BLOCK: An Open-Source Bi-Stage MLLM Character-to-Skin Pipeline for Minecraft

Read full text
Authors: Hengquan Guo
Cited by: 0
References: 2

Abstract

We present \textbf{BLOCK}, an open-source bi-stage character-to-skin pipeline that generates pixel-perfect Minecraft skins from arbitrary character concepts. BLOCK decomposes the problem into (i) a \textbf{3D preview synthesis stage} driven by a large multimodal model (MLLM) with a carefully designed prompt-and-reference template, producing a consistent dual-panel (front/back) oblique-view Minecraft-style preview; and (ii) a \textbf{skin decoding stage} based on a fine-tuned FLUX.2 model that translates the preview into a skin atlas image. We further propose \textbf{EvolveLoRA}, a progressive LoRA curriculum (text-to-image $\rightarrow$ image-to-image $\rightarrow$ preview-to-skin) that initializes each phase from the previous adapter to improve stability and efficiency. BLOCK is released with all prompt templates and fine-tuned weights to support reproducible character-to-skin generation.

Fields of Study & Subjects

Generative Adversarial Networks and Image Synthesis 3D Shape Modeling and Analysis Multimodal Machine Learning Applications

Publication details

Journal / source
arXiv (Cornell University)
Publication date
4 March 2026
Language
EN
Document type
Preprint