GlazyBench: A Benchmark for Ceramic Glaze Property Prediction and Image Generation
2026-05-07 • Artificial Intelligence
Artificial IntelligenceComputer Vision and Pattern Recognition
AI summaryⓘ
The authors created GlazyBench, a large collection of over 23,000 real ceramic glaze recipes, to help AI learn how different ingredients affect the final glaze look after firing. This dataset helps AI predict glaze properties like color and transparency from the raw materials, and also generate images showing how the glaze will appear. They tested various AI methods and found promising but still difficult results. Their work provides a new tool for improving ceramic glaze design with AI and sets a standard way to measure progress.
ceramic glazeglaze formulationpost-firing propertiesmachine learninglarge language modelsimage generationmultimodal AIdeep generative modelsbenchmark dataset
Authors
Ziyu Zhai, Siyou Li, Juexi Shao, Juntao Yu
Abstract
Developing ceramic glazes is a costly, time-consuming process of trial and error due to complex chemistry, placing a significant burden on independent artists. While recent advances in multimodal AI offer a modern solution, the field lacks the large-scale datasets required to train these models. We propose GlazyBench, the first dataset for AI-assisted glaze design. Comprising 23,148 real glaze formulations, GlazyBench supports two primary tasks: predicting post-firing surface properties, such as color and transparency, from raw materials, and generating accurate visual representations of the glaze based on these properties. We establish comprehensive baselines for property prediction using traditional machine learning and large language models, alongside image generation benchmarks using deep generative and large multimodal models. Our experiments demonstrate promising yet challenging results. GlazyBench pioneers a new research direction in AI-assisted material design, providing a standardized benchmark for systematic evaluation.