Frontiers of Artificial Intelligence in Architecture pt.2
How is MVRDV Striving to Harness AI within the Design Process?
Thursday
18th April 2024 | 12:00 – 14:30 CET
Aula 201 Lingotto | Streaming on YouTube
INTRODUCTION
The lecture will delve into MVRDV as a data-driven design practice, from its historical foundations to MVRDV NEXT’s current research on AI. Fortich will unfold the current applications of image-based MVRDV AI across their various design stages; including brainstorming, reference research, conceptualization, collage design, massing, materialization, and rendering. Finally, the firm’s current innovation in AI customization will be unveiled.
BIO
Fredy Fortich is an Architect and Engineer, specializing in computational design: BIM coordination, performance-based design, generative design, and machine learning methods. He holds an MSc in Building Technology from TU Delft and a Master of Architecture from Universidad de los Andes, Bogotá. He is a Technical Architect, serving simultaneously as BIM Manager at MVRDV’s French Studio as well as AI Researcher on Diffusion Models for MVRDV NEXT.
Contacts
Architect and Engineer Fredy Fortich expressed in this seminar, through the example of a project produced by their studio MVRDV, how its goal as BIM Manager is to use BIM to achieve parametric optimization and to integrate AI to create a digital workflow. The project in fact through the BIM and its intrinsic complexity becomes like a “notebook” where each element is represented by a letter that thanks to it allows to distinguish the different characteristics. For him the use of AI at the moment is not able to replace the creative part of the design but is able to assist in some phases of the project (you must in any case have the basics of an architect before you can use it and be able to filter and “rehumanize” the results it proposes). In addition to the various applications of AI used by him and the studio, it was interesting to see the cyclic utility that has in their design process: from the digital workflow are realized projects that in turn, through their own images, allow to “instruct” the intelligence itself to create outputs more and more faithful to their style and method.
The Second lecture provided a comprehensive exploration of the intersection between AI and architecture, delving into both historical precedents and contemporary developments. It skillfully highlighted the enduring presence of AI concepts in creative fields, tracing back to pioneering work like Frederick Brooks’ experiments in generating musical sequences in the 1950s. By contextualizing the evolution of AI within architectural discourse, the speaker illuminated its longstanding relevance and the transformative potential it holds for design practices. Furthermore, the discussion on ethical considerations, labor implications, and environmental impacts offered a critical perspective on the broader implications of AI integration in architecture. The examples presented, ranging from distant readings of architectural typologies to innovative approaches in construction automation, demonstrated the diverse applications of AI in shaping architectural processes. Overall, the lecture served as an inspiring and thought-provoking examination of AI’s role in architecture, encouraging a nuanced understanding of its possibilities and challenges.
Fredy Fortich’s talk in the lecture truly captivated my attention and left me eager to learn more. Witnessing the seamless integration of NEXT (New Experimental Technologies) into the MVRDV design process was nothing short of fascinating. Throughout his lecture, Fortich delved deep into the potential applications of artificial intelligence in architectural design, offering invaluable insights into its multifaceted utility across various stages and tools. His demonstration of the software programs employed to generate AI-driven graphics was particularly enlightening. Thanks to Fortich’s presentation, I have gained a comprehensive understanding of how artificial intelligence functions and its diverse applications, especially in the realm of image creation within architecture. His candid exploration of the limitations and challenges associated with AI utilization in the design process was a thought-provoking conclusion to his talk. It served as a reminder that while technology offers immense benefits, it also presents unique complexities and considerations that must be carefully navigated.
Fredy Fortich presents us with the fascinating recent methodologies used by MVRDV studio in terms of parametric design and AI technology. According to the architect, with the new tools now it became possible to organize the city through managing data and information. Fortich discusses how AI can be applied in multiple phases of the project, from brainstorming to final design development. With his presentation it is possible to question what the limits of technology and creative design are, and if part of this role can be carried out by a computer. The architect, in this matter, argues that although AI technology can provide a wide range of possibilities, it always requires a human pilot behind it to filter its results and help it learn. Furthermore, Fortich proposes some open debates on this field. He affirms that the tool is still limited, the first issue regards the occasional lack of coherence and constructability, secondly, the sustainability problem, being the process responsible for great energy consumption, and last, the topic of copyright and creativity limit.
In Fredy Fortich’s lecture on AI in architecture, he outlined a journey of exploration and integration of AI tools into architectural workflows. He emphasized the use of stable and reliable software platforms such as Rhino and Photoshop as the base for incorporating AI techniques. For drawing desired elements, he suggested utilizing base PSD or base sketches with high denoising strength and low denoising for optimal results.
Fortich discussed various applications of AI in different architectural tasks, starting with massing studies where a stable base render is employed. For interior design, he recommended using clean renders along with Enscape channels and providing key words for generating desired outcomes.
When it comes to materials, Fortich suggested using low-quality wireframes along with text prompts to guide AI in material selection. He stressed the importance of understanding the character of an image and incorporating textual descriptions to enhance the narrative.
In the context of upscaling images, Fortich discussed custom upscaling techniques using software like SD and IPScale to achieve high-quality results. He also introduced the concept of live AI, where custom LORAs (Local Operation Reinforcement Agents) are employed for interior design tasks, similar to the approaches used by renowned firms like MVRDV. The combination of stable diffusion and custom LORAs leads to the generation of new architectural concepts.
Fortich highlighted the significance of reinforced learning through human feedback (RLHF), which involves pairing text descriptions with images to refine AI-generated designs. He advocated for the use of separate LORAs for each project, allowing for tailored AI assistance based on specific design requirements and objectives. Overall, Fortich’s lecture provided valuable insights into the integration of AI technologies into architectural practice, offering practical strategies and considerations for architects looking to leverage AI tools effectively.
Fredy Fortich, architect at dutch studio MVRDV, is in the process of exploring the possibilities and limits of the application of Artificial Intelligence on architetcural projects. The studio is currenly using experimental technologies to optimize both the speculative and applied work. AI tool is simplifying the work at every single stage of the design process but mostly in the concept development and schematic design at the moment. AI is at the moment doing work such as materialization, rendering and the studio is training it to learn how to generate work with MVRDV design. As Fortich upholds, AI is not limiting the work of the architecture profession but is a tool which can be integrated to simplify some work phases, as it happened in the past with the introduction with new technologies which are now daily used. AI’s future can be very wide and regard also phases like construction and documentation work.
Architect Fredy Fortich from MVDRV, during the lecture talks about his experience with the vast world of Artificial Intelligence, and how it can implement a project.
AI, like many other programs, is a tool that we must tame to our intentions.
Many complex projects by MVDRV has had to be done by different BIM programs in order to conceive the structure in it’s entirety, AI could be part of this process, it can be used in every step of the way, but it has to be clear that it doesn’t do the work for you, it helps.
Some of the many way artificial intelligence can be used is to upscale photos, you can give it a pattern and then ask for it to be applied to an architecture, you can applied a stile to a photo, it can be used to drawn, or you could give it a primitive collage and it would give you back a more cohesive rendering.
As MVDRV they create their own artificial intelligence program, called LoRas, teaching it architecture throughout their projects, training it to avoid copyright. For now, it is just a theorical project, it isn’t yet ready to be applied to real structure on a larger scale.
Fredy Fortich, at the end of his lecture underlined that Ai is not a perfect system, there are many shortcomings such as repeatability, consistency, coherence, constructability, sustainability and, last but not least, copyright.
To summer up, if you can’t do architecture in the traditional way you shouldn’t do it with any form of AI.
The lecture thoroughly explored the limits of architecture as it bridged the gap between the architectural practices of today and what the future will unfold. It was intriguing to know the newer paradigm of concepts of AI being like Super Pinterest, Mass generator, Image producer, Materialization, AI Rendering, Customization, custom upscaling, live custom workflows, etc. The practices and initiatives by MVRDV through MVRDV Next where they explored Parametric optimisation through computational design was thought provoking. There were a lot of resources and platforms discussed during the presentation like Plan finder, denoising tools, Confi UI, Upscaling, Lora(that Mvrdv uses), stable diffusion, etc. Over all their practice approached AI to first learn what MVRDV design feels and make it MVDRV specific, so that its free from plagiarism and the uniqueness of the studio doesn’t perish. While AI is the new normal, how far it will replace humans, is a dilemma to be resolved. It is however again emphasized that AI will not replace humans, a person knowing AI will surely replace you. So the lecture worked more like an alarm to aware us of our growing tech world to match pace with it and shine out of it.
Professor Cardoso’s lecture on the critical history and future of Generative design explored its evolution, pivotal concepts, and potential trajectories. He began with Palladian grammar, highlighting Generative design as a platform for diverse viewpoints. Referencing Ivan Sutherland’s “Sketchpad,” he advocated for utilizing computers’ capacities in design, shifting focus from mechanical tasks to creativity. Cardoso questioned if contemporary Generative design replaces conventional approaches entirely. While acknowledging decades-old technology, he emphasized recent advancements facilitating practical applications. He raised concerns about AI’s future role, questioning autonomous reference citing and ethical remixing practices. Cardoso urged grounding ideas in reality for meaningful progress. He discussed data as material, hybridity in design, and meaningful human-machine interfaces. Transitioning to construction, he introduced ReAC, revolutionizing construction processes with robotics. Emphasizing critical reflection, he addressed ethical considerations and the balance between technology and human creativity. Cardoso’s lecture highlighted the importance of understanding the limits of architecture within the context of Generative design. While technology opens new possibilities, it’s essential to recognize the constraints imposed by materiality, cultural context, and environmental sustainability. Some of the points mentioned by Professor Cardoso, that caught my attention was his statement that we should see the existing problems in their real size “There are some difficult problems we shouldn’t try to avoid or simplify, because in reality they’re difficult problems”.
In Fredy Fortich’s discussion on how MVRDV strives to integrate AI within the design process, various aspects of AI in architecture were highlighted. He started by addressing the general idea of AI in Architecture, mentioning that in scripting and generative design, input undergoes logical processes to generate an output. In contrast, Generative AI design operates with input using unknown sources, yielding an output that precisely aligns with the input’s description. Fortich then delved into the Ai uses that they experimented with, such as Super Pinterest that serves as AI reference generator, and Coceptualizer, that unifies concepts (unifier), using Midjourney. Another AI usage that he talked about was Collage-based design which involves iterative software use and is a “BACK AND FOURTH PROCES”. Moving into interior design and materialization, he talked about one of their experiments where they input different Enscape channel views with simple clear interior to Ai, asking it to generate a suitable interior design based on each of these channel views. One of the revolutionary AI tool they experimented with in my opinion, was Live AI which facilitates custom workflows and updates a live image. Another experiment that interested me was using AI on maquette images, adding life to it, by representing on it the prompts asked, realistically. Fortich’s mention of the essential role of human oversight highlights the limits of AI in architecture, reminding us of the importance of human creativity, judgment, and ethical considerations in shaping the built environment.
Eng./Architect Fortich presented the capabilities of MVRDV as an architect tool using AI. Using it and software like Grasshopper allows us to put landscapes over the other, deal easier with complicated geometry as well as giving the architects new ideas based on inputs. Example of Dutch landscapes over each other as well as the Dutch Market Hall new design that raised the number of visitors significantly were given. The new developed system makes collage-based design while refining concepts back and forth. There is also the possibility to create gradients quickly, to freeze dimensions. Using receptive we could understand what prejudices are. Changing character is also an option. Future developments could include customization using Confy UI. Loras which are mini models were introduced. those allows us to “teach” the system a new concept based on 5 billion images. DLHF allows us applying materials and store facades, for example of a valley.
Arch. Fortich presented a very enlightening lecture from a technological point of view, as he explored how artificial intelligence can help us designers in our everyday work.
However, what he emphasized throughout the lecture was that artificial intelligence does not do things for you but is a tool that can help you to have clarity of thought where it is still very abstract and make it easier for you to do your work. However, the basis is still down to you putting your hand in, based on your intentions.
You testify to this by presenting various concrete cases based on images. So it presents a problem that may be a lack of ideas or references or even something else and how you can get help or the solution through artificial intelligence.
So artificial intelligence is a great way to simplify an architect’s life and help him do his job better but it is still up to the architect to do the bulk of the work.
Architect Fortich in his lecture talks about the beginning of AI starting from history of generative design to the development of contemporary techniques in architecture. In the past some architecture researchers began to take an interest in computer and generative art based on labour of computer machine. The novelty introduced by generative architectural representation was the possibility to see visual information as computable entities and then the possibility to define visual rules. Today architectural practices are going to change because of these technologies. New systems to curate and archive data set and develop of new projects workflows are something new in architecture. In addiction to this aspect today there are a lot of public debate about some ethical and social question behind AI that remain unanswered. In architecture new future direction can be the possibility to combine the concepts of data, considered as material, hybridity, and interface to approach in a good way to AI technologies in architecture.
Nella conferenza tenuta dall’architetto Fredy-Fortich ci ha presentato i risultati dell’utilizzo delle nuove metodologie impiegate dallo studio MVRDV in termini di progettazione computazionale basata su metodi di apprendimento automatico nella programmazione informatica
Con la sua presentazione e i risultati ottenuti con l’utilizzo dell’IA l’architetto ci pone l’interrogativo su quali siano i limiti della tecnologia e del progetto creativo, e se questo ruolo possa essere svolto da un computer
Non può che esserci solo un’unica risposta :’intelligenza artificiale non renderà la figura dell’architetto obsoleta. Non importa quanto sia sofisticata, la tecnologia non potrà
mai eguagliare le capacità di un professionista nell’analizzare uno scenario e le sue problematiche, come non potrà di certo riuscire ad elaborare un progetto che prenda in considerazione le aspettative del cliente nella loro totalità.
Attualmente l’AI può offrire nuovi strumenti e tecniche per costruire in modo più efficiente ed esteticamente interessante. Ma in futuro?
I now have a thorough understanding of artificial intelligence’s many uses and how it works, particularly when it comes to creating images for architecture, all thanks to Fortich’s presentation. During his talk on AI in architecture, Fredy Fortich described a process for investigating and incorporating AI technologies into architectural workflows.
During his talk on AI in architecture, Fredy Fortich described a process for investigating and incorporating AI technologies into architectural workflows. He stressed that the foundation for using AI approaches should be the usage of dependable and stable software platforms like Photoshop and Rhino. in fact AI is a great way to make an architect’s life easier and help them do their job better, but the energy consumption and limitations of the work is a major factor, I don’t think it can take away architects’ jobs. He also showed in his discussion of AI’s numerous applications in diverse architectural jobs with massing investigations, which need a stable base render.
Still this topic is quite hard to be internalized and blurred.
Fredy Fortich discusses the origins and development of generative and Ai powered design in various fields, including music, art and architecture. Fredy Fortich explained the early use of computers in music composition, art that was created with the use of computers and architectural research, such as the Palladian Grammar project. Fredy Fortich also talks about his ethical concerns with the use of AI in architecture for example plagiarism, as AI can access a significant amount of the data available on the internet it can create products that are similar to other architects and artists.Fredy Fortich also talked about the carbon footprint of Aİ.Fredy Fortich also shared his research on using AI in architecture, and the possibility of incorporating AI technologies into architecture design. İn his lecture, Fredy Fortich suggested architects to learn more about the usage and functioning methods and histories of these tools and how we can effectively utilize them in our work.
Fredy Fortich, an architect at Dutch studio MVRDV, has led an exploration into the integration of Artificial Intelligence in architectural design. MVRDV NEXT’s research on AI, from its historical roots to current applications, will be unfolded. Fortich has shown-case how image-based MVRDV AI is utilized across various design stages, including brainstorming, conceptualization, massing, and rendering. He also unveiled the firm’s latest innovation in AI customization. MVRDV’s approach exemplifies a progressive engagement with technology, aiming to optimize both speculative and applied work. AI streamlines tasks, particularly in concept development and schematic design. The studio is training AI to generate work in alignment with MVRDV’s design ethos. Fortich emphasized that AI enhances rather than constrains architectural practice, akin to past technological advancements. Looking ahead, AI’s potential extends to construction and documentation phases, promising a transformative future for the profession.
Professor Cardoso’s lecture on Generative design explored its history, concepts, and future directions, emphasizing its role in fostering diverse viewpoints and creativity. He discussed the integration of computer capabilities in design, highlighting recent advancements while questioning the potential replacement of conventional methods. Cardoso also raised concerns about AI’s evolving role and ethical considerations, emphasizing the importance of grounding ideas in reality. Transitioning to construction, he introduced ReAC as a robotics-driven innovation. Fredy Fortich complemented these insights with MVRDV studio’s methodologies, focusing on parametric design and AI. Fortich highlighted AI’s potential in city organization and various project phases but stressed the need for human oversight. He initiated debates on coherence, sustainability, and copyright issues in AI-driven design. Both presentations underscored the complex interplay between technology and human creativity in design innovation.
The lecture by Fredy Fortich, it was super interesting for a young generation of architects, who are just meeting and getting used to artificial intelligence. It has already started to change and evolve around these new technologies but the question is of course how are we live with this, to what extend it limits ourselves? It was so real to see the actual works that are improved by a world known architecture firm, how they are and we are adopting to this. Especially the programs that we use in our daily life, we are just adopting to use the BIM systems, and now also the intergration of AI into this is beyond imagination. However the lecture was very interesting also the question and answers were also an interesting moment because in a room full of architects and designers, the first question rise is “will they take our jobs?”. The answers and interpretations from both Fortich and Llach was similar and they do think that these systems are important to integrate into our lives but are here just to help and improve the work, but definitely not take over.
Daniel Cardoso Llach’s lecture on “Frontiers of Artificial Intelligence in Architecture” takes a deep dive into the history and future trajectories of generative design methods in architecture, particularly focusing on the implications of integrating artificial intelligence and machine learning techniques into this field. The recent adoption of AI and machine learning in architecture represents a significant shift in how design processes are viewed and implemented. Cardoso Llach discussed both the potential and the pitfalls of these technologies in architectural contexts, addressing issues like creativity, authorship, and the role of the architect in an AI-driven design process. His insights helped pave the way for thoughtful integration of these technologies in architectural practices, ensuring that they enhance rather than overshadow the creative and social imperatives of architecture.
Fredy Fortich’s lecture on how MVRDV is integrating Artificial Intelligence into its architectural design processes presents an exciting overview of contemporary practices at the intersection of AI and architecture. MVRDV, known for its innovative and often unconventional architectural solutions, appears to be pushing the boundaries of how AI can be incorporated into every stage of the design process. Fortich started by discussing the history of MVRDV, emphasizing its roots as a practice that leverages data extensively to inform its design decisions. This historical perspective could provide insights into how the firm’s approach to data-driven design has evolved and set the stage for the adoption of AI. Fortich’s lecture provided a comprehensive look at how AI can not only streamline and enhance the design process but also potentially transform the way architectural practices operate, leading to innovations that were previously unimaginable.
The “Frontiers of Artificial Intelligence in Architecture” lecture by Daniel Cardoso Llach examined the development of generative design techniques in architecture, emphasizing on the implications of incorporating machine learning and artificial intelligence methods. The recent use of AI and machine learning in architecture signifies a dramatic change in the way that design processes are seen and carried out. In his discussion of these technologies’ possibilities and drawbacks in the context of architecture, Cardoso Llach touched on topics such as authorship, creativity, and the architect’s place in an AI-driven design process. His understanding of these, helps new technologies to be carefully incorporated into architectural methods, ensuring that they complement the numerous aspects of architecture than compromise on any major ones.
Fredy Fortich provided an overview of current practices at the nexus of AI and architecture, discussing how MVRDV is incorporating AI into architectural design processes. MVRDV is known for its creative and unorthodox architectural solutions and is at the forefront of applying AI in the design phase.
Fortich delved into the origins of MVRDV, emphasizing its foundation as a data-driven methodology that informs design decisions and sets the stage for the integration of AI.