Graphisoft AI Visualizer — Interactive AI Installation

Bringing the tactile freedom of architectural sketching into the era of generative AI.

What if architects could shape an idea with their hands and watch AI transform it into an architectural vision? The AI Design Live Experience explores how generative AI can bring the tactile, experimental spirit of architectural model-making into a new creative medium. Visitors arrange wooden blocks, everyday objects, or their own items in front of a live camera and watch their compositions transform into architectural imagery. Behind the experience, Stable Diffusion generates the images while TouchDesigner orchestrates the workflow and visual effects. I collaborated with the design team on the concept, prototyping, visual direction, and refinement of the experience — tuning transitions and predefined prompts to make architectural transformations fluid, expressive, and engaging. Presented at the AIA Conference on Architecture & Design 2024 in Washington, DC, and the 20th Media Architecture Awards in Budapest, the installation invited audiences to experiment hands-on and discover new possibilities for AI-assisted architectural ideation.

Year

2024

2024

Role

Product Designer — collaborative design team of three

Product Designer — collaborative design team of three

Work type

AI Product

AI Product

Project scope

Concept Development, Interaction Design, Art Direction, Prototyping, Testing, Exhibition Preparation

Collaboration

01 — Explore the Concept

Working collaboratively with two other designers, including my mentor, I helped develop the concept for an experience that reconnects architects with the tactile, experimental nature of early-stage design. The goal was to combine the freedom of arranging simple shapes and objects with the possibilities of AI-generated architectural imagery, creating an experience accessible to both industry professionals and the general public.

02 — Connect Physical Interaction with AI

The installation used a live camera to capture visitors arranging wooden blocks, geometric shapes, boxes, cups, and other everyday objects. Their physical compositions became the starting point for AI-generated architectural imagery. As visitors changed the arrangement, the visual output evolved, creating a direct connection between physical experimentation and digital exploration.

03 — Prototype, Test & Refine

I participated in concept ideation, prototyping, iteration, and preparation of the final installation. Working closely with technical teammates, I explored the TouchDesigner workflow to find the right balance between fluid transitions and visually compelling results. I helped refine the mix of visual effects and the predefined prompts, including the underlying architectural prompt, so that short inputs such as “medieval architecture” or “futuristic cityscape” could produce rich, coherent architectural imagery.

Through internal and visitor testing, we iterated on the experience to make the transformations more engaging and the creative possibilities easier to explore.

04 — Bring the Experience to an Audience

The installation was presented at the AIA Conference on Architecture & Design 2024 in Washington, DC, and at the 20th Media Architecture Awards at Uránia in Budapest. Visitors engaged with the hands-on experience, experimented with different physical arrangements, and asked questions about how the system worked.

The project demonstrated a new way to experience AI-powered architectural visualization: not simply as a tool for generating images, but as an interactive medium for creative exploration and conversations about the future of architectural design.

← all work

Graphisoft · AIA 2024 Washington DC · Media Architecture Awards Budapest

AI Design Live Experience

Build it with your hands, and watch AI turn it into architecture.

What

An interactive installation where visitors arrange blocks and everyday objects in front of a camera, and generative AI turns the composition into architectural imagery in real time.

My part

Concept, prototyping, visual direction and refinement: tuning transitions, visual effects and the predefined prompts in TouchDesigner.

Result

Shown at the AIA Conference on Architecture & Design 2024 in Washington, DC, and the 20th Media Architecture Awards in Budapest.

Role

Designer

Team

3 designers (including my mentor), plus technical teammates

Year

2024

Scope

ConceptPrototypingInteraction designGenerative AI

01 — context

Model-making, meet generative AI

Early-stage architectural design is tactile and experimental: blocks, boxes, quick models. We wanted to bring that spirit into generative AI. I worked on the concept with two other designers, including my mentor, and with technical teammates who built the pipeline: Stable Diffusion generates the images, TouchDesigner runs the workflow and the visual effects.

Visitors arrange objects, and the AI turns them into architecture live.

02 — the problem

Make AI feel like a material, not a prompt box

The experience had to work for two very different audiences at the same time.

Architects

Industry professionals at the AIA conference, who know exactly what good architectural imagery looks like.

The public

Visitors at the Media Architecture Awards with no AI or design background, who needed to get it in seconds.

Live

Every change on the table had to show up on screen quickly, while still looking like architecture.

03 — key decisions

Hands first, prompts in the background

a

Physical objects as the input

Instead of typing, visitors arrange wooden blocks, geometric shapes, boxes, cups or their own items in front of a live camera. The composition becomes the starting point for the image, so moving one object changes the result. It brings back the experimental feel of early model-making.

typing a promptarranging objects
b

Short prompts, rich results

Visitors only had a short input, like "medieval architecture" or "futuristic cityscape". I helped refine the predefined prompts and the underlying architectural prompt behind them, so a few words were enough for rich, coherent architectural imagery.

c

Fluid, but still convincing

The images had to change smoothly as visitors moved objects, and still look good at every moment. In TouchDesigner, I worked on the balance between fluid transitions and visually compelling results, and on the mix of visual effects.

04 — process

Prototype, test, refine

1

Concept

Defined the experience with the design team: tactile input, AI output, open to anyone.

2

Prototype

First tested in ComfyUI with Lego models, then moved the workflow to TouchDesigner with the technical team for the live version.

3

Test

Internal tests, then tests with visitors.

4

Refine

Iterated on prompts, effects and transitions to make the results more engaging and the possibilities easier to explore.

An early prototype in ComfyUI: a Lego model in, an aerial view of a building out.

An early prototype in ComfyUI: a Lego model in, an aerial view of a building out.

05 — the result

Two stages, one conversation

AIA 2024

AIA Conference on Architecture & Design, Washington, DC

Media Architecture Awards

The 20th edition, at Uránia in Budapest

Visitors experimented with different arrangements and asked how the system worked. The installation showed AI-assisted visualization not just as an image generator, but as an interactive medium for creative exploration, and it started conversations about the future of architectural design.

At AIA 2024 in Washington, DC: visitors built with blocks, and the screen turned them into architecture.

At AIA 2024 in Washington, DC: visitors built with blocks, and the screen turned them into architecture.

06 — what I learned

Designing for play

The input shapes the experience

Arranging objects instead of typing made the AI something people could play with. The interface was the table.

Prompts are design material

Much of the quality came from prompts visitors never saw. Writing and tuning them was design work, not setup.

Real time is a balance

Fluid and impressive pull against each other. Finding the balance took testing with visitors, not just tuning on our own screens.

where it startedAI Visualizer The Archicad tool this installation was built on.

next: your team?

Right now

Looking for a mid-senior product design role in B2B SaaS or fintech. Available from December 2026.

© 2026 Karola Menyhárt · Budapest

Built in Framer