# Gemini 4 Argon and Google Antigravity: From 2D concept to 3D cathedral

## Executive summary

The video demonstrates an advanced workflow where an autonomous AI agent reconstructs a photorealistic 3D cathedral model in Blender, starting only from a flat 2D concept image. The process leverages Gemini 4 Argon and Antigravity, connecting them directly to Blender via the Model Context Protocol (MCP). The system utilizes multiple iterative agentic loops to deduce complex architectural geometry, refine details like column fluting, and set up advanced volumetric lighting.

## Key takeaways

- AI-Driven 3D Reconstruction: An AI agent can take a complex 2D architectural image and autonomously build a photorealistic 3D model (e.g., a cathedral) in Blender.
- Agentic Iterative Geometry Deduction: The process involves running 45 iterative agentic loops, allowing the model to automatically overlay comparison strips against the reference image to refine the base mesh geometry.
- Targeted Detail Refinement: After the main structure is locked, targeted micro-loops are triggered to handle specific details, such as column fluting and floor textures.
- Advanced Lighting Setup: The AI model automatically handles complex lighting elements, including volumetric fog, camera depth, and audio-reactive sunlight.

## Technical details

- Model Context Protocol (MCP): Antigravity is connected directly to Blender using the Model Context Protocol (MCP) to facilitate the transfer of image data and commands for 3D reconstruction.
- Agentic Workflow: The reconstruction is driven by an agentic loop prompt, which runs for multiple rounds (45 rounds mentioned) to iteratively build and refine the structure.
- Tools and Frameworks: The workflow utilizes Gemini 4 Argon and Antigravity, starting the process in Flow to define initial parameters (lighting, angles).

## Practical implications

- Accelerates the concept-to-visualization pipeline for architectural design, allowing build engineers to rapidly prototype complex geometry from simple 2D sketches.
- Demonstrates a new method for automating the tedious, detail-oriented tasks (like fluting and texturing) traditionally done manually in 3D software.
- Highlights the potential for AI agents to bridge the gap between conceptual design (2D) and fully realized, light-mapped technical models (3D).

## Topics

Generative AI, 3D Modeling, Architectural Visualization, Agentic Systems, Blender, Model Context Protocol, Gemini 4 Argon Blog, Antigravity Website

Source: https://www.youtube.com/watch?v=OYp5j2RihPE