Technology Inheritance Architektonescht Design-Generatiounsinstrument vum Junming Chen

D'Wierk Technology Inheritance Architektonescht Design-Generatiounsinstrument vum Designer Junming Chen ass en héich geschätzten Gewënner vum prestigiéisen 2023 A' Design Award an Eisen an der Wettbewerbskategorie Generativt, Algorithmesch, Parametrescht a KI-ënnerstëtzt Design.

EisenGenerativ· 2023

Technology Inheritance Architektonescht Design-Generatiounsinstrument

vum Junming Chen

Client: Chen junming

A' Design Award an Eisen Gewënner an der Kategorie Generativ

45,702

Verifizéierte Präisgewënner

Präisstatus fir #150834 verifizéieren

Kuckt beim A' Design Award Pressemëtteelung Award Badge

Faarwen

Den Design

Iwwer Technology Inheritance Architektonescht Design-Generatiounsinstrument

Technology Inheritance ass en Instrument mat kënschtlecher Intelligenz, dat Design vu Gebäidefassaden generéiert. D'Instrument erstellt Gebäudeäusseren an verschiddene architektonesche Stiler op Basis vun engem Text, deen den Benotzer aginn huet. All Bild gëtt an e puer Sekonnen erstallt, an d'Design kann duerch d'Änneren vun der Textbeschreiwung ugepasst ginn. Dat System gouf entwéckelt andeems Dausende vun architektonesche Renderings gesammelt an ëmbenannt goufen, ier en existent Bildgeneratiounsmodell mat dësem neie Datesaz feinjustéiert gouf. D'Zil ass et, Ufänger dobäi ze ënnerstëtzen, en professionellen Niveau u Qualitéit z'erreechen.

D'Unerkennung

Iwwer den A' Design Award an Eisen

Technology Inheritance Architektonescht Design-Generatiounsinstrument ass e Gewënner vum A' Design Award an Eisen, enger prestigiéiser Unerkennung, déi un gutt Designe vergi gëtt, déi déi professionell an industriell Ufuerderunge erfëllen, déi vu gutt gestaltene Kreatioune erwaart ginn. Eisen-Gewënner weisen déi grouss Fäegkeet, déi héich Spezialiséierung, dat Expertewëssen an d'kreativ Kapazitéit vun hire Schëpfer. Et gëtt erwaart, datt Technology Inheritance Architektonescht Design-Generatiounsinstrument eng héich geschätzt, bewonnert a beléifte Kreatioun ass, déi praktesch an innovativ ass. Dëst mam Eisen ausgezeechent Design integréiert déi beschte Praktike vun der Industrie a huet kompetent technesch Eegeschaften, déi mat Know-how an Talent verbonne sinn. Technology Inheritance Architektonescht Design-Generatiounsinstrument gëtt fir seng Grëndlechkeet respektéiert a ass gestalt, d'Liewensqualitéit ze verbesseren an ze hëllefen, d'Welt zu enger besserer Plaz ze maachen.

Hannert dem Design

Press Kit

Credits, Teammemberen an technesch Detailer vum Designer zur Verfügung gestallt.

Eenzegaarteg Eegeschaften: This project trains an AI that professionally generates the appearance of buildings. The AI can generate buildings of different architectural styles according to the text entered by the user. The AI only takes a few seconds to generate the building's appearance, and users can recreate the design by changing the text description. That is, designers can obtain design concept proposals through AI cooperation and continuously optimize the design.
Dimensiounen & Verpackung: Generating building exteriors using a fine-tuned stable diffusion technique.
Tags: Artificial intelligence, Human-computer cooperation, Architectural appearance generation, Text generation design, Quick modification, Architectural style control
Produktiounstechnologie: The effect of using stable diffusion to produce architectural appearance could be better. The reason is that this mode needs to sufficiently understand the design skills of different designers, resulting in a messy appearance design and low quality. For this, fine-tuning the existing AI is essential. So this project reworked the data set, fine-tuned the critical stable diffusion, and made an AI to generate the specified architectural style to assist the junior designer in the design.
Design Erausfuerderung: The challenge of this design is to build a professional architectural design AI for generating high-quality and stylized designs. This project collected and marked thousands of architectural appearance renderings of dozens of well-known architects, created a data set of architectural appearance, and then handed the data set to AI for fine-tuning learning. This project builds an AI to generate a given building's exterior style.
Fuerschung: Research Background: It is difficult for beginners to design high-quality architectural appearances.
Methods: This project trained an AI to professionally generate building exteriors, which can contract with designers to complete architectural exterior designs.
Results: Using the AI trained in this project, the designer can generate an architectural appearance rendering in just a few seconds.
Insights: Using this method, the architectural appearance of a specified style can be generated and modified through text description, and the quality of the generated design is close to that of a professional designer. This method does not require manual modeling and rendering, which improves design efficiency and quality.
Inspiratioun: Most people measure the quality of a building by evaluating how it looks. Good architectural exterior design can bring attention and economic benefits. However, the exterior architectural design is complex, and the quality of architectural exteriors designed by excellent designers and beginners varies greatly. This design makes an artificial intelligence (AI) that can expertly generate building exteriors to help beginners achieve designs that approach the quality of master builders.
Projetdauer: The project has already been completed in 2023.
Operatiounsablaf: 1. Professional designers collect and mark, and screen images of outstanding designer building exteriors.
2. Use the filtered data to train an AI that specializes in generating the exterior of a given architectural style.
3. Designers use AI to design.
4. The designer inputs the design text description into the AI to specify the decoration style.
5. AI generates the interior design of the specified decoration style.
6. Modify the unsatisfactory details in the design through text description, and regenerate the design.
7. After adjusting the text description and generating it multiple times, a good design is obtained.