We present , 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 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 based on a fine-tuned FLUX.2 model that translates the preview into a skin atlas image. We further propose , 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.

生成讲解博客的中文版本

生成AI智能校验的中文版本