BLOCK: An Open-Source Bi-Stage MLLM Character-to-Skin Pipeline for Minecraft
Organizations: ShanghaiTech University
Abstract
We present 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 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 skin decoding stage based on a fine-tuned FLUX.2 model that translates the preview into a skin atlas image. We further propose EvolveLoRA, a progressive LoRA curriculum (text-to-image image-to-image 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.
Figures & tables
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
Conditional Image Generation
Conditional image generation creates images guided by inputs such as text, sketches, layouts, masks, reference images, or physical measurements.
See all 160 papers