1
0
Fork 0
mirror of synced 2024-07-01 20:50:29 +12:00
Commit graph

10 commits

Author SHA1 Message Date
nagadomi d818923f33 Revert anime_style_art_rgb/scale2.0x_model.t7 2016-03-27 20:20:17 +09:00
nagadomi f221febf5f Update jsons 2016-03-27 17:47:19 +09:00
nagadomi 69ded0223a Add level 3 noise reduction models 2016-03-27 17:26:10 +09:00
nagadomi 8802c8c081 Update anime_style_artanime_style_art(RGB) models 2016-03-27 17:18:25 +09:00
nagadomi aef9fd8443 Update art 2x model 2015-12-11 16:34:37 +09:00
nagadomi bcbebe5f77 Update denosing models 2015-11-12 03:44:40 +09:00
nagadomi 7856ba90c7 Update trained models 2015-11-06 10:43:05 +09:00
nagadomi 33389d5d22 update anime_style_art_rgb/noise1 and anime_style_art_rgb/noise2 2015-07-18 11:37:06 +09:00
nagadomi 2c00335f96 update anime_style_art_rgb/scale2.0x_model 2015-07-12 00:03:24 +09:00
nagadomi 5b4d692f03 add support for RGB color space reconstruction
- add new RGB model (models/anime_style_art_rgb).
- RGB model can reduce color noise.
- waifu2x uses this RGB model by default.

You can use Y model with:
$ th waifu2x.lua -model_dir models/anime_style_art -i input.png -o output.png
$ th train.lua -color y ...
2015-06-23 02:55:30 +09:00