danielroich / PTI

Official Implementation for "Pivotal Tuning for Latent-based editing of Real Images" (ACM TOG 2022) https://arxiv.org/abs/2106.05744

danielroich/PTI Issues

This needs updating with readme
Closed 6 months ago4
How to improve the invert image to be more similar to the input image?
Updated 6 months ago1
how to get the inversion of my custom images with the latent codes and tuned generators?
Updated 6 months ago
Can I run it on Windows？
Updated 7 months ago
insetGan+PTI?
Updated 8 months ago
inversion on whole body images
Closed 2 years ago4
May I ask how the pt file for editing attributes was obtained?
Updated 10 months ago
Failed to run 512x512 images
Updated a year ago
Custom Images - Run on full images
Updated a year ago3
Applying PTI to other non style-GAN generators
Updated a year ago
How can i get "car images " w_pivot?
Updated a year ago
run_pit: assert target.shape == (G.img_channels, G.img_resolution, G.img_resolution)
Closed a year ago3
[question] What kind of pre-processing would a model that doesn't generate faces require?
Updated a year ago1
How to take the generated model pt -> and mash it back into stylegan2-ada pkl format for use in other apps. [DRAFTED]
Updated a year ago3
checkpoint
Updated a year ago3
Effect of lpips type
Closed a year ago1
KeyError: 'FullyConnectedLayer'
Closed 3 years ago2
GPU error
Closed a year ago1
Run PTI on 256*256 images
Closed 3 years ago3
SG and SG2 issue
Closed 2 years ago2
The more smile, the more black
Updated 2 years ago5
Style Clip editing on Hyperstyle + PTI output using global directions
Updated 2 years ago1
How did you find the directions?
Updated 2 years ago1
Unexpected size of W features in generated_images = self.G.synthesis(w, noise_mode='const', force_fp32=True)
Closed 2 years ago2
opt multi image one time?
Updated 2 years ago1
The input parameters of the Generator
Updated 2 years ago1
PTI + style CLIP
Updated 2 years ago1
every image need 127M checkpoint
Closed 2 years ago
Colab Unpickling Error
Closed 3 years ago3
Is noise optimized in the first step?
Updated 2 years ago1
experiments with throwing many images at decoder (via ffmpeg)
Closed 2 years ago4
How many images have been tried at most to train together?
Closed 2 years ago3
use_locality_regularization = False?
Closed 3 years ago3
errors in colab
Closed 3 years ago2
it's any method to speed up?
Closed 3 years ago5
lpips seems broken -
Closed 3 years ago2
saving PTI latent vector w projection to npz file
Closed 3 years ago2
how to get more editing directions
Closed 3 years ago6
how to use this?
Closed 3 years ago1
RuntimeError: ./pretrained_models/e4e_ffhq_encode.pt is a zip archive (did you mean to use torch.jit.load()?)
Closed 3 years ago1
ModuleNotFoundError: No module named 'six.moves.collections_abc'
Closed 3 years ago1
Pivotal tuning for grey-scale (sketch) images
Closed 3 years ago8
Where to download the out-of-domain images?
Closed 3 years ago2
Noob - question missing something
Closed 3 years ago2
where i can get the align.data file
Closed 3 years ago1
run align_data error
Closed 3 years ago1
About the initialization of the Inversion
Closed 3 years ago2
generate random faces
Closed 3 years ago2
Why don't you use e4e in the first stage Inversion?
Closed 3 years ago3
inference on cpu
Closed 3 years ago4