PulseAugur
实时 23:01:18
English(EN) MRT: Masked Region Transformer for Layered Image Generation and Editing at Scale

MRT 模型以 200 亿参数推进分层图像生成

研究人员推出 MRT,这是一种拥有 200 亿参数的掩码区域扩散模型,专为可扩展的分层图像生成和编辑而设计。该模型在一个框架内统一了文本到图层、图像到图层和图层到图层任务,并利用选择性 token 掩码进行灵活的图层操作。MRT 还配备了溢出感知画布,以处理超出可见边界的图层,并采用扩散蒸馏实现快速的 8 步生成。 AI

影响 为分层图像生成树立了新标杆,性能超越现有商业系统,并在速度和内存方面实现了显著改进。

排序理由 该集群描述了一篇关于用于图像生成的新型 AI 模型的研究论文。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

MRT 模型以 200 亿参数推进分层图像生成

报道来源 [3]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    MRT:用于大规模分层图像生成和编辑的掩码区域 Transformer

    A 20B-parameter masked region diffusion model enables scalable multi-layer transparent image generation and editing through unified task handling and efficient canvas management.

  2. arXiv cs.CV TIER_1 English(EN) · Zhicong Tang, Zhao Zhang, Jingye Chen, Mohan Zhou, Yifan Pu, Yuchi Liu, Yalong Bai, Ethan Smith, Yuhui Yuan ·

    MRT:用于大规模分层图像生成和编辑的掩码区域Transformer

    arXiv:2605.27235v1 Announce Type: new Abstract: Layered image generation and editing is a fundamental capability that enables layer-wise reuse, editing, and composition of generated visual content, analogous to word-level editing in natural language. Despite its importance, this …

  3. arXiv cs.CV TIER_1 English(EN) · Yuhui Yuan ·

    MRT:用于大规模分层图像生成和编辑的掩码区域Transformer

    Layered image generation and editing is a fundamental capability that enables layer-wise reuse, editing, and composition of generated visual content, analogous to word-level editing in natural language. Despite its importance, this remains an underexplored area at scale. To addre…