All Projects → hijkzzz → prisma

hijkzzz / prisma

Licence: other
Prisma

Programming Languages

python
139335 projects - #7 most used programming language
HTML
75241 projects

Projects that are alternatives of or similar to prisma

Face-Sketch
Face Sketch Synthesis with Style Transfer using Pyramid Column Feature, WACV2018
Stars: ✭ 52 (-26.76%)
Mutual labels:  style-transfer
Artistic-Style-Transfer-using-Keras-Tensorflow
Art to Image Style Transfer using Keras and Tensorflow.
Stars: ✭ 22 (-69.01%)
Mutual labels:  style-transfer
mix-stage
Official Repository for the paper Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach published in ECCV 2020 (https://arxiv.org/abs/2007.12553)
Stars: ✭ 22 (-69.01%)
Mutual labels:  style-transfer
StyleCLIPDraw
Styled text-to-drawing synthesis method. Featured at IJCAI 2022 and the 2021 NeurIPS Workshop on Machine Learning for Creativity and Design
Stars: ✭ 247 (+247.89%)
Mutual labels:  style-transfer
ImgFastNeuralStyleTransfer TensorFlow
快速风格迁移学习实践
Stars: ✭ 22 (-69.01%)
Mutual labels:  style-transfer
TitleStylist
Source code for our "TitleStylist" paper at ACL 2020
Stars: ✭ 72 (+1.41%)
Mutual labels:  style-transfer
Joint-Bilateral-Learning
An unofficial implementation of Joint Bilateral Learning for Real-time Universal photorealistic Style Transfer
Stars: ✭ 52 (-26.76%)
Mutual labels:  style-transfer
PSGAN-NCNN
PSGAN running with ncnn⚡妆容迁移/仿妆⚡Imitation Makeup/Makeup Transfer⚡
Stars: ✭ 140 (+97.18%)
Mutual labels:  style-transfer
gans-2.0
Generative Adversarial Networks in TensorFlow 2.0
Stars: ✭ 76 (+7.04%)
Mutual labels:  style-transfer
Neural-Style-Transfer
Using CNN to achieve style transfer
Stars: ✭ 14 (-80.28%)
Mutual labels:  style-transfer
style swap tensorflow
tensorflow code for Fast Patch-based Style Transfer of Arbitrary Style
Stars: ✭ 42 (-40.85%)
Mutual labels:  style-transfer
StyleTransfer-PyTorch
Implementation of image style transfer in PyTorch
Stars: ✭ 18 (-74.65%)
Mutual labels:  style-transfer
Android-Tensorflow-Style-Transfer
An Android app built with an artistic style transfer neural network
Stars: ✭ 31 (-56.34%)
Mutual labels:  style-transfer
style-transfer-video-processor
This code extends the neural style transfer image processing technique to video by generating smooth transitions between several reference style images
Stars: ✭ 113 (+59.15%)
Mutual labels:  style-transfer
android tflite
GPU Accelerated TensorFlow Lite applications on Android NDK. Higher accuracy face detection, Age and gender estimation, Human pose estimation, Artistic style transfer
Stars: ✭ 105 (+47.89%)
Mutual labels:  style-transfer
Domain-Aware-Style-Transfer
Official Implementation of Domain-Aware Universal Style Transfer
Stars: ✭ 84 (+18.31%)
Mutual labels:  style-transfer
color-aware-style-transfer
Reference code for the paper CAMS: Color-Aware Multi-Style Transfer.
Stars: ✭ 36 (-49.3%)
Mutual labels:  style-transfer
barracuda-style-transfer
Companion code for the Unity Style Transfer blog post, showcasing realtime style transfer using Barracuda.
Stars: ✭ 126 (+77.46%)
Mutual labels:  style-transfer
StyleSight
Browser based 'real-time' AR 'fast' neural style transfer using tensorflowjs
Stars: ✭ 15 (-78.87%)
Mutual labels:  style-transfer
GLStyleNet
Semantic style transfer, code and data for "GLStyleNet: Exquisite Style Transfer Combining Global and Local Pyramid Features" (IET Computer Vision 2020)
Stars: ✭ 48 (-32.39%)
Mutual labels:  style-transfer

prisma

Online fast neural style transfer

Requirements

  • Python 3+
  • Tensorflow 1.1.0+
  • Scipy
  • Flask
  • Flask-Mail
  • Celery
  • Redis

Setup

  • Dependencies
pip3 install numpy pillow scipy
pip3 install flask flask-mail celery redis
pip3 install tensorflow // for cpu
  • Download Models

http://pan.baidu.com/s/1pLPSXdx

mv models/ prisma/
  • Mailbox
default_config.py

MAIL_SERVER = 'xxxxx'
MAIL_PORT = xxx
MAIL_USERNAME = 'xxxxxx'
MAIL_PASSWORD = 'xxxxxx'
  • Run Redis
default_config.py

CELERY_BROKER_URL = 'redis://localhost:6379/0'
./redis-server
  • Run Celery
celery -A server.celery worker
  • Run Flask
python server.py

Training

  • Download COCO dataset and VGG19 model

VGG19 model

COCO dataset

  • Put the model and dataset into "prisma/"
# Recommend using tensorflow of gpu version
python3 train.py --STYLE_IMAGES style-image.jpg --CONTENT_WEIGHT 1.0 --STYLE_WEIGHT 10.0 --MODEL_PATH models/newmodel.ckpt

mv models/newmodel.ckpt-done models/newmodel.ckpt

# Test
python3 eval.py --CONTENT_IMAGE content-image.jpg --MODEL_PATH models/newmodel.ckpt --OUTPUT_FOLDER generate/
  • Add to Prisma
default_config.py

MODEL_FILES = set(['newmodel.ckpt', ......])

# Put a example image ("newmodel.jpg") into "static/models_image/"

Screenshot

http://localhost:5000/

Reference

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].