TODAY'S SPECIAL  in Progress

2025 
Today’s Special is an AI-driven microsite that transforms everyday food photos into emoji-style stickers. The tool allows users to generate playful, shareable assets for messaging apps or social posts, making daily meals part of a personalized visual language. The site is built through Vibe Coding as a lightweight interactive experience.

Category


NEOGOTCHI  in Progress

2025 
NeoGotchi explores AI-assisted form generation for the Tamagochi case. Early concepts are produced through iterative studies inside the ComfyUI Creative Workflow, combined with stylistic variations to test different identities. The design is rebuilt using an AI 3D tool, refined for fabrication, and produced through 3D printing.

Category


Virtual Influencer Content Creation Pipeline

2025 
Contributed to building an AI-powered content creation pipeline for Jade & Zelda’s virtual influencer startup, transforming Chef Jade from a traditional 3D character into a scalable digital personality. Using custom FLUX LoRA model training, the workflow generated thousands of consistent, high-quality images while preserving Chef Jade’s signature style across every variation. This pipeline accelerated content production, fueling explosive growth that expanded their Instagram following from under 1,000 to over 9,000 in just two months. The same process was later scaled and applied to another character, Orion, further demonstrating its adaptability and scalability.

Creative direction: Kiki Wu
Technical Artist: Ann Yang with Production Support: Jieyi Lee

Category

AI Burger Commercial Test Case

2025
As the technical artist for RiTE Media and Undercurrent XR’s burger commercial test case, I designed custom LoRA training processes and multi-platform evaluation systems. Handling dataset curation, model training, and performance optimization, I worked across AI video generation tools, including Runway ML, Kling AI, and Google Veo 3. Before video generation, I integrated ComfyUI-based workflows for inpainting and relighting to enhance frame quality and visual consistency across datasets. This systematic approach delivered hundreds of commercial-quality assets with 30–40% approval rates while establishing reproducible workflows for future campaigns.

Creative direction: Kiki Wu
Technical Artist: Ann Yang with Production Support: Jieyi Lee

Category


Semantic Seeker —
A Dialogue between Randomness and Patterns


2024
“Semantic Seeker,” an interactive installation, explored Taiwanese residential architecture through generative design. For this project, I trained specialized models using LoRA fine-tuning with Kohya on Stable Diffusion 1.5 and developed an image generation pipeline that produced culturally accurate interior design variations. By curating datasets of authentic Taiwanese homes, the system maintained architectural integrity while generating stylistically precise outputs throughout the process.

Project Lead: Jimmy Cheng, Technical Artist: Ann Yang

Category
Gen AI, Dev
              


CONTEXTU(AI) — AI x 3D Pipeline Development


2024
In this project, I built an AI stack that transforms social media content into architectural design iterations and visualizations through custom workflow integration. 

The pipeline combined ComfyUI for image generation with 3D production workflows across Unreal Engine 5, Blender, Houdini, and Maya, leveraging fine-tuned large generative models and 3D Gaussian Splats. The result was a seamless bridge between visual storytelling and architectural visualization.

Category
Creative Workflow Integration


WOVENSCAPE
AI x 3D Machine Vision Design
2023


2024
This project focuses on AI-driven design exploration, including AI-3D generation, real-time rendering, and generative transformation. 

The process starts with a form drafted in Rhino and expanded through Gaussian Splat 3D generation to create a hybrid model, which is then brought into Unreal Engine for lighting, animation, and rendering. The rendered sequence is processed in ComfyUI with video-to-video generation to create new stylistic variations and transformed visual states. The project highlights how each tool shapes the piece as it moves from geometric construction to visualization and AI-guided reinterpretation.

Category
Creative Workflow Integration