用少步文生图模型快速修复图像，效果媲美多步方法
TurboFill: Adapting Few-step Text-to-image Model for Fast Image Inpainting
- 基于少步文生图模型训练适配器，提升修复速度
- 3步对抗训练确保修复区域真实且结构一致
- 适合需要快速高质量修复的设计师和开发者
本文提出TurboFill，一种基于少步文生图扩散模型的快速图像修复方法。通过在少步蒸馏文生图模型DMD2上训练一个修复适配器，并采用创新的3步对抗训练策略，实现高保真、结构一致且视觉协调的修复结果。为评估性能，提出了两个基准：DilationBench（测试不同掩码尺寸下的表现）和HumanBench（基于人类反馈评估复杂提示下的表现）。实验表明，TurboFill在速度与质量上均优于多步BrushNet及现有少步修复方法，树立了高性能图像修复的新标准。
原文摘要 · Abstract (English)
This paper introduces TurboFill, a fast image inpainting model that enhances a few-step text-to-image diffusion model with an inpainting adapter for high-quality and efficient inpainting. While standard diffusion models generate high-quality results, they incur high computational costs. We overcome this by training an inpainting adapter on a few-step distilled text-to-image model, DMD2, using a novel 3-step adversarial training scheme to ensure realistic, structurally consistent, and visually harmonious inpainted regions. To evaluate TurboFill, we propose two benchmarks: DilationBench, which tests performance across mask sizes, and HumanBench, based on human feedback for complex prompts. Experiments show that TurboFill outperforms both multi-step BrushNet and few-step inpainting methods, setting a new benchmark for high-performance inpainting tasks. Our project page: https://liangbinxie.github.io/projects/TurboFill/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。