Can You Really Use AI for Design and Architecture? Step-by-Step Guide

Nuno Silva
19 Sept 202341:29

TLDRThe video offers a comprehensive guide on leveraging AI for design and architecture projects. It begins with the use of AI to generate images for inspiration, using platforms like Mid-journey and Chat GPT for creating specific and realistic visuals. The host then demonstrates the process of using these AI-generated images as references for 3D modeling and rendering in Lumion software. The video covers various aspects, including adjusting light settings, selecting materials, and utilizing terrain tools and object libraries. It also addresses concerns about AI replacing human jobs in design, suggesting that AI serves as a reference tool rather than a complete project generator. The host shares tips on blending images, adjusting aspect ratios, and creating detailed prompts for more precise AI outputs. The video concludes with a discussion on using Lumion for rendering, emphasizing the importance of adding simple colors before textures to ensure visual coherence and the use of effects like fog for enhanced realism. The host also recommends Microsoft's Power Toys for color picking and other utilities, and highlights the use of Lumion's new assets for creating detailed and character-rich scenes.


  • 🎨 **AI in Design and Architecture**: AI can be a game-changer for generating design and architecture inspiration through platforms like Midjourney.
  • 🚀 **Step-by-Step Method**: A step-by-step approach is used to create realistic AI-generated images that can be used as references in projects.
  • 🏡 **Image Prompts**: Specificity in image prompts, such as 'modern house in a pine forest,' can significantly influence the output of AI-generated images.
  • 🔍 **Fine-Tuning with Chat GPT**: Using Chat GPT for more precise results can refine the AI's output to align closely with the desired creative vision.
  • 📐 **3D Modeling with References**: AI-generated images can serve as references for 3D modeling, providing a starting point for architectural designs.
  • 🖼️ **Rendering in Lumion**: Techniques for rendering in Lumion software include tweaking light settings, selecting materials, and using terrain tools and object libraries.
  • 🧩 **Blending Images**: Combining multiple AI-generated images can create unique blends that offer new design perspectives.
  • 📈 **Upscaler and Variations**: Upscaling AI images provides more options for variations, such as custom zooms and extensions, which add context to the scene.
  • 🛠️ **Interior Design Applications**: AI can also be applied to interior design projects, offering detailed prompts for creating specific spaces like kitchens.
  • 🌐 **AI as a Tool, Not a Replacement**: AI is seen as a valuable tool for generating references rather than a replacement for the creative input of architects and designers.
  • ⛓️ **Adding Details in Lumion**: Details such as decals, materials, and objects from Lumion's library can add realism and character to a scene, making it more engaging and story-driven.

Q & A

  • What is the main topic of the video?

    -The main topic of the video is using AI for design and architecture, specifically how it can be used to generate images for reference in architecture and design projects.

  • What is the first tool the speaker uses to generate images?

    -The first tool the speaker uses is called 'Mid-journey', which is used to create and fine-tune images for specific design and architecture prompts.

  • How does the speaker suggest improving the specificity of the generated images?

    -The speaker suggests improving the specificity by dividing the prompt into different elements, such as the type of house, materials, architectural features, setting, and even mentioning a specific architect's style.

  • What is the role of Chat GPT in the process described?

    -Chat GPT is used for generating more precise and detailed prompts, which can then be used in Mid-journey to create more accurate and specific images.

  • How does the speaker use the generated images in 3D modeling?

    -The speaker uses the generated images as a background reference in 3D modeling software. They set up lines and dimensions based on the reference image to ensure the correct perspective and proportions in their 3D model.

  • What software does the speaker use for rendering the final images?

    -The speaker uses Lumion software for rendering the final images, where they share tips on tweaking light settings, selecting materials, and navigating the terrain tools and object library.

  • How does the speaker feel about the concern that AI might take over jobs of architects and designers?

    -The speaker expresses skepticism about AI replacing architects and designers. They view AI as a tool for generating references and getting inspiration, rather than a means to generate entire projects.

  • What is the purpose of using the 'no' command in the prompts?

    -The 'no' command followed by a dash is used to specify elements that the AI should not include in the final images. This allows for more control over the generated content.

  • How does the speaker use the 'blend' feature in Mid-journey?

    -The 'blend' feature is used to combine multiple images into one, creating a new image that is a mixture of the original inputs. This can be useful for integrating different styles or elements into a single design.

  • What is the significance of adjusting the aspect ratio of the generated images?

    -Adjusting the aspect ratio allows the speaker to change the shape of the image to better fit the desired composition or to match specific design requirements, such as a horizontal or vertical orientation.

  • How does the speaker use the 'style' setting in Mid-journey?

    -The 'style' setting is used to control the level of creativity in the generated images. A 'high' style setting allows for more creative freedom, while a 'low' style setting makes the AI adhere more closely to the specifics of the prompt.



🎨 AI in Design and Architecture: Midjourney Exploration

The speaker discusses the use of AI for generating images related to design and architecture, specifically using a tool called Midjourney. They share their experience of using AI to spark new inspiration for their projects and admit the process can be addictive. The speaker outlines a step-by-step method for creating realistic images with AI, which can be used as references in architecture and design projects. They also mention the importance of specifying elements in the AI prompt to achieve desired results and give examples of how different prompts can drastically change the output. The video promises to cover creating and refining images, using chat GPT for precision, 3D modeling with an image reference, and rendering in Lumion software.


📐 Upscaling and Customizing AI-Generated Images

The speaker talks about the process of upscaling AI-generated images and making variations to them. They demonstrate how to zoom out and extend images to add more context to the scene. The focus then shifts to interior design, specifically a kitchen, and how to refine the AI's output by adding specific details to the prompt. The speaker also discusses the limitations of AI in design, such as not being able to generate multiple views from a single prompt, and how they view AI as a tool for reference rather than a job replacement. They also touch on the settings available in Midjourney for controlling the style of the generated images.


🏡 3D Modeling and Rendering with AI References

The speaker describes how to use an AI-generated image as a reference for 3D modeling. They discuss the process of setting up lines for perspective and modeling the scene with correct dimensions based on the reference image. The speaker then imports the model into Lumion for rendering, where they adjust the environment to match the scene, including adding terrain, an ocean, and trees. They also mention the use of reflection probes for material accuracy and the importance of considering the lighting direction in the scene.


🌳 Creating a Winter Scene with Lumion

The speaker details the process of creating a winter scene in Lumion by adjusting terrain, painting the landscape, and adding leafless trees and other vegetation. They discuss the use of mass placement and randomization of properties for a more natural look. The speaker also talks about selecting the right camera angle and focal length to capture the scene as desired. They mention the use of effects like fog and color correction to enhance the scene's realism and mood.


🖌️ Adding Details and Textures to the Scene

The speaker explains how to add details and textures to a scene in Lumion. They discuss the use of various assets like trees, rocks, and vegetation to populate the scene. The speaker also talks about the importance of color picking from the reference image and applying it to materials in Lumion for consistency. They mention the use of decals to create a sense of decay and age in certain elements of the scene, which adds character and helps tell a story. The speaker also shows how to add everyday objects like cooktops, shelves, and electronic items to make the scene more realistic.


🧩 Final Touches and Creating Multiple Views

The speaker discusses the final touches to the scene, including adding chromatic aberrations, adjusting the sky, and using fog for depth. They also mention making small adjustments in Photoshop to match the style of the reference image. The speaker highlights the ability to create multiple views from the same scene, which is a task that AI currently cannot perform. They demonstrate how to change camera angles and lenses, as well as adjust lighting conditions quickly within Lumion. The video concludes with a mention of a new course dedicated to Lumion 2023 and an invitation for viewers to share how they use AI tools in their projects.




Artificial Intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions. In the video, AI is used to generate images for design and architecture projects, showcasing its potential as a creative tool in these fields.


Midjourney is an AI tool mentioned in the video that allows users to generate images based on textual prompts. It is used to create various architectural and design visuals, demonstrating how AI can assist in the creative process by providing inspiration and reference images.

💡Chat GPT

Chat GPT is an AI language model that can generate human-like text based on given prompts. In the context of the video, it is utilized to refine the prompts for Midjourney, resulting in more precise and detailed images that align closely with the user's specifications.

💡3D Modeling

3D modeling is the process of creating a three-dimensional representation of an object or environment using specialized software. The video discusses using AI-generated images as a reference for 3D modeling in architecture and design projects, highlighting the practical application of AI in professional workflows.


Lumion is a real-time 3D rendering software that architects and designers use to visualize their models with lifelike lighting, materials, and textures. The video demonstrates the use of Lumion for rendering AI-generated images, emphasizing its role in enhancing the final presentation of design projects.

💡Aspect Ratio

The aspect ratio is the proportional relationship between the width and the height of an image or screen. In the video, the creator discusses adjusting the aspect ratio of AI-generated images to fit specific design needs, such as changing from a square to a more horizontal or vertical orientation.

💡Architectural Style

Architectural style refers to the visual appearance and design elements that characterize a building or structure. The video script mentions specifying an architectural style, like works of famous architects Cesavier or Kengo Kuma, to influence the style of AI-generated images.


Photorealism is a visual art style that strives to create images that closely resemble photographs. Within the video, the term is used in relation to a plugin for Chat GPT that helps generate more detailed and realistic prompts for creating images with AI, which is crucial for design and architectural references.


Upscaling is the process of increasing the resolution of an image or video. The video mentions upscaling AI-generated images to achieve higher quality visuals that can be used for various design purposes, such as creating variations or extending the image context.

💡Interior Design

Interior design involves the arrangement and design of the inside of a building to achieve a pleasing and functional space. The video script includes an example of using AI to generate an image of a modern kitchen, illustrating how AI can be a tool for interior designers to conceptualize and plan spaces.


Decals are graphic designs or motifs that can be applied to surfaces. In the video, decals are used in Lumion to add details like rust, dirt, and peeling paint to a scene, contributing to a more realistic and character-rich environment, which is essential for storytelling in design presentations.


AI can be a game-changer for generating images for design and architecture projects.

Mid-journey is an AI tool that can create addictive and time-consuming image generation for inspiration.

The speaker developed a step-by-step method to create realistic AI-generated images for architectural and design references.

AI can be used for creating images with different aspect ratios and styles by specifying elements like materials and setting.

The importance of prompt specificity in AI image generation is emphasized for achieving desired architectural styles.

AI-generated images can be used as references but not as a complete substitute for client requests and project views.

Upscaling AI-generated images provides more options for variations and context.

Interior design projects can also benefit from AI image generation, specifying elements like kitchen style and view.

The use of 'no' in prompts can help remove unwanted elements from AI-generated images.

Settings in AI tools like Mid-journey allow for control over the level of creativity in the generated images.

Chat GPT can be used in conjunction with Mid-journey for more precise and detailed prompts.

Blending multiple images in AI tools can create unique and contextually rich scenes.

AI-generated images can be used as a background reference for 3D modeling in design software.

Lumion software can render AI-based designs with realistic lighting, materials, and terrain tools.

The video demonstrates how to use Lumion for creating a winter scene with an ocean and detailed landscape.

Power Tools from the Microsoft Store can assist with color picking and other utilities for design work.

Adding decals and details in Lumion can give a scene character and tell a story, enhancing the realism of the design.

Lumion's library provides a wide range of assets for designers to bring scenes to life with realism and detail.

The finished scene in Lumion can be further adjusted in Photoshop for style matching and other enhancements.

A new course dedicated to Lumion 2023 is available for those looking to deepen their skills in the software.