Style-transfer Libraries

5 Components & Libraries

Sortby

Style-transfer Libraries

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.

The algorithm transfers style from one input image (the style image) onto another input image (the content image) using CNN nets (usually VGG-16/19) and gives a composite, stylized image out which ke…

A python implementation of Deep-Image-Analogy based on pytorch.

python3 opencv3 I train a series of invert blocks which estimate the inputs given the outputs for each stage of Vgg19. The results are slightly worse than optimization-based method.

style transfer web app [FastAPI + streamlit + Docker]

pytorch-naive-video-neural-style-transfer

Create naive (no temporal loss) NST for videos with person segmentation. Just place your videos in data/, run and you get your stylized and segmented videos.

The first video of the series was created exactly using this method (I also used ReCoNet for 1 part of the video). On the left you can see typical NST output and the 2 other images on the right were …

An Implementation of Ebsynth for video stylization, and the original ebsynth for image stylization as an importable python library!

Perform things like style transfer, color transfer, inpainting, superimposition, video stylization and more! This implementation makes use of advanced physics based edge detection and RAFT optical fl…

Related tags