BriefGPT.xyz
May, 2022
利用扩散模型对输入噪声进行调控以进行可控图像生成
On Conditioning the Input Noise for Controlled Image Generation with Diffusion Models
HTML
PDF
Vedant Singh, Surgan Jandial, Ayush Chopra, Siddharth Ramesh, Balaji Krishnamurthy...
TL;DR
通过给扩散模型输入精制的噪声来提高其控制性，从而可以产生基于语义属性的图像。
Abstract
conditional image generation
has paved the way for several breakthroughs in
image editing
, generating
stock photos
and 3-D object generati
→