# VLMaterial: Procedural Material Generation with Large Vision-Language Models Source: [VLMaterial: Procedural Material Generation with Large Vision-Language Models]() Collection index: [llms.txt]() Data updated: 2025-10-26T04:07:06.968Z Authors: Beichen Li, Rundi Wu, Armando Solar-Lezama, Changxi Zheng, Liang Shi, Bernd Bickel, Wojciech Matusik Published: 2025-01-27T00:20:48.000Z ## Abstract Procedural materials, represented as functional node graphs, are ubiquitous in computer graphics for photorealistic material appearance design. They allow users to perform intuitive and precise editing to achieve desired visual appearances. However, creating a procedural material given an input image requires professional knowledge and significant effort. In this work, we leverage the ability to convert procedural materials into standard Python programs and fine-tune a large pre-trained vision-language model (VLM) to generate such programs from input images. To enable effective fine-tuning, we also contribute an open-source procedural material dataset and propose to perform program-level augmentation by prompting another pre-trained large language model (LLM). Through extensive evaluation, we show that our method outperforms previous methods on both synthetic and real-world examples. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Unconditional Procedural Material Synthesis on CompactSBS](): Unconditional Procedural Material Synthesis; CompactSBS; KID: 14.155. - [Conditional (Inverse) Material Generation on CompactSBS](): Conditional (Inverse) Material Generation; CompactSBS; DSim: 31.348. ## Original sources and implementation [Original paper]() [PDF]()