Hugging Face Papers ↗ · 2026-11-13
Restoring Diversity in Distilled Image and Video Generators by Probing Activations
研究论文 Hugging Face Papers 原文语言:中文
论文摘要(作者报告,未经本站复测):Distilling diffusion models into few-step student models substantially reduces sampling latency, but induces severe diversity collapse: samples generated from different random seeds show minimal…
原文摘录
论文摘要(作者报告,未经本站复测):Distilling diffusion models into few-step student models substantially reduces sampling latency, but induces severe diversity collapse: samples generated from different random seeds show minimal…
以下是来源提供的简短摘录,完整内容请查看原文。