chainer-fast-neuralstyle

chainer-fast-neuralstyle copied to clipboard

How to train a new model?

1

In the _model_ file, It has two exampled model. How two train a new kind of model? Like **starry_night** etc?

linrio

Keep original colors?

5

Is it possible to add a flag to keep original color of the image and only transfer the style? // from jcjohnson's neural style -- Combine the Y channel of...

artnose

In **generate.py line:57** Changing ``` flow = cv2.calcOpticalFlowFarneback(img1, img2, 0.5, 3, 15, 3, 5, 1.2, 0) ``` To ``` flow = cv2.calcOpticalFlowFarneback(img1, img2, None, 0.5, 3, 15, 3, 5, 1.2,...

linrio

4K Video example !

10

Hi all ! I created two 4K videos with this repo, you can watch them here : https://www.youtube.com/watch?v=2YRVt80g2Ek and https://www.youtube.com/watch?v=i69cBYI6f-w (watch in 1080p or 4K) Thanks everyone here for theirs...

ttoinou

Here is a bug when style video

1

 Finished style video,when the video already exists. Overwrite ? [y/N] I choose 'n' . I will get nothing~Just like the image~ 

dovanchan

I have developed an iOS App based on fast neural style. It can process both image and video. And all computation is 100% on your iPhone. The App is called...

ArtlyStyles

I made an interactive playground for the neural style transfer systems. You can pick one of several style models and upload your own source image to be processed. This service...

StyleMyImage

https://github.com/luanfujun/deep-photo-styletransfer

artnose

Adds a button and code for the real-time demo.

elmarhaussmann

Same with Sound?

1

Hi all. Is it possible to make same but with sound/voice? For example make speech from 1 person be likely the other. Waiting for any kind of discussion here. Thanks!

LionisIAm