Generative Design & AI Trends in Architecture Series: “Hybrid Collage”
Title Image: “Nostalgic Futurism 3 / 6”, created using Midjourney by Keir Regan-Alexander

Generative Design & AI Trends in Architecture Series: “Hybrid Collage”

In the third post of this series we are looking at a trend I’m calling “Hybrid Collage”.


The term ‘ideation’ always sounds made up to me, but essentially this is what these image generation platforms aim to do. “Hybrid Collage” is a term I have started to think about as describing the process of image creation using diffusion models, like Midjourney using a novel recipe of image, sketch and text prompts.

The process is akin to pinning up all the inspiration, precedent studies and icons for a project in one place above your drawing board and trying to hold them in your mind all at once while you sketch. Each is an ingredient to be plucked from the shelf and combined in new ways. The outcomes of such experiments are highly unpredictable, but that’s what makes them fun.


Hybrid Collage: An architectural material palette created by Keir Regan-Alexander within Midjourney, colours inspired by David Hockney’s “A Bigger Splash”.



When collaging ideas using diffusion models you will go down many blind alleys, but gradually you form a firm opinion about which path you wish to take and start to guide the model into an area of focus by honing your prompts. This is done by casting a wide net initially and seeing the range of responses the model sends back to you. Once you see an option that is very close to what’s in your head, you push the re-use of the same “seed code” to keep new versions closely within the same line of enquiry and this allows you to maintain consistent results that you can manage the evolution of. Further control is achieved by using negative prompting to refine the idea through the exclusion of unwanted elements.

In this method you provide the model with ideas in the form of text, image and/or hand sketch inputs and let it go to work and it will present back a range of possible options to develop further. When you find a path you like, you take it until the concept feels like it has reached a conclusion. Images can then be blended to remix the same visual concept to a new composition, or even used to train your own bespoke model with.

Initially the aesthetic potential of these tools appeared boundless and experimentation was enthusiastic but slightly random. But very engaged designers are becoming more sophisticated in their direction by combining wireframe, sketch, render, image, text; meaning they are able to exert ever more control over the final outcomes. Midjourney will react very effectively to an architectural sketch as an image prompt, understanding the overall nature of the composition. Designer Tim Fu is an early proponent of using AI Diffusion models with sketches for design work and has deployed Midjourney to great effect. His recent work “House of Future Fluidity” is less dreamlike that most of the architectural outputs from Midjourney but is definitely starting to look at home within the parametric canon and feels within touching distance of being a buildable design concept.


House of Future Fluidity by Tim Fu, created in Midjourney



Midjourney’s main competitor, Stable Diffusion produces images that are powerful, albeit slightly less alluring. However because they are an open-source platform there is a growing community of software developers building tools and models to enhance experimentation. This has allowed the use of ‘ControlNets’ and ‘In-painting’, two incredibly powerful features that give architects the ability to go straight from a hand drawn sketch to a render in real-world context, in less than an hour.


Created in 30 minutes: process for Sketch-to-render-in-context, an imaginary development in Herne Hill, by Keir Regan-Alexander using Stable Diffusion with ControlNet



Be Careful of:

A. IP infringement considerations.

This is relevant to both the dataset upon which a diffusion model is trained and upon the image prompts you decide to add to your idea input in order to generate your new imagery. For example, Adobe’s Firefly is trained on Adobe stock imagery and so licencing of any images you produce isn’t an issue provided you are paying Adobe for a licence. There is scant case law around this new phenomenon, but if you are commercialising image use and making money (in the form of fees) from utilising such models, technically you may be at risk of an infringement.

Incidentally, you can see the most popular training set of 5.8 billion images used by these AI models at HaveIBeenTrained.com and if you would like your images to be removed from the library that can be done upon request. A key thing to note here is that it’s assumed that the imagery is included by default, you have to take the active step of asking to have images removed or delisted from the training data to avoid being sampled. In the event that a claim were made, unscrambling exactly what proportion of an invention was derived directly from a particular source would be incredibly difficult and while a work might appear derivative, the percentage weighting of a single source image or design may well prove to be vanishingly small in practice — the courts will have to prove this out.

B. Addictive use.

There is a ‘slot machine’ quality to these apps and you will end up wasting time if you aren’t focused; like infinite scrolling on social media, it can become an unproductive and ultimately fruitless dopamine binge — it also goes to work incredibly fast, giving potentially engaging results within minutes. By contrast traditional design work has always taken a great deal of deliberation, effort and time to garner results, it has required endurance and patience. There is an emergent potential for apps like Midjourney to do to architectural design what TikTok has done to long form video content.

C. Believing it’s all great.

Platforms like Midjourney create very alluring imagery with great ease, but when striking imagery is abundant, this calls for a greater level of judgement from the designer. Be careful you aren’t too easily seduced by the first thing that catches your eye.

3 tools to look at:

https://www.midjourney.com/home/

https://stablediffusionweb.com/ControlNet

https://www.evolvelab.io/veras



This article was originally published in Building Design.

Principal @ Arka.Works | Consulting Director and AEC Project Partner for the AI Era


For more like this, sign up to the Arka newsletter here.

Very good summary! ?? Midjourney is an amazing tool for the ideation phase but when you already have a design you are better off with a purpose build ai visualization tool like VISOID. We encourage you to sign up for a trial!????

回复
Ronan Donohoe

Natural Capital, Property & Technology

1 年

Will you be deploying generative and/or parametric design methods at all? Slightly different angle via data science in effect rather than generative/Midjourney etc.

回复

要查看或添加评论,请登录

Keir Regan-Alexander的更多文章

  • 2025: Curiosity Becomes Strategy

    2025: Curiosity Becomes Strategy

    As we enter 2025, architectural practices are moving beyond AI experimentation toward strategic implementation. In the…

    2 条评论
  • Turns Out GenAI Is Hard

    Turns Out GenAI Is Hard

    Have you noticed how AI is often written about in two dramatically different ways? a) its a silver bullet or b) its a…

    11 条评论
  • We Need to Talk About Fees

    We Need to Talk About Fees

    AI is going to force the architecture profession to take a long hard look at the way we are currently charging for our…

    33 条评论
  • 5 Lessons from Practice

    5 Lessons from Practice

    This article was first published in the Architects Journal, AI Edition "Style Wars" When I was studying…

    5 条评论
  • Architectural Deep-Fakes in the age of automation.

    Architectural Deep-Fakes in the age of automation.

    In the summer break after graduating, I bought an absurdly heavy camera and set off with my closest…

    13 条评论
  • What do “Custom GPTs” mean for the Practice of Architecture?

    What do “Custom GPTs” mean for the Practice of Architecture?

    A new breed of chat bot is about to make Large Language Models a whole lot more useful in practice. LINK: Building…

    3 条评论
  • Generative Design Vs Generative AI: Know Your Apples

    Generative Design Vs Generative AI: Know Your Apples

    While Generative Design and Generative AI have existed for a while, it is only now that we are seeing them wrapped up…

    7 条评论
  • Generative Design & AI Trends: ‘Pre-procurement’

    Generative Design & AI Trends: ‘Pre-procurement’

    How new technology could revolutionise approaches to technical design and procurement In the fifth and final post of…

    2 条评论
  • Generative Design & AI Trends Series: “Leveraged Drafting”

    Generative Design & AI Trends Series: “Leveraged Drafting”

    In the fourth article of this series, we look at ‘Leveraged Drafting’ and how it could dramatically increase…

    5 条评论
  • Generative Design & AI Trends in Architecture Series: “Hybrid Collage”

    Generative Design & AI Trends in Architecture Series: “Hybrid Collage”

    In the third post of this series we are looking at a trend I’m calling “Hybrid Collage”. The term ‘ideation’ always…

    2 条评论

社区洞察

其他会员也浏览了