0%

adaattn

While similar to ClipSTYLER, AdaAttN model gives you the opportunity to use two images to fuse their styles into one unique combination. Have fun experimenting!

Hold: 0
Required: 10,000 $wRAI
21.1k runs
Demo
Examples
Input

content
input content image

style
input style image
Hold at least 10,000 wRAI to use this model
Multi AI platform is completely free, but most models are only accessible to wRAI token holders. If you have any questions, feel free to ask in our Telegram chat
Input
style
content
Input
style
content

Readme

This repository contains the officially unofficial PyTorch re-implementation of paper:

AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer

Developers

#

Songhua Liu, Tianwei Lin, Dongliang He, Fu Li, Meiling Wang, Xin Li, Zhengxing Sun, Qian Li, Errui Ding