stylegan3
StyleGAN3-CLIP-notebooks
stylegan3 | StyleGAN3-CLIP-notebooks | |
---|---|---|
38 | 2 | |
6,176 | 200 | |
0.8% | - | |
1.1 | 0.0 | |
8 months ago | about 2 years ago | |
Python | Jupyter Notebook | |
GNU General Public License v3.0 or later | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
stylegan3
-
StyleGAN3 NvidiaLabs - The state-of-the-art in Artificial Intelligence applied to Human Face Generation.
StyleGAN3 by Nvidia Open Source Software »
-
AI's Triumph: Lifelike Human Faces through GAN Technology
StyleGAN by Nvidia (Open Source) - GitHub » StyleGAN on GitHUB
- StyleGAN by Nvidia: Revolutionizing Generative AI
-
What Photoshop Can't Do, DragGAN Can! See How! Paper Explained, Along with Additional Supplementary Video Footage
Not unless you are Nvidia Corporation: https://github.com/NVlabs/stylegan3/blob/main/LICENSE.txt
-
How to load a StyleGAN3 PKL into PyTorch?
I found the follow script but unsure of how to utilize it in this context. https://github.com/NVlabs/stylegan3/blob/main/torch_utils/persistence.py
-
Can't figure out how to link key pairs with one hot encoded binary tables in a Json file - Stylegan3/pytorch/python
full dataset.py file that I'm changing is here: https://github.com/NVlabs/stylegan3/blob/main/training/dataset.py
-
Online Football Manager face generator
The neural network on which the training was carried out - https://github.com/NVlabs/stylegan3
-
AI-generated Formidable portraits
I trained a Generative Adversarial Network stylegan2-ada model with NVIDIA’s StyleGAN3 algorithm with a RTX 3090 GPU for a few nights. This is an interpolation video of the generator model’s random-walk datapoints divided into 4 different windows. Initially I web crawled some 2000 images of any Formidable images and cropped them with nagadomi’s lbpcascade_animeface anime face detector, with a setting that I attempted to also include her assets in the image. Previously I have done by transfer-learning from Gwern’s ThisWaifuDoesNotExist, which only included heads of Emilia from Re:Zero, which was quite good. This time I wanted to see if the model can also handle having something more than just a head. Having Formidable’s chest also in the image made some angles perform pretty bad, as there are as many ways of making anatomy as there are artists. Because of this, I removed all swimsuit and party skin images, as making her features was hard enough with her default skin, making the final dataset size some 1500 images. In the end, I’m pretty satisfied with the results, but I could prune the dataset even more and crop the images more homogenously as well as try a bit different hyperparameters (most importantly gamma) and stylegan3-t. However, I want to move into trying out Stable Diffusion model, so I will wrap this project up at least for now and post this. There is a psi hyperparameter used in this video generation, that determines how “creative” the generator might be, i.e. how far from an optimal statistical distribution it can go at any given datapoint (video time in this case). With psi=0 you have almost static video, and with psi=1 wildly varying results of which half aren’t even recognizable, and some are really good. I settled for 0.65, which I think has some nice variety with a reasonable amount of bad morphs.
-
Training StyleGAN3 on anime faces.
Refer to the training configurations to choose the correct values for your hardware, config and dataset. Reducing the --batch value typically warrants increasing --gamma and/or lowering the D and G learning rates (--dlr and --glr). Think of --gamma as the “randomness” or “creativity” of the model.
-
I sure love chasing an ungodly fast VGT that has a 25 second head start on me
Heck to train StyleGAN, an AI image style transfer model, requires 1-8 GPU’s with a minimum of 12GB of VRAM to train. Using a single Tesla V100, which is about £6-10k, it still can take upwards of one minute to process 1000 256x256 images.
StyleGAN3-CLIP-notebooks
-
we have the technology - sbahj_the_movie.jpg
Actors were generated with StyleGAN3+CLIP, text was written by latent-diffusion, names were generated using this site.
-
[P] StyleGAN3 + CLIP
Since it's a work in progress, I'll also share this repo where I've been updating the notebook.
What are some alternatives?
stylegan2-ada-pytorch - StyleGAN2-ADA - Official PyTorch implementation
CLIP - CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
pixel2style2pixel - Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" (CVPR 2021) presenting the pixel2style2pixel (pSp) framework
latent-diffusion - High-Resolution Image Synthesis with Latent Diffusion Models
stylegan3-encoder - stylegan3 encoder for image inversion
NeuralTextToImage - Colabs for text prompt steered image generators
NovelAI-Colab - One-click run on Colab for all major models (NovelAI, Stable Diffusion V1.5) [Moved to: https://github.com/acheong08/Diffusion-ColabUI]
stylegan2-pytorch - Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
stylegan2-projecting-images - Projecting images to latent space with StyleGAN2.
stylegan3 - Official PyTorch implementation of StyleGAN3
Diffusion-ColabUI - Choose your diffusion models and spin up a WebUI on Colab in one click