Zongze Wu
@forkbabu I just upload the [Cross-domain Image Morphing codes](https://github.com/betterze/StyleAlign/blob/main/README.md#cross-domain-image-morphing).
Dear Yaseryacoob, Thank you for your interest in our work. 1. [e4e encoder](https://github.com/omertov/encoder4editing) does a better job than our encoder in terms of reconstruction. Although they use W+ space rathan...
Dear Yaseryacoob, The M.dlatents is in the first layer of S vector, which is length 512, the 2000 is number of examples. For details of the relation between S and...
It takes around 40 mins to calculate the gradient map per images. To get 1k gradient maps, I use 250 GPUs, each gpu will be assigned with 4 images. If...
Yep，it should work.
If I understand correctly, I need to blur the image first. The codes are not very easy from PIL (https://pillow.readthedocs.io/en/stable/_modules/PIL/Image.html#Image.resize).
Maybe add a flag of just downloading instance mask, since we already have the nature image. (Given class name, just download instance mask.)
We use [e4e encoder](https://github.com/omertov/encoder4editing) to invert real images into w+ space. We provide pretrained e4e models for FFHQ512, FFHQ512_dog, FFHQ512_dog_cat in [here](https://drive.google.com/drive/folders/1MqCHQ6Yx-eon-3fu1g_AGjpyAUmzH6Jy). Please clone the [e4e repo](https://github.com/omertov/encoder4editing) and download the...
@snow1929 which tensorflow version you are using? I use 1.14