← Back to work

HYPERTRIANGLE · AI + 3D MATERIAL PIPELINE

HYPERTRIANGLE · AI + 3D MATERIAL PIPELINE

HYPERTRIANGLE · AI + 3D MATERIAL PIPELINE

Making Generative AI Usable for 3D Production

USE CASE 1

How the pipeline was used to produce texture for 3D artists | Nature Grass Texture

USE CASE 2

USE CASE 1

USE CASE 2

USE CASE 1

How the pipeline was used to produce texture for 3D artists | Nature Grass Texture

USE CASE 2

HYPERTRIANGLE

HYPERTRIANGLE

OVERVIEW

PROJECT SUMMARY

During my internship at Hypertriangle, I researched, designed, and developed AI-powered texture generation pipelines using ComfyUI to accelerate PBR material creation for 3D artists. My work focused on transforming fragmented AI workflows into modular production-ready tools that simplified texture generation while maintaining artist control.

During my internship at Hypertriangle, I researched, designed, and developed AI-powered texture generation pipelines using ComfyUI to accelerate PBR material creation for 3D artists. My work focused on transforming fragmented AI workflows into modular production-ready tools that simplified texture generation while maintaining artist control.

During my internship at Hypertriangle, I researched, designed, and developed AI-powered texture generation pipelines using ComfyUI to accelerate PBR material creation for 3D artists. My work focused on transforming fragmented AI workflows into modular production-ready tools that simplified texture generation while maintaining artist control.

ROLE

ROLE

R&D Project Manager, AI Developer, Technical Artist, Design Technologist

R&D Project Manager, AI Developer, Technical Artist, Design Technologist

COMPANY

COMPANY

HYPERTRIANGLE (DESIGN TEAM + EXECUTIVE)

HYPERTRIANGLE (DESIGN TEAM + EXECUTIVE)

DURATION

DURATION

8 Weeks

8 Weeks

SOFTWARE

SOFTWARE

ComfyUI • LoRA Training/ JavaScript • REST API • OpenAI API • Figma

ComfyUI • LoRA Training/ JavaScript • REST API • OpenAI API • Figma

RESPONSIBILITIES

RESPONSIBILITIES

Design Research · UX Research • AI Training • Data Collection • Interaction Design • Research Analysis • Prototyping · HCI

Design Research · UX Research • AI Training • Data Collection • Interaction Design • Research Analysis • Prototyping · HCI

RECOGNITION

RECOGNITION

Mary Gates Research Scholarship

Mary Gates Research Scholarship

COMPANY SITE —>

<-

AT A GLANCE

AT A GLANCE

RESEARCH SUMMARIZATION

RESEARCH SUMMARIZATION

ABOUT HYPERTRIANGLE

ABOUT HYPERTRIANGLE

Hypertriangle is an AI startup developing generative tools for 3D content creation. As generative AI continues transforming digital content production, one of the biggest challenges remains creating high-quality physically based rendering (PBR) textures that are seamless and ready for production. The company sought to explore how generative AI could accelerate this process while giving artists greater flexibility and reducing repetitive manual work.

Hypertriangle is an AI startup developing generative tools for 3D content creation. As generative AI continues transforming digital content production, one of the biggest challenges remains creating high-quality physically based rendering (PBR) textures that are seamless and ready for production. The company sought to explore how generative AI could accelerate this process while giving artists greater flexibility and reducing repetitive manual work.

Hypertriangle is an AI startup developing generative tools for 3D content creation. As generative AI continues transforming digital content production, one of the biggest challenges remains creating high-quality physically based rendering (PBR) textures that are seamless and ready for production. The company sought to explore how generative AI could accelerate this process while giving artists greater flexibility and reducing repetitive manual work.

Because traditional 3D production pipelines require significant time from modeling through texturing, the goal is to build a system that leverages AI to generate realistic texture data in a single workflow—applicable not only to games but also to cinematic content such as advertisements.


While AI-based texturing methods offer the advantage of generating images through simple prompt inputs, relying on a single approach can be limiting.

Because traditional 3D production pipelines require significant time from modeling through texturing, the goal is to build a system that leverages AI to generate realistic texture data in a single workflow—applicable not only to games but also to cinematic content such as advertisements.


While AI-based texturing methods offer the advantage of generating images through simple prompt inputs, relying on a single approach can be limiting.

Because traditional 3D production pipelines require significant time from modeling through texturing, the goal is to build a system that leverages AI to generate realistic texture data in a single workflow—applicable not only to games but also to cinematic content such as advertisements.


While AI-based texturing methods offer the advantage of generating images through simple prompt inputs, relying on a single approach can be limiting.

PRIMARY GOAL

PRIMARY GOAL

“How can AI translate traditional ethnic patterns into contemporary digital textures while preserving their cultural meaning and visual identity??”

“How can AI translate traditional ethnic patterns into contemporary digital textures while preserving their cultural meaning and visual identity??”

APPROACH

APPROACH

To flexibly respond to diverse production scenarios, the following multiple approaches will be explored in parallel:

  1. Generating texture images through simple text-based prompts

  2. Developing high-quality texture images using Midjourney and ComfyUI

  3. Creating textures based on real-world photographs

  4. Enhancing and adapting textures using online texture resources

To flexibly respond to diverse production scenarios, the following multiple approaches will be explored in parallel:

  1. Generating texture images through simple text-based prompts

  2. Developing high-quality texture images using Midjourney and ComfyUI

  3. Creating textures based on real-world photographs

  4. Enhancing and adapting textures using online texture resources

CONTRIBUTION

CONTRIBUTION

Research in AI tools and workflows, developed the generative design direction, and iterated on AI-generated outputs.

OUTCOME

OUTCOME

30% reduction in repetitive manual production work—by connecting generation, texture processing, material preview, and export into a single production workflow.

OUTPUT / RESULTS

USE CASES

RESEARCH

TECHNICAL RESEARCH

Experimenting emerging AI tools

Experimenting emerging AI tools

Experimenting emerging AI tools

I compared tools by the qualities that mattered in a production workflow: output quality, texture consistency, seamlessness, processing time, controllability, integration complexity, and artist usability.

I compared tools by the qualities that mattered in a production workflow: output quality, texture consistency, seamlessness, processing time, controllability, integration complexity, and artist usability.

MODELS EVALUATED

Stable Diffusion XL
ControlNet · IPAdapter
Flux · LoRA workflows
Hunyuan3D · Tripo · Trellis
Sparc AI

Stable Diffusion XL
ControlNet · IPAdapter
Flux · LoRA workflows
Hunyuan3D · Tripo · Trellis
Sparc AI

TOOLS SELECTED FOR INTEGRATION

ComfyUI custom nodes
Python + JavaScript
Three.js + WebGL
Gemini API · OpenAI API

ComfyUI custom nodes
Python + JavaScript
Three.js + WebGL
Gemini API · OpenAI API

INTEGRATION CRITERIA

Texture consistency
Seamlessness
Control + latency
Pipeline compatibility
Artist-facing clarity

Texture consistency
Seamlessness
Control + latency
Pipeline compatibility
Artist-facing clarity

KEY FINDING

Models were treated as interchangeable capabilities—not as a product strategy. The system prioritized repeatable material quality and visible controls over a single impressive output.

Models were treated as interchangeable capabilities—not as a product strategy. The system prioritized repeatable material quality and visible controls over a single impressive output.

Models were treated as interchangeable capabilities—not as a product strategy. The system prioritized repeatable material quality and visible controls over a single impressive output.

KEY FINDING

Models were treated as interchangeable capabilities—not as a product strategy. The system prioritized repeatable material quality and visible controls over a single impressive output.

Models were treated as interchangeable capabilities—not as a product strategy. The system prioritized repeatable material quality and visible controls over a single impressive output.

DEVELOPMENT

SYSTEM ARCHITECTURE

Designing the material pipeline

Designing the material pipeline

A connected workflow turned fragmented image generation and material-prep steps into a repeatable system: generate, process, preview, adjust, and export without forcing artists to reconstruct the same asset across multiple applications.

A connected workflow turned fragmented image generation and material-prep steps into a repeatable system: generate, process, preview, adjust, and export without forcing artists to reconstruct the same asset across multiple applications.

01 / INPUT

Text prompt
Reference image
Material intent

02 / AI PROCESSING

Texture generation
Seamless processing
PBR map creation

03 / WEBGL PREVIEW

Three.js geometry
Live PBR controls
Visual validation

04 / EXPORT

PNG · JPG · ORM
Normal · Roughness
GLB asset package

FINAL WORKFLOW BUILD

VIDEO OF FULL WORFKLOW BUILD

KEY FINDING

Models were treated as interchangeable capabilities—not as a product strategy. The system prioritized repeatable material quality and visible controls over a single impressive output.

VIDEO OF FULL WORFKLOW BUILD

03 / UPSCALING

Developed a Three.js material viewer to inspect generated maps on multiple geometries with real-time roughness, metalness, normal, lighting, and tiling controls.

VIDEO OF FULL WORFKLOW BUILD

01 / WORKFLOW DESIGN

Mapped material creation steps and identified where artists repeatedly moved files, rebuilt maps, and retested the same decisions.

02 / OPENAI API GENERATION

Built custom ComfyUI nodes with Python and JavaScript, tested emerging models, and connected generation stages into a repeatable artist-facing workflow.

VIDEO OF FULL WORFKLOW BUILD

01 / WORKFLOW DESIGN

Mapped material creation steps and identified where artists repeatedly moved files, rebuilt maps, and retested the same decisions.

02 / OPENAI API GENERATION

Built custom ComfyUI nodes with Python and JavaScript, tested emerging models, and connected generation stages into a repeatable artist-facing workflow.

MATERIAL DATA

Generating physically based material maps

Generating physically based material maps

A realistic digital material is not defined by one image. It is a coordinated set of maps that describe how a surface responds to light—and each map needs to remain legible, organized, and predictable when an artist changes the material.

BASE COLOR

The visible surface color without lighting assumptions.

NORMAL

Adds small-scale surface depth without additional geometry.

ROUGHNESS

Controls whether reflected light appears matte, satin, or glossy.

ORM PACKING
R: Ambient Occlusion
G: Roughness
B: Metalness

Packing three grayscale maps into RGB channels reduced texture-file clutter and prepared assets for common real-time and GLB-based delivery workflows.

VIDEO OF FULL WORFKLOW BUILD

DESIGN + DEVELOPMENT

Working across design and development

Working across design and development

01 / WORKFLOW DESIGN

Mapped material creation steps and identified where artists repeatedly moved files, rebuilt maps, and retested the same decisions.

02 / AI TOOL DEVELOPMENT

Built custom ComfyUI nodes with Python and JavaScript, tested emerging models, and connected generation stages into a repeatable artist-facing workflow.

03 / 3D VISUALIZATION

Developed a Three.js material viewer to inspect generated maps on multiple geometries with real-time roughness, metalness, normal, lighting, and tiling controls.

04 / TESTING + TRANSFER

Evaluated failure modes, refined parameters, and created Korean-language documentation for setup, node connections, errors, and export instructions.

≈30%

reduction in repetitive manual production work—by connecting generation, texture processing, material preview, and export into a single production workflow.

workflow

06 / ITERATION

What did not work at first

What did not work at first

01 — Output quality could vary substantially between models; the workflow needed visible checkpoints rather than blind automation.

02 — Removing seams could flatten texture detail, so iteration focused on preserving surface character while improving repeatability.

03 — Flat images and rendered materials did not always agree; the real-time viewer made those differences visible before export.

04 — File paths, node communication, and dependency management required the prototype to be tested as a system—not as isolated interface screens.

DESIGNING FOR
CONTINUED USE

The tool was accompanied by Korean-language documentation for installation, workflow structure, node connections, parameters, model requirements, common errors, export instructions, and example use cases. Documentation was treated as part of the product: it made the workflow legible enough to be adopted, maintained, and extended by others.

NEXT STEPS

NEXT STEPS

HYPERTRIANGLE

REFLECTION

Hypertriangle taught me to see AI as one part of a larger human workflow that must be designed, tested, and translated into tools people can actually use.

The project strengthened my interest in AI product design, human–AI interaction, creative technology, and tools that enhance rather than replace human creativity.

NEXT PROJECT

NEXT PROJECT

NEXT PROJECT

Priorio →

Priorio →

Priorio →