-
Notifications
You must be signed in to change notification settings - Fork 2.7k
Similar to Neural Style
-
A PyTorch implementation of DeepDream that allows users to quickly and easily train their own custom DeepDream models using custom image datasets.
-
dream-creator runs on Windows, Linux, and macOS, as per the installation guide.
-
A PyTorch implementation of Neural-Style, that's faster and more memory efficient than the original.
-
The same Caffemodels are used along with a similar code setup, resulting in almost identical output quality to that of Neural-Style. Additional Caffemodels and other information can be found at the neural-style-pt Wiki here.
-
neural-style-pt runs on Windows, Linux, and macOS, as per the installation guide.
-
A PyTorch implementation of the DeepDream algorithm, based on neural-style-pt.
-
neural-dream runs on Windows, Linux, and macOS, as per the installation guide.
-
Includes almost all major DeepDream features, seamless tiling, and more.
- A PyTorch implementation of htoyryla's convis project, which let's you view input images in the same way that the model views them.
-
Based on the "Deep Painterly Harmonization" research paper: https://arxiv.org/abs/1804.03189
-
Let's you seamlessly "blend" objects into existing artwork.
- A continuation of deep-photo-styletransfer's photorealistic style transfer.
Universal Style Transfer via Feature Transforms
- Similar to AdaIN and Style-swap.
-
Based on the Neural Style Transfer : A Review paper, here: https://arxiv.org/abs/1705.04058
-
Contains a summary of papers and corresponding codes related with Neural Style.
-
A versatile GAN(generative adversarial network) implementation focused on scalability and ease-of-use.
-
Uses Tensorflow and can be installed via pip.
-
Features many different GAN types, and complimentary features.
-
Based on the DreamCanvas code, which is based on the Tensorflow DeepDream tutorial code.
-
Able to generate images of any size, on both CPU, and GPU, with any hardware that supports Tensorflow. This includes running Ubuntu in a VM like VirtualBox.
martinbenson's deep-photo-styletransfer
-
A fork of luanfujun's code which removes the Matlab dependency.
-
The code is updated to match the current Neural-Style code, so that it is more memory efficient than luanfujun's code.
-
Based on the Deep Photo Style Transfer research paper, here: https://arxiv.org/abs/1703.07511
-
Photo-realistic changes to images, via special modifications to Neural-Style's code.
-
The deep-photo-styletransfer wiki can be found here
luanfujun's deep-photo-styletransfer
-
Based on the Deep Photo Style Transfer research paper, here: https://arxiv.org/abs/1703.07511
-
Photo-realistic changes to images, via special modifications to Neural-Style's code.
-
Based on the Controlling Perceptual Factors in Neural Style Transfer research paper, here: https://arxiv.org/abs/1611.07865
-
Adds Spatial Control, Color Control, and a whole bunch of other features to style transfer systems.
-
Based on Neural-Style's code, but heavily modified.
-
The paper builds on A Neural Algorithm of Artistic Style by Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge by training feedforward neural networks that apply artistic styles to images. After training, our feedforward networks can stylize images hundreds of times faster than the optimization-based method presented by Gatys et al.
-
This repository also includes an implementation of instance normalization as described in the paper Instance Normalization: The Missing Ingredient for Fast Stylization by Dmitry Ulyanov, Andrea Vedaldi, and Victor Lempitsky. This simple trick significantly improves the quality of feedforward style transfer models.
-
This is the torch implementation for the paper "Artistic style transfer for videos", based on neural-style code by Justin Johnson https://github.com/jcjohnson/neural-style .
-
It's the same as Neural-Style but with support for creating video instead of just single images.
-
code for paper "Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis".
-
Seems to work well for using real images as styles.
-
Work similar to Neural-Style in how you input your commands. Requires a style image and content image, just like Neural-Style.
- A different implementation of A Neural Algorithm of Artistic Style. A method to transfer the style of one image to the subject of another image.
- Turn your two-bit doodles into fine artworks with deep neural networks, generate seamless textures from photos, transfer style from one image to another, perform example-based upscaling, but wait... there's more! (An implementation of Semantic Style Transfer.)
- Used to create those trippy dream like images
-
crowsonkb's implementation of Google's Deepdream
-
Capable of creating high resolution images in just a matter of minutes due to tiling.
-
Tiling allows for even GPU's and CPUs with few resources, to create high res images.
crowsonkb's Style_Transfer
-
The image is divided into tiles which are processed one at a time (with one GPU). Since the tiles can be sized so as to fit into GPU memory, this allows arbitrary size images to be processed—including print size. (ex: --size 2048 --tile-size 512)
-
Images can be processed at multiple scales for speed. For instance, --size 512 1024 2048 -i 100 will run 100 iterations (the default is 200) at 512x512, then 100 at 1024x1024, then 100 more at 2048x2048.
-
Multi-GPU support (ex: --devices 0 1 2 3). Four GPUs, for instance, can process four tiles at a time.
- This is basically an implementation of this "Image Analogies" paper, In our case, we use feature maps from VGG16. The patch matching and blending is inspired by the method described in "Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis". Effects similar to that paper can be achieved by turning off the analogy loss (or leave it on!) --analogy-w=0 and turning on the B/B' content weighting via the --b-content-w parameter. Also, instead of using brute-force patch matching we use the PatchMatch algorithm to approximate the best patch matches. Brute-force matching can be re-enabled by setting --model=brute
- It's basically a Tensorflow version of Neural-Style and Artistic-Videos, combined into a single project. It shares almost all of the same features, and it has support for semantic style transfer.
- A project that trains a convolutional neural network over a dataset to repaint an novel image in the style of a given painting. This is the implementation of Neural Style Transfer from the paper A Neural Algorithm of Artistic Style in Keras 1.0.2. This is also the code for 'Build an AI Artist' on Youtube.
-
Neural net operations are handled by Caffe, while loss minimization and other miscellaneous matrix operations are performed using numpy and scipy. L-BFGS is used for minimization.
-
Can use GoogLeNet models?
Neural-Art Mini: Using SqueezeNet
iGAN: Interactive Image Generation via Generative Adversarial Networks
-
A deep learning software that easily generates images with a few brushstrokes (from UC Berkeley and Adobe CTL)
-
iGAN (aka. interactive GAN) is the author's implementation of interactive image generation interface described in: "Generative Visual Manipulation on the Natural Image Manifold" Jun-Yan Zhu, Philipp Krähenbühl, Eli Shechtman, Alexei A. Efros In European Conference on Computer Vision (ECCV) 2016
-
Realistic Photoshop with two adversarial neural networks.
titu1994's Neural-Style-Transfer
-
Implementation of Neural Style Transfer in Keras 1.1.0 (Theano backend tested, Tensorflow support present but not tested)
-
Implements the original A Neural Algorithm of Artistic Style paper in Network.py and and an improved version of the above paper Improving the Neural Algorithm of Artistic Style in INetwork.py
-
Implements Color Transfer from the paper Preserving Color in Neural Artistic Style Transfer and Masked Style Transfer from the paper Show, Divide and Neural: Weighted Style Transfer
-
Provides helper scripts to accomplish color transfer, masked color transfer and masked style transfer after the final image has been generated in color_transfer.py and mask_transfer.py scripts
-
Includes Keras scripts for Neural Doodle generation which is a re-implementation of jcjohnson's Neural-Doodle
-
Provides a Script Helper program that runs on Windows or Linux (using Mono) for easy selection of images, alteration of parameters and ensures correct syntax when executing the script.