Generative Architecture with AI (SD+FLUX)

This workshop will teach you how to work with a multimodal approach: Using your model with Render tools + Stable Diffusion (SD) + FLUX + Adobe Photoshop. 

The workshop is divided into two main parts: 

First, a general overview of what is currently achievable and what could be in the near future. In this workshop, you will learn the fundamentals of prompting, word and LoRa weights, Seeds, Steps, Denoising, IPadaptors, and the use of ControlNet.  Next, you will learn an experimental ADE20K segmentation methodology that can provide architects with more control by defining a specific architectural category to include in their scene.

While this approach still has limitations—such as the fact that the category remains heavily influenced by the prompt—it proves effective for defining general objects in the scene using tools like Photoshop or Rhino.

If all this sounds too complex, don't worry, it's okay! This workshop will take the time to cover the fundamentals comprehensively, ensuring you have a strong foundation for the more advanced material to follow.

Next, on Day 2:

We will go over a modular tool called ComfyUI that allows for customizing your own workflows depending on your specific needs and intentions. You will practice using custom workflows using the basics you learned the day before. Next, We will learn Upscaling and a multimodal SDXL+Flux workflow that leverages LLM techniques to improve image precision and prompting efficiency. 

This workshop will teach you Fredy's approach to integrating generative AI into various stages of design to enhance, rather than replace, the architect's critical role in the design process. This course is aimed at architects and designers who are experimenting yet looking to take AI into their professional use.