style-transfer-pytorch
flownet2-pytorch
style-transfer-pytorch | flownet2-pytorch | |
---|---|---|
6 | 2 | |
468 | 3,065 | |
- | 0.7% | |
3.9 | 0.0 | |
12 months ago | 12 months ago | |
Python | Python | |
MIT License | 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.
style-transfer-pytorch
-
Windows 11 wallpaper style transfers
They're 2304p. I just used https://github.com/crowsonkb/style-transfer-pytorch locally, which takes about 10 minutes per image on my 1050ti. with 4gb of vram i can only get it to 568p, so i used https://github.com/n00mkrad/cupscale to upscale them
-
Pinwheel
The GitHub repo for the code I made this with: https://github.com/crowsonkb/style-transfer-pytorch
- starry night drip
-
Stylized Painting (made with my new high-res style transfer code)
The GitHub repo for the code I made this with: https://github.com/crowsonkb/style-transfer-pytorch
-
Stylized Bird (made with my new high-res style transfer code)
It works on Colab, but you have to install the PyTorch version for CUDA 10.1. https://github.com/crowsonkb/style-transfer-pytorch/issues/1#issuecomment-769389269
flownet2-pytorch
-
Developing an after effects plugin for deep dreaming. Here are some first renders. Took 20 mins to render 790 frames (each time). But I didn't found any way to control the Optical Flow (Check Comments)
Did you try https://github.com/NVIDIA/flownet2-pytorch ?
-
Stylized Painting (made with my new high-res style transfer code)
I find this tool great for optical flow computation: NVIDIA/flownet2-pytorch. I use it for the video style transfer. I've slightly modified it for backward computation, which is needed for that task: ryletko / flownet2-pytorch
What are some alternatives?
cupscale - Image Upscaling GUI based on ESRGAN
artistic-videos - Torch implementation for the paper "Artistic style transfer for videos"
prism - High Resolution Style Transfer in PyTorch with Color Control and Mixed Precision :art:
Neural-Tile - A better tiling script for Neural-Style
neural-style-pt - PyTorch implementation of neural style transfer algorithm
DeepDreamVideoOpticalFlow
pytorch-neural-style-transfer - Reconstruction of the original paper on neural style transfer (Gatys et al.). I've additionally included reconstruction scripts which allow you to reconstruct only the content or the style of the image - for better understanding of how NST works.
DeepDreamAnimV2 - Code is still under development
pytorch-AdaIN - Unofficial pytorch implementation of 'Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization' [Huang+, ICCV2017]