HairFastGAN

HairFastGAN copied to clipboard

Can you make this into an installable module

3

Hello HairFastGAN Team, First of all, thank you for your incredible work on the HairFastGAN project. It's a fascinating and valuable tool for the community. I would like to request...

skyler14

Out of CPU Memory caused by Parallel()

3

First of all, thank you again for open-sourcing such excellent work. I am trying to run **blending_train.py,** but when I reach the following section: ``` class Blending_dataset(Dataset): def __init__(self, exps,...

Wenwen717

``` (hairenv) PS E:\Python Project\HairFastGAN> pip list Package Version -------------------- ------------ addict 2.4.0 appdirs 1.4.4 build 1.2.1 CacheControl 0.14.0 certifi 2024.2.2 charset-normalizer 3.3.2 cleo 2.1.0 click 8.1.7 clip 1.0 colorama...

bhavesh-hirpara

Can you describe about the training process , how can one train this for there own dataset...?

sahilshukla3003

Regarding the latent_avg.pt weights, how should I obtain Savg?

BiiiGerrr

No one cares, right? Create an issue to express support.

1

No one cares, right? Create an issue to express support. Not sure how it will perform, will give it a try later to see if it can run.

huangguifeng

Unexpected Output – Solid Color Image

1

I successfully set up the project and loaded the models without any errors. However, the inference output is just a flat-colored image (see attached screenshot). I used the provided images...

MosbehBarhoumiRAI

Pillow 10.0.0 is throwing an error: ``` ImportError: cannot import name 'is_directory' from 'PIL._util' (/usr/local/lib/python3.11/dist-packages/PIL/_util.py) ``` You can update this line: ``` !pip install --upgrade Pillow face_alignment dill==0.2.7.1 addict fpie...

CoinCoderBuffalo

Docker image

1

I tried many times to install the project, however, I encountered many issues with ninja, c++ library, etc... Would it be possible to create a docker image for this project?

pdebuyer

Hello, it won't start, tried limiting VRAM consumption, nothing helped. What can I do? I tried to run it on an RTX 4060, Ubuntu 24.04 LTS ```python torch.cuda.OutOfMemoryError: CUDA out...

Ansveer