BriefGPT.xyz
May, 2024
面向概念驱动文本到图像生成的个性化残差
Personalized Residuals for Concept-Driven Text-to-Image Generation
HTML
PDF
Cusuh Ham, Matthew Fisher, James Hays, Nicholas Kolkin, Yuchen Liu...
TL;DR
个性化残差和局部关注引导采样，用于使用文本到图像扩散模型的高效概念驱动生成。
Abstract
We present
personalized residuals
and
localized attention-guided sampling
for efficient
concept-driven generation
using
→