1Shan AI – Aesthetic Intelligence for Visual Content
I am a co-founder of 1Shan AI, where we are developing an AI-powered platform that helps users design and retrieve custom clothing based on their aesthetic preferences. By leveraging image ranking, enhancement, and retrieval, our model personalizes the design process, making custom apparel more accessible and tailored to individual styles. We fine-tune a text-to-image generation model with reinforcement learning to ensure high-quality visuals that align with user preferences. This technology streamlines the custom fashion design process, making it easier to create unique outfits and explore new styles—whether for personal use or fashion e-commerce.
🚀 Current Progress:
- Developed a large-scale aesthetics dataset for model training.
- Built a working prototype for scoring, ranking, and retrieval.
- Exploring applications in fashion, design, and AI-generated media.
- Our vision is to define aesthetic reasoning in AI, ensuring that generated visuals meet the highest standards of beauty and personalization.
More at: 1Shan Design
About us: 1Shan
Technologies Used
- AI Foundation Model
- Machine Learning
- Vision Language Model
- Reinforcement Learning
- Website Development
Collaborator
- Ziang Gu: guziang@msu.edu
- Juyuan Huang: juyuanhuang24@gmail.com
- Feichi Cai: linuscai.feichi@gmail.com
- Zhiyuan Ren: renzhiy1@msu.edu
