onion-liu/blendgan

Official PyTorch implementation of "BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation" (NeurIPS 2021)

Hi there 👋! Here is onion 🧅!

blendgan's Issues

When will you release training script?

Thank you for your great work. When will you release training script?

Requirements not specified

The readme contains information how to run the python scripts and the notebook.

• for installing the scripts: Which requirements are needed?
• hint: this Pull request is hinting to some requirements
• Hardware/pypi packages?

I ran the scripts on a laptop with 4GB GPU size.
But:

• only the generate_image_pairs is working, the other script style_transfer_folder is throwing a CUDA OutOfMemoryError.
• jupyter notebook is throwing the same CUDA error.

Thanks in advance for a short feedback.

Not good result

Hi, I use your model to run reference-guided generation. However, I give a strong 3D style reference, while the result seems to be an oil panting just like this:

Is there anything wrong with me?

About pretrained baselines

Hi, could you please provide the .pth files of your pretrained baselines (AdaIN [25], MUNIT [16], FUNIT [17], DRIT++ [18], and StarGANv2) ? I am doing some experiments and it will help me a lot, thanks!

Add Weights & Biases Image Logging

Hi @onion-liu

I am an ML Engineer at Weights & Biases and I wanted to know if you were actively reviewing PRs at the moment? We would love to make a PR to add Weights & Biases' image logging of images if you had time to review it?

We have built integrations into transformers, YOLOv5, PyTorch Lightning etc so we should be able to make a quick and clean PR that shouldn't take too much time for you to review :)

Will AAHQ dataset be released soon?

萌新求问视频分辨率的具体设置

默认设置会导致内存溢出，求问具体设置。您所说的修改115行代码，本人碍于无编程经验，所以求教要如何缩小视频分辨率。
或者如何把图片保存到指定目录

Video Example overflowing ram

I've tried locally and on colab. The ram over flows on writing of the video -- locally I have 32 GB.

I might try writing a different video implementation for you in a week or two, but maybe you'll find a fix sooner.

google colab workbook

Here is a collab workbook for you or others :

• https://colab.research.google.com/github/3dsf/BlendGAN/blob/main/BlendGAN_3dsf.ipynb

It won't display the results in the book, but should download results when cell(s) have completed running.

It is written in a way, that users should be able to change folders/files with minimal effort.

note: video example is not currently working due to system ram overflow #3

blendgan.pt/psp_encoder.pt

找不到这个文件

Requirements

hi, can you tell me the Requirements to run this project. thanks

baidu yunpan of pretrained_models

can you share the baidu yunpan of pretrained_models?
thanks

The implementation of WBM

I really like your paper!! Thank you for sharing your work.
I am a beginner in GAN and image editing and interested in your implementation of WBM module which is used to blend latent codes in two domain.
I want to ask would you like to release your code about WBM?☺
Thanks.

How to train with celebA-HQ or other datasets.

Thank you for this grateful job!
I'm interested in the generated images that were trained with real photos.
Does anyone have the way to do that?

About the style-latent D

Hi, thanks for your awesome work!

I read the BlendGAN paper, and I'm confused about the role the style-latent discriminator plays in the network. I wonder that will the results be negatively affected a lot if I remove this module away from the network.

Do you have any intuition or idea behind the design of style-latent D?

Looking forward to hearing from you! Thanks again.