How does Conv2d transform style images into embedding vectors that can be added to self-attention

naver-ai / Visual-Style-Prompting

Official Pytorch implementation of "Visual Style Prompting with Swapping Self-Attention"

https://curryjung.github.io/VisualStylePrompt/

Apache License 2.0

407 stars 30 forks source link

Open codemakerzz opened 4 months ago

codemakerzz commented 4 months ago

How does Conv2d transform style images into embedding vectors that can be added to self-attention， I want to see where the code is located

zimenglan-sysu-512 commented 4 months ago

gph1q commented 1 month ago

Is it solved?