DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis

CV 

A Simple and Effective Baseline for Text-to-Image Synthesis

[ECCV2022] CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer

CV 

一种通用的风格转移方法,可以实现艺术、逼真的风格迁移,以及实现视频的风格迁移,同时在训练过程中并没有视频的参与

Demystifying Neural Style Transfer

CV 

Style transfer is essentially a domain adaptation problem, which aligns the feature distributions.

基于CLIPstyler的研究过程记录

CV 

对CLIPstyler进行研究的过程记录

[CVPR2022] CLIPstyler: Image Style Transfer with a Single Text Condition

CV 

使用CLIP进行风格迁移

[arXiv] Pivotal Tuning for Latent-based Editing of Real Images

CV 

基于优化的,更新StyleGAN参数的反演方法

服务器使用文档

CV  Life 

服务器使用文档

[CVPR2022] HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing

CV 

对生成器参数进行更新的GAN Inversion