# Moebius：0.22B参数轻量级图像修复框架，性能媲美10B级模型

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-17 08:00
- AIHOT 分数：52
- AIHOT 链接：https://aihot.virxact.com/items/cmqkbvrcp04ubslhiazojgvcz
- 原文链接：https://arxiv.org/abs/2606.19195

## AI 摘要

Moebius是一个仅0.22B参数的轻量级图像修复框架。它通过引入Local-λ Mix Interaction（LλMI）块重构扩散主干，其中Local-λ和Interactive-λ模块将空间上下文与全局语义先验压缩为固定大小的线性矩阵，在削减参数的同时保留复杂潜在交互。配合仅在隐空间执行的自适应多粒度蒸馏策略，Moebius在自然图像和人像基准上达到了与11.9B参数模型FLUX.1-Fill-Dev相当甚至更优的生成质量，总推理速度提升超过15倍。

## 正文

While 10B-level industrial foundation models have pushed the boundaries of image inpainting, their prohibitive computational costs severely hinder practical deployment. Constructing a highly optimized task-specific specialist offers a promising solution; however, extreme structural compression inevitably triggers a severe representation bottleneck. To conquer this, we propose Moebius, a highly efficient lightweight inpainting framework. We systematically reconstruct the diffusion backbone by introducing the Local-λ Mix Interaction (LλMI) block. Comprising Local-λ and Interactive-λ modules, it elegantly summarizes spatial contexts and global semantic priors into fixed-size linear matrices, preserving complex latent interactions while drastically shedding parameters. Furthermore, to unlock the full representational capacity of this highly compact architecture, we synergistically pair it with an adaptive multi-granularity distillation strategy. Operating strictly within the latent space to avoid expensive pixel-space decoding, this strategy dynamically balances multiple gradient-based losses to achieve high-fidelity alignment. Extensive experiments across natural and portrait benchmarks demonstrate that this optimal synergy enables Moebius to rival or even surpass the generation quality of the 10B-level industrial generalist FLUX.1-Fill-Dev. Remarkably, Moebius achieves this using less than 2\% of the parameters (0.22B vs. 11.9B) while delivering a >15times acceleration in total inference time, setting a new efficiency standard for high-fidelity inpainting. Project page at https://hustvl.github.io/Moebius.