by m516825

Anime Generation

132 Stars 30 Forks Last release: Not found MIT License 34 Commits 0 Releases

Available items

No Items, yet!

The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:

Conditional GAN

Conditional Generative Adversarial Networks for anime generation (AnimeGAN).

Training results dump every 500 min-batch in 25 epoch(26000th min-batch) for the following tags - blue hair blue eyes
image - gray hair green eyes
image - green hair red eyes
image - orange hair brown eyes
image - blonde hair gray eyes
image - pink hair aqua eyes

Sample training data



tensorflow 1.0

Model structure



source link
google drive link


  1. Download hw3 data from data link, place the MLDSHW3dataset/ in the same directory and unzip the in MLDSHW3dataset/
  2. Replace the tags in MLDSHW3dataset/sampletestingtext.txt to the right format.
  3. Start training !


First time use, you need to do the preprocessing

$ python3 --prepro 1
If you already have done the preprocessing
$ python3 --prepro 0


  • dcgan structure
  • use one hot encoding for condition tags


This code will automatically dump the results for the tags specified in MLDSHW3dataset/sampletestingtext.txt every dumpevery batches to the testimg/ folder.

Testing tags format

1, hair  eyes 
2, hair  eyes
3, hair  eyes
4, hair  eyes
  • Possible colors for eyes
    ['', 'yellow', 'gray', 'blue', 'brown', 'red', 'green', 'purple', 'orange',
    'black', 'aqua', 'pink', 'bicolored']
  • Possible colors for hair
    ['', 'gray', 'blue', 'brown', 'red', 'blonde', 'green', 'purple', 'orange',
    'black', 'aqua', 'pink', 'white']

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.