Seoul-based architectural designer Lynn Kim (LynnSquared) has shared her thoughts and experiences on AI-generated tools, especially Midjourney.
Lynn Kim has extensive experience in architecture, interiors and design in the professional world, while her AI artworks focus on realistic dreamscapes and architectural visions.
Before midday
Before Midjourney, Lynn had always been fascinated by computational design. Her curiosity was explored through an algorithmic design course using processing taught by Roland Snooks at the University of Southern California, where she received her collegiate Bachelor of Architecture degree in 2011. The course dealt with the development of algorithmic processes with multiple agents that encode architectural design decisions within computational agents that interact to create an emergent architecture. During her career in architecture, Lynn integrated parametric designs through Rhino 3D and Grasshopper.
About LynnSquared’s artistic approach
Lynn Kim’s ability to create compelling visions through AI makes her work unique and compelling, setting her apart from other AI artists. While her visions and concepts may still be futuristic and imaginative, Lynn creates AI-generated artworks and virtual environments that are more visually immersive. Her AI artworks allow viewers to visually experience beautiful places and cultures that they could never visit in person or in real life.
Her latest work explores using AI imaging technologies like Midjourney to share her imaginative vision for the future in visual immersion. Additionally, she is currently researching and exploring ways to bring her two-dimensional AI-generated visions into a three-dimensional virtual space where humans can visit their dreamscapes in the metaverse and have fully immersive experiences.
Use of midjourney and AI-generated text-to-image models
Initially, text-to-image generative models were started with the development of generative models such as Generative Adversarial Networks (GANs). Generative AI text-to-image models such as DALLE-2, Stable Diffusion, and Midjourney have garnered public attention since the summer of 2022, when the models were released to the public. Like DALLE-2 and Stable Diffusion, Midjouney uses AI and machine learning to generate images based on text prompts. While testing different models, Midjourney’s visual style is consistent with my artistic approach. Therefore, she is currently focusing on midjourney as her primary tool for her artworks.
Your prompt crafting process generally considers these components: room type, architectural style, spatial elements and shapes, time of day, location, scene details, and render style. The order of components and keywords within the prompt also determines the strength of influence, so she often examines different keywords and their placement within the prompt. It usually begins with a vision and mental image.
How Lynn works with AI to create her immersive visions?
As an architectural designer by training, Lynn Kim has gained an eye for compelling architectural design through experience. According to Lynn, as an AI artist specializing in architectural vision, it is important to understand what makes good architecture and space. Many design elements can play a large role in creating compelling architectural visuals – overall composition, building mass and proportions, materiality, camera angles, lighting, and surroundings. Understanding these basic architectural elements and visual techniques can help in designing the prompt.
According to Lynn, when using Midjourney, spending can often be messy or disproportionate, and the image produced can feel “nonsensical.” Although this style can be a chaotically beautiful representation of surrealism, it loses credibility of the feasibility of the vision when the elements are disproportionate or chaotic.
As an architectural designer, Lynn Kim is more drawn to believable and photorealistic dreamscapes, visions that convince the viewer that this is possible in the future as technology advances. However, if the visions are too realistic, they can also be boring and offer no value for inspiration of new ideas. Therefore, navigating the line between imagination and reality is crucial to create visual immersion.
Lynn is a big fan of Christopher Nolan’s films such as Inception, Interstellar and James Cameron’s Avatar. Although these films are stunning and convey out-of-this-world visions, their visual immersion makes them very compelling. Her visual techniques of realism and attention to detail make the audience feel as if the movie world is “real” and they can step right into it.
Lynn wants to achieve something similar to what these filmmakers do by creating sequences using AI work. In film, a sequence is a series of scenes that form a specific narrative unit, usually linked by a unit of space or time. A lot of my AI work is created in series where different scenes from different camera angles and depths of field are developed using AI to convey a strong narrative of vision. She takes great care to create a coherent visual language in each scene, crafting quickly and exploring many variations in midjourney.
AI x NIKE
Recently, Midjourney released the new “Remix” feature that allows users to control and edit the result of the image. Before the introduction of this feature, there was no way to edit the outputs and users had to go through endless variations to even have a chance of getting the desired result. She tried to push the limits of this “remix” function with this AI X NIKE shoe concept. This series was not an actual collaboration with the NIKE brand, but rather their exploration of how AI tools can help commercial brands.
Initially, Lynn Kim started with sculptural forms, which she later used as a basis for creating a concept. According to Lynn, once she had an image with the shapes, compositions, and colors she liked, she used the remix feature and added the text prompt with a touch of “futuristic Nike concept shoe.” The AI then had rough parameters with previously defined shapes and compositions and tried to understand the remixed prompt.
The results were impressive – you can see that the variations try to stick to the previously defined parameters and still playfully explore different shoe designs.
This process demonstrated the potential of AI as a controllable design tool that can be integrated into the design process for designers and architects and even commercial brands.
escape streak
Often referenced from The Matrix, the concept of simulated reality is another notion Lynn seeks to explore in her work. In an interview with Joe Rogan’s podcast, Elon Musk said, “If you assume any rate of improvement at all, at some point games will become indistinguishable from reality… We are most likely in a simulation.” The simulation hypothesis assumes that our entire Existence is a simulated reality, such as a computer simulation. Whether this is true or not, she is intrigued by this theory as it allows us to expand our imaginations and boundaries beyond physical reality.
Getaway Series is an AI-generated vision with a simulation hypothesis as the underlying message. This Midjourney AI-generated series aims to allow viewers to reconsider physical reality and imagine what it would be like to live in a fantastical simulated reality.
First, Lynn created a series of AI-generated images of a real luxury resort in the middle of the jungle in Bali, Indonesia. She then invests her time in refining the details of compositions and midjourney details so that the visual representation is close to photorealistic.
According to Lynn Kim, with strategic sequencing, the series is evolving to test the physical limits of buildability.
The structures are cantilevered and hover over waterfalls; One can only imagine what a spectacular experience it would be to be there in person.
overview effect
Lynn recently read about William Shatner’s journey into space and how she was overcome with sadness. Shatner describes this psychological effect, which astronauts often perceive as the “overview effect.” The university article goes on to explain: “Basically, when someone travels into space and looks at the Earth from orbit, there is an indescribable, instinctive sense of the fragility of the planet. It can change the way we look at the planet, but also other things like countries, ethnic groups and religions; it can lead to an immediate reassessment of our shared harmony and a shift in focus to all the wonderful things we have in common rather than what makes us different.”
Inspired by William Shatner’s experience, Lynn wanted to give viewers a visual representation to evoke similar emotions to what she was experiencing. Space travel is something the general public cannot experience. So, using the AI, I asked the AI to create a visual representation of Willam Shatner’s spaceflight experience.
For Lynn, the impressive thing about AI-generated imagery is that AI allows us to visually explore and expand our imaginations, even the experiences and maybe the feelings we’ve never had before.
Lynn’s thoughts on AI and its role in Architecture and the Metaverse
Artificial intelligence is likely to play a significant role in architecture and the metaverse. Lynn believes AI will be critical for architects to create more innovative designs in the physical world. It will enable architects to be more efficient, expand creativity and imagination in the design process and help advance our traditional construction technology and methodology. The Metaverse uses AI to create more immersive and realistic virtual environments that allow people to experience places and cultures they could never visit in person or in real life.
If you are curious to delve deeper into Midjourney and AI-generated tools, you can check out PAACADEMY’s workshop “Midjourney Architecture 2.0 / Studio Tim Fu”.
