Technology Inheritance Aisina de Generacion de Disseny Arquitectural per Junming Chen

Lo dissènh Technology Inheritance Aisina de Generacion de Disseny Arquitectural per Junming Chen es un laureat autfo estimfo del prestigfo 2023 A' Design Award de Fèrre dins la Categoria de Competfo Generatiu.

FèrreGeneratiu· 2023

Technology Inheritance Aisina de Generacion de Disseny Arquitectural

per Junming Chen

Client : Chen junming

Laureat del A' Design Award de Fèrre dins la Categoria Generatiu

45,702

Laureat de Prèmi Verificat

Verificar l'Estat del Prèmi per #150834

Veire a A' Design Award Comunicat de premsa Insígnia del prèmi

Colors

Lo Concèpte

A prepaus de Technology Inheritance Aisina de Generacion de Disseny Arquitectural

Eiretatge Tecnologic es una aisina d'intelligéncia artificiala que genèra de disseny d'exteriors de bastiments. L'aisina crea d'aparéncias de bastiments dins d'estils arquitecturals diferents a partir de tèxte picat per l'utilizaire. Cada imatge es produsida en qualques segondas, e lo disseny pòt èsser cambiat en editant la descripcion de tèxte. Lo sistèma foguèt bastit en recampant e etiquetant de milièrs de rendudas arquitecturalas, puèi en ajustant fin un modèl de generacion d'imatges existent amb aquel nòu ensems de donadas. L'objectiu es d'ajudar los debutants a arribar a un nivèl de qualitat professionala.

La Reconoissença

A prepaus del A' Design Award de Fèrre

Technology Inheritance Aisina de Generacion de Disseny Arquitectural a ganhat la distincion A' Design Award de Fèrre, una reconeissença prestigiosa acordada a de bons designs que respondon a las exigéncias professionalas e industrialas esperadas de creacions plan concebudas. Los ganhaires del Fèrre demòstran una granda abilitat, una nauta especializacion, una comprenedura d'expèrt e la capacitat creativa de lors creators. S'espèra que Technology Inheritance Aisina de Generacion de Disseny Arquitectural siá una creacion fòrça considerada, admirada e estimada, practica e innovanta. Aqueste design ganhaire de la distincion A' Design Award de Fèrre integra las melhoras practicas del sector e a de caracteristicas tecnicas competentas ligadas a un saber-far e a un talent. Per son rigor, Technology Inheritance Aisina de Generacion de Disseny Arquitectural merita lo respècte e es destinat a aportar de melhoraments a la qualitat de la vida que ajudan a far del mond un luòc melhor.

Darrièr lo concèpte

Kit de premsa

Crèdits, membres de l'equipa e detalhs tecnics fornits pel designer.

Proprietats Unicas: 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.
Dimensions e Embalatge: Generating building exteriors using a fine-tuned stable diffusion technique.
Etiquetas: Artificial intelligence, Human-computer cooperation, Architectural appearance generation, Text generation design, Quick modification, Architectural style control
Tecnologia de Produccion: 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.
Desaffo de Dissènh: 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.
Recèrca: 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.
Inspiracion: 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.
Durada del Projècte: The project has already been completed in 2023.
Flux Operacional: 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.