predict a 3D-shaped object started from a 2D image generated by the AI. This contribution will provide the key elements to understand some fundamental aspects of research on artificial intelligence, while through the “Ambrosinus-Toolkit” project, publicly shared on the network, the reader will be provided with operating cues that can be experienced during the schematic design stage. The research presented bears witness to a first step foot with a new paradigm that uses Diffusion Models in the computational design workflow.

Keywords: Artificial Intelligence, LTGMs, Dense Prediction Transformers, Diffusion Models, Generative AI, Human-AI

Chapter
Some related images
Stable Diffusion text-to-image simplified process schema (source by author)
Operative schema of the Toolkit usability
(top) “DPTto3D” component generated the depth map estimation; (bottom) preview frames of the Mesh object and the PointCloud prediction.
How to cite this Research work
Please if you want to cite this Research work (in publication phase) totally or partially, enter this DOI reference: 10.1007/978-3-031-47913-7_1 or cite it as reported here.
Interested in my works? see *About Me* section and contact me by email and/or by social