Few-Shot-Patch-Based-Training
ganspace
Few-Shot-Patch-Based-Training | ganspace | |
---|---|---|
5 | 3 | |
603 | 1,766 | |
- | - | |
1.8 | 0.0 | |
about 3 years ago | over 1 year ago | |
C++ | Jupyter Notebook | |
- | Apache License 2.0 |
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.
Few-Shot-Patch-Based-Training
-
To the people who use SD to apply different styles to videos
and here is the Code and weights: https://github.com/OndrejTexler/Few-Shot-Patch-Based-Training
-
Another CN test! Sorry for the swedish!
PS: https://github.com/OndrejTexler/Few-Shot-Patch-Based-Training in case you havent taken a look, works like wonders.
- InstructPix2Pix Video: "Turn the wave into trash"
-
A quick demonstration of how I accomplished this animation.
Then why did you limit yourself in exactly the ways I described, by using the appropriate tools meant for video? Because it looked like shit until you pulled out ebsynth, right? Try this. It'll look even better and you won't have to deal with janky manual keyframe interpolation. That's the difference the right tool makes.
-
[R] Few-Shot Patch-Based Training (Siggraph 2020) - Dr. Ondřej Texler - Link to free zoom lecture by the author in comments
Interactive Video Stylization Using Few-Shot Patch-Based Training (Siggraph 2020) Project page: https://ondrejtexler.github.io/patch-based_training/index.html Git: https://github.com/OndrejTexler/Few-Shot-Patch-Based-Training
ganspace
- Enforcing AE (and/or VAE) latent vector parameters to learn specific features?
- [P][OC] 3 years ago, we made the music video Jean-Pierre using neural style transfert, optical flow, and Deep dream. Today we release "Inbreed For Thalassa", with auto-morphing, using Generative Adversarial Network, deep-dreaming and glitchs.
- [D] Generating faces with different angles
What are some alternatives?
Deep-Exemplar-based-Video-Colorization - The source code of CVPR 2019 paper "Deep Exemplar-based Video Colorization".
GFPGAN-for-Video-SR - A colab notebook for video super resolution using GFPGAN
iSeeBetter - iSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection Networks | Python3 | PyTorch | GANs | CNNs | ResNets | RNNs | Published in Springer Journal of Computational Visual Media, September 2020, Tsinghua University Press
pixel2style2pixel - Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" (CVPR 2021) presenting the pixel2style2pixel (pSp) framework
Deep-Image-Analogy - The source code of 'Visual Attribute Transfer through Deep Image Analogy'.
ganbert-pytorch - Enhancing the BERT training with Semi-supervised Generative Adversarial Networks in Pytorch/HuggingFace
BlendGAN - Official PyTorch implementation of "BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation" (NeurIPS 2021)
ru-dalle - Generate images from texts. In Russian
pix2pixHD - Synthesizing and manipulating 2048x1024 images with conditional GANs
HugsVision - HugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision
image_edit - Demos of neural image editing
PTI - Official Implementation for "Pivotal Tuning for Latent-based editing of Real Images" (ACM TOG 2022) https://arxiv.org/abs/2106.05744