首次系统研究文本生成图像的高效蒸馏方法，助力快速生成高质量图像。
Few-Step Distillation for Text-to-Image Generation: A Practical Guide
- 将主流蒸馏技术统一框架，适配自由文本提示的生成任务
- 在FLUX.1-lite上实现多步蒸馏，显著提升生成速度与质量
- 提供可复现代码与预训练模型，适合工业落地应用
扩散蒸馏大幅加速了类别条件图像生成，但其在开放文本到图像（T2I）生成中的适用性尚不明确。本文首次系统研究将先进蒸馏技术应用于强性能T2I教师模型FLUX.1-lite，通过统一框架对比现有方法，识别出从离散类别标签转向自由语言提示时的关键障碍。除了深入的方法分析，我们还提供了关于输入缩放、网络结构和超参数的实用指南，并开源实现及预训练学生模型。研究结果为实际T2I应用中部署快速、高保真、资源高效的扩散生成器奠定了坚实基础。代码已发布于github.com/alibaba-damo-academy/T2I-Distill。
原文摘要 · Abstract (English)
Diffusion distillation has dramatically accelerated class-conditional image synthesis, but its applicability to open-ended text-to-image (T2I) generation is still unclear. We present the first systematic study that adapts and compares state-of-the-art distillation techniques on a strong T2I teacher model, FLUX.1-lite. By casting existing methods into a unified framework, we identify the key obstacles that arise when moving from discrete class labels to free-form language prompts. Beyond a thorough methodological analysis, we offer practical guidelines on input scaling, network architecture, and hyperparameters, accompanied by an open-source implementation and pretrained student models. Our findings establish a solid foundation for deploying fast, high-fidelity, and resource-efficient diffusion generators in real-world T2I applications. Code is available on github.com/alibaba-damo-academy/T2I-Distill.
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。