encoder4editing
encoder4editing copied to clipboard
omertov
Official implementation of "Designing an Encoder for StyleGAN Image Manipulation" (SIGGRAPH 2021) https://arxiv.org/abs/2102.02766
Hi, I have gone through [issues](https://github.com/omertov/encoder4editing/issues/46) However, I am wondering if we can use the w+ space predicted by e4e can be analysed in any way to find the directions....
Hi authors: I have read this excellent paper recently. Thank you so much for your paper. It really helped me to understand the differences between W space and Wk space....
I'm trying to run this project on ubuntu 18.4 and getting this error while importing PSP. Can help me figure out what's going on? encoder4editing-app-1 | Traceback (most recent call...
Is it possible to fine tune your e4e_ffhq_encode.pt model and change it to another different domain? I have a dataset of babies with a stylegan2 trained. Can I resume a...
This would appear to be a repeat of [#60](https://github.com/omertov/encoder4editing/issues/60), however, deleting the output directly (or clearing it) does not fix the problem. If option --n_sample is set to any number...
Thanks for this great work! I'm trying to train e4e from scratch on the face domain (mostly the same as FFHQ, but 512x512 resolution). Now it has been trained for...
Hi! Thanks for your fantastic work! I ran into some problems when I try to resume training for car using other dataset. It is quite wierd that when I use...
 All my arguments are as follows: { "batch_size": 8, "board_interval": 50, "checkpoint_path": null, "d_reg_every": 16, "dataset_type": "ffhq_encode", "delta_norm": 2, "delta_norm_lambda": 0.0002, "encoder_type": "Encoder4Editing", "exp_dir": "./experiment", "id_lambda": 0.5, "image_interval": 100,...
 hello, i trained on e4e my own dataset and pretrained stylegan2 model,but the result looks totally different with source img,can you give me some suggestion.
