Creative Intelligence:
AI-Powered Design Workflows
Dive into the innovative realm of AI within the architectural domain through our hands-on workshop. Designed for architects and enthusiasts alike, this session demystifies AI’s role in design processes, offering a comprehensive walkthrough of its integration into architects’ workflows.
Our workshop places special emphasis on sketch-to-render, model-to-render, and contextualizing designs within a specific site. We will also focus particularly on façade design exploration.
To empower you in your daily work, we will provide a collection of scripts, workflows, and templates that are not only ready to use but also simple to adapt. Post-workshop, you’ll find customizing these templates to fit your unique requirements to be a breeze, making your workflow both more efficient and effective.
Participants will get hands-on experience with advanced tools like Stable Diffusion and ControlNet, using the user-friendly ComfyUI interface. Those familiar with visual scripting environments like Grasshopper or Dynamo will appreciate ComfyUI’s intuitive design.
No prior experience? No worries. Our workshop is structured to cater to both beginners and seasoned professionals. We’ll guide you through the basics of creating a workflow in ComfyUI, advancing step-by-step to ensure a solid foundation and mastery over the tools and techniques.
Course Highlights
1. Integrate AI tools into your workflow.
Stay ahead of the curve by leveraging artificial intelligence and Generative AI in your architectural design workflows. AI empowers rapid iteration, visualizes alternatives, and expands creative freedom, introducing an “element of surprise” in design exploration and idea research.
2. Site-Specific Design Contextualization: Visualizing Ideas in Their Intended Environment
AI-driven rapid iteration enables swift visual assessment of design options in real-world contexts, bypassing the need for time-consuming modeling. Effortlessly analyze shadows, sightlines, and spatial dynamics.
3. Creative Clarity: Spotlighting What Truly Matters.
AI streamlines architecture by automating laborious tasks like rendering, freeing up time for architects. This shift allows professionals to focus their energy on the human-centric aspects of design, rather than on technical drawings.
Course Focus
- 1. AI Application.
- Our workshop is designed to cover a wide range of architectural projects, spanning from the intricacies of interior design to the complexities of small and large-scale architectural endeavors. You’ll gain insights into the flexible application of AI across various project sizes, ensuring a comprehensive understanding of how to leverage these tools in diverse design contexts.
- 2. • Emphasis on Façade Design Exploration
- The workshop places a strong emphasis on exploring façade design, guiding participants through the intricacies of transforming sketches and models into detailed renders. We’ll concentrate on assessing design options within the unique constraints and opportunities of specific sites and contexts.
What you will learn
- Demystifying AI Image Generation Uncover the mechanics behind AI-powered image creation.
- Mastering Stable Diffusion via ComfyUI Navigate and utilize Stable Diffusion with the intuitive ComfyUI interface.
- Crafting Text-Based Image Prompts Learn the art of generating images from textual descriptions and refine your prompting skills.
- Styling with Custom LoRA Models Explore various styles by implementing custom LoRA models in your image generation.
- Introduction to ControlNet and Its Applications Understand what ControlNet is and discover how to use it for advanced image manipulation.
- Sketch to Reality: Rendering Techniques Transform your sketches into realistic views with practical rendering techniques.
- From 3D Mass Model to Render Convert 3D mass models into detailed renders, enhancing your architectural visualization.
- Contextual Design: Sketch in Context Merge sketches with existing images using ControlNet to visualize designs in context.
Mentors
Ömer Nuray
Ömer Nuray is an architect, content creator, and founder of Design Input Studio. Through his studio, he creates content aimed at integrating new technologies such as AI into architecture and the design process. His interest in computational design and automation led him to the world of Artificial Intelligence.
As an AI Architect at Rendair AI, he is involved in developing an AI-powered architecture visualization solution. This technology aims to make high-quality visualizations more accessible for architects.
Ömer shares his expertise and journey through his online presence, reaching and inspiring architects and designers worldwide. He provides guidance on computational design, automation, and integrating AI through platforms such as his YouTube channel and social media.
In addition, he is currently pursuing a master’s degree in Architecture in Budapest. This allows him to expand his knowledge and skills in both traditional architecture and innovative technologies like AI. Overall, he aspires to continue discovering innovative ways to incorporate AI into the design process, unlocking fresh creative potential for architects.
Programme
Day 1
- Welcome and Overview of the Workshop
- Demystifying Stable Diffusion: A Simplified Explanation
- Navigating the Comfy User Interface for Stable Diffusion
- Fundamental Text-to-Image Workflow Techniques
- Personalizing Style Images with Custom LoRA Models
- Understanding ControlNet and Its Applications
- Converting Sketches into Renders Using ControlNet
Day 2
- Mastering Multiple ControlNet Models for Enhanced Accuracy
- From 3D Mass Model to Render: A Streamlined Workflow
- Image Refinement Techniques with Inpainting
- Merging Sketches and Inpainting for Contextual Design Iterations
- Upscaling and Finalizing Images for Professional Presentation
- Wrapping Up: Reflections on Key Takeaways and Future Directions
Important info
- No need to install or download anything to join this workshop. We’ll provide a running Stable Diffusion instance for everyone.
- We’ll provide sketches and drawings for the “sketch-to-render” workflow.
- You’ll get a base 3D mass view for the “3D-to-render” workflow.
- There’s a foundational Image + Sketch for the “Sketch in Context” method.
* Base materials are optional, but it’s really recommended that participants bring their own sketches and 3D mass to have different outputs to discuss among attendees.
Important Info:
- It is advisable to have active plans for the following tools: Midjourney, Prome AI, Krea AI and Runway. This tools covered have free versions, except for Midjourney.
- Basic knowledge of interior design and architecture is recommended.