GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → MingwangLin → automatic-manga-colorization

MingwangLin / automatic-manga-colorization

Licence: MIT License
Use keras.js and cyclegan-keras to colorize manga automatically. All computation in browser. Demo is online:

Programming Languages

javascript
184084 projects - #8 most used programming language
CSS
56736 projects
GLSL
2045 projects

Labels

computer-visiondeep-learningkerasganimage-manipulationimage-generationcyclegankeras-jscyclegan-keras

Projects that are alternatives of or similar to automatic-manga-colorization

Pytorch Cyclegan And Pix2pix
Image-to-Image Translation in PyTorch
Stars: ✭ 16,477 (+82285%)
Mutual labels:  gan, image-manipulation, image-generation, cyclegan
Cyclegan
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
Stars: ✭ 10,933 (+54565%)
Mutual labels:  gan, image-manipulation, image-generation, cyclegan
Awesome-ICCV2021-Low-Level-Vision
A Collection of Papers and Codes for ICCV2021 Low Level Vision and Image Generation
Stars: ✭ 163 (+715%)
Mutual labels:  gan, image-manipulation, image-generation
Anycost Gan
[CVPR 2021] Anycost GANs for Interactive Image Synthesis and Editing
Stars: ✭ 367 (+1735%)
Mutual labels:  gan, image-manipulation, image-generation
Paddlegan
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, wav2lip, picture repair, image editing, photo2cartoon, image style transfer, and so on.
Stars: ✭ 4,987 (+24835%)
Mutual labels:  gan, image-generation, cyclegan
Distancegan
Pytorch implementation of "One-Sided Unsupervised Domain Mapping" NIPS 2017
Stars: ✭ 180 (+800%)
Mutual labels:  gan, image-manipulation, image-generation
Contrastive Unpaired Translation
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)
Stars: ✭ 822 (+4010%)
Mutual labels:  image-manipulation, image-generation, cyclegan
Pix2pix
Image-to-image translation with conditional adversarial nets
Stars: ✭ 8,765 (+43725%)
Mutual labels:  gan, image-manipulation, image-generation
Combogan
Stars: ✭ 134 (+570%)
Mutual labels:  gan, image-manipulation, cyclegan
Exprgan
Facial Expression Editing with Controllable Expression Intensity
Stars: ✭ 98 (+390%)
Mutual labels:  gan, image-manipulation, image-generation
Lggan
[CVPR 2020] Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
Stars: ✭ 97 (+385%)
Mutual labels:  gan, image-manipulation, image-generation
Focal Frequency Loss
Focal Frequency Loss for Generative Models
Stars: ✭ 141 (+605%)
Mutual labels:  gan, image-manipulation, image-generation
Oneshottranslation
Pytorch implementation of "One-Shot Unsupervised Cross Domain Translation" NIPS 2018
Stars: ✭ 135 (+575%)
Mutual labels:  gan, image-manipulation, image-generation
Tsit
[ECCV 2020 Spotlight] A Simple and Versatile Framework for Image-to-Image Translation
Stars: ✭ 141 (+605%)
Mutual labels:  gan, image-manipulation, image-generation
Cyclegan Vc2
Voice Conversion by CycleGAN (语音克隆/语音转换): CycleGAN-VC2
Stars: ✭ 158 (+690%)
Mutual labels:  gan, cyclegan
Gannotation
GANnotation (PyTorch): Landmark-guided face to face synthesis using GANs (And a triple consistency loss!)
Stars: ✭ 167 (+735%)
Mutual labels:  gan, cyclegan
Arbitrary Text To Image Papers
A collection of arbitrary text to image papers with code (constantly updating)
Stars: ✭ 196 (+880%)
Mutual labels:  gan, image-generation
Deblurgan
Image Deblurring using Generative Adversarial Networks
Stars: ✭ 2,033 (+10065%)
Mutual labels:  gan, image-manipulation
Storygan
StoryGAN: A Sequential Conditional GAN for Story Visualization
Stars: ✭ 184 (+820%)
Mutual labels:  gan, image-generation
Cyclegan Music Style Transfer
Symbolic Music Genre Transfer with CycleGAN
Stars: ✭ 201 (+905%)
Mutual labels:  gan, cyclegan
View All Similar Projects ➔

Manga Colorization In Browser [Demo-Link] [Demo-Introduction]

Ongoing web applications for automatic manga colorization with models totally run in browser.

Built based on keras.js demos, Use Keras.js to run Models in everyone's browser.

Model Training

Model is trained with my keras implementation of cycle-gan, it's based on pytorch-CycleGan (by junyanz) and tf/torch/keras/lasagne (by tjwei).

Trained model is converted to Keras.js model by keras.js Model Conversion

Demo Limits

Due to some compatibility issues of keras,js, demo has problems when run in browsers of mobile devices.

Latest Chrome desktop version or Firefox desktop version is recommended for best user experience.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].