BLOCK: An Open-Source Bi-Stage MLLM Character-to-Skin Pipeline for Minecraft
AI 摘要
BLOCK是一个开源的二阶段MLLM Minecraft皮肤生成流程,通过MLLM和FLUX.2模型实现像素级皮肤生成。
主要贡献
- 提出BLOCK开源皮肤生成流程
- 设计基于MLLM的3D预览合成阶段
- 设计基于FLUX.2的皮肤解码阶段
- 提出EvolveLoRA渐进式LoRA训练策略
方法论
使用MLLM生成Minecraft风格的3D预览,然后使用精调的FLUX.2模型将预览解码为皮肤图集,并采用EvolveLoRA进行训练。
原文摘要
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.