Commit graph

179 commits

Author SHA1 Message Date
Shen-Chenhui
0fdc6e9935 config 2024-04-09 17:56:42 +08:00
Shen-Chenhui
a4025b0ea7 magvit v2 enc dec arc 2024-04-09 17:49:01 +08:00
Shen-Chenhui
ae6bffb8c5 restore train vae script 2024-04-09 09:34:59 +08:00
Shen-Chenhui
47b51ba07d debug 2024-04-08 16:53:18 +08:00
Shen-Chenhui
c6181ebdfd debug 2024-04-08 16:36:54 +08:00
Shen-Chenhui
fa0ca3983e debug inference code 2024-04-08 15:40:14 +08:00
Shen-Chenhui
4b27448a49 debug 2024-04-08 14:22:21 +08:00
Shen-Chenhui
ad02d28d9c debug inference running loss 2024-04-08 10:22:07 +08:00
Shen-Chenhui
88be217a13 debug 2024-04-05 16:25:32 +08:00
Shen-Chenhui
e3584b4e43 debug 2024-04-05 16:20:39 +08:00
Shen-Chenhui
9091419b28 save vae to model dir 2024-04-05 16:07:23 +08:00
Shen-Chenhui
44b8142b4f add wrapper for pretrained loading 2024-04-05 16:01:24 +08:00
Shen-Chenhui
c7506e2461 adding pretrained vae 2024-04-04 15:54:55 +08:00
Shen-Chenhui
a656421c83 debug from_pretrained in progress 2024-04-04 15:41:15 +08:00
Shen-Chenhui
d08d52ea03 config add is_vae 2024-04-04 15:23:57 +08:00
Shen-Chenhui
60eaffed4a debug 2024-04-04 15:11:42 +08:00
Shen-Chenhui
4250cfa9a2 debug 2024-04-04 15:10:11 +08:00
Shen-Chenhui
e9776584e4 allow vae not to have prompt file 2024-04-04 15:06:36 +08:00
Shen-Chenhui
9dc9afb254 add data path to inference config 2024-04-04 14:39:04 +08:00
Shen-Chenhui
dfdf8db491 add inference config
add readme
complete inference script
TODO: DEBUG inference
2024-04-04 14:11:25 +08:00
Shen-Chenhui
b6c39873ee finish discriminator arch
use einops.rearrange in vae model_utils
add get_latent_size in vae_3d
inference vae_3d WIP
2024-04-03 10:29:01 +08:00
Zheng Zangwei (Alex Zheng)
7612d22fc6 Exp/image mix (#20)
* [exp] image mixed training

* [exp] add batch info

* [exp] launch

* update num_step_per_epoch

* [feat] verify image mix training
2024-04-02 13:35:09 +08:00
Shen-Chenhui
aa733aa1d7 debug 2024-04-02 11:21:01 +08:00
Shen-Chenhui
562a966a77 debug 2024-04-01 16:14:11 +08:00
Shen-Chenhui
6bed1bdd0b working perceptual loss 2024-04-01 16:11:21 +08:00
Shen-Chenhui
6f460c1d05 debug 2024-04-01 16:06:47 +08:00
Shen-Chenhui
036b427b00 debug 2024-04-01 15:38:29 +08:00
Shen-Chenhui
996e6fb180 debug 2024-04-01 15:33:39 +08:00
Shen-Chenhui
49498b7cdb debug 2024-04-01 15:29:08 +08:00
Shen-Chenhui
85f929d126 debug 2024-04-01 15:26:16 +08:00
Shen-Chenhui
c687b700bc debug 2024-04-01 14:53:11 +08:00
Shen-Chenhui
eda89dd643 debug 2024-04-01 14:25:37 +08:00
Shen-Chenhui
dbda9e9c3a debug 2024-04-01 14:18:58 +08:00
Shen-Chenhui
3d6d499543 add perceptual loss 2024-04-01 13:57:25 +08:00
Zheng Zangwei (Alex Zheng)
f9f539f07e format and some fix (#8) 2024-03-30 13:34:19 +08:00
Shen-Chenhui
60a0a6ea8f clean up vae (rec+kl loss) 2024-03-29 10:43:33 +08:00
Shen-Chenhui
8e49c1575b debug 2024-03-29 10:38:44 +08:00
Shen-Chenhui
6cb4e83d8a debug 2024-03-29 10:31:58 +08:00
Shen-Chenhui
d1e57cbfd5 debug 2024-03-29 10:30:56 +08:00
Shen-Chenhui
b4b541756e debug 2024-03-29 10:28:57 +08:00
Shen-Chenhui
a23b800952 debug 2024-03-29 10:17:49 +08:00
Shen-Chenhui
1edc7c60ed debug 2024-03-29 10:17:09 +08:00
Shen-Chenhui
c9fac9fa2b debug 2024-03-29 10:14:37 +08:00
Shen-Chenhui
12100a2c94 debug 2024-03-29 10:12:06 +08:00
Shen-Chenhui
b185c54160 debug 2024-03-29 10:01:39 +08:00
Shen-Chenhui
1f81907ceb debug 2024-03-29 09:59:07 +08:00
Shen-Chenhui
3aa248d7cf debug 2024-03-29 09:31:43 +08:00
Shen-Chenhui
907c71bcd6 debug 2024-03-28 23:24:37 +08:00
Shen-Chenhui
1c3d6d4c4c debug 2024-03-28 23:12:36 +08:00
shenchenhui
d927619833 debug 2024-03-28 23:08:32 +08:00
shenchenhui
21296e1497 debug 2024-03-28 22:59:01 +08:00
shenchenhui
59d36321c9 debug 2024-03-28 22:58:26 +08:00
shenchenhui
6598eec0b8 debug 2024-03-28 22:53:57 +08:00
shenchenhui
356ff604c0 debug 2024-03-28 22:51:22 +08:00
shenchenhui
f1a6f7523e debug 2024-03-28 21:41:39 +08:00
shenchenhui
9d3bdcafc4 debug 2024-03-28 21:19:35 +08:00
shenchenhui
41f7b9b01e debug 2024-03-28 18:17:42 +08:00
shenchenhui
a0f9aa87c9 debug 2024-03-28 18:03:37 +08:00
shenchenhui
7f105cbdfa debug 2024-03-28 18:02:30 +08:00
shenchenhui
0aec391d80 debug 2024-03-28 17:57:38 +08:00
shenchenhui
5935c5b10b debug 2024-03-28 17:36:31 +08:00
shenchenhui
f617d40505 debug 2024-03-28 17:26:55 +08:00
shenchenhui
9b75f917ed debug 2024-03-28 17:25:46 +08:00
shenchenhui
d80ef70020 debug 2024-03-28 17:15:04 +08:00
shenchenhui
bdf8a1d144 debug 2024-03-28 17:13:16 +08:00
shenchenhui
61c7a0d029 debug 2024-03-28 17:09:37 +08:00
shenchenhui
3755547fb9 debug 2024-03-28 17:07:56 +08:00
shenchenhui
04c03eeed4 debug 2024-03-28 16:55:37 +08:00
shenchenhui
64a1e76100 debug 2024-03-28 16:46:38 +08:00
shenchenhui
b3f2dacc69 debug 2024-03-28 16:44:41 +08:00
shenchenhui
383ae23859 debug 2024-03-28 16:39:50 +08:00
shenchenhui
afff661efd debug 2024-03-28 16:22:33 +08:00
shenchenhui
8a5de06b44 remove ml_collections 2024-03-28 16:06:00 +08:00
shenchenhui
a5917c6a3e added vae3d training code 2024-03-28 15:12:20 +08:00
Zangwei Zheng
7392d2e551 [feat] multiple frames with 360p 2024-03-27 00:24:46 +08:00
Zangwei Zheng
7d27f5553e merge mask-related utils 2024-03-23 16:32:51 +08:00
Zheng Zangwei (Alex Zheng)
150cf4666a Docs/readme (#74)
* update docs

* update docs

* update docs

* update acceleration docs and fix typos
2024-03-16 21:17:16 +08:00
Zheng Zangwei (Alex Zheng)
d851a85535 format (#69) 2024-03-15 22:16:20 +08:00
xyupeng
9aab3ad343 added open_sora package (#66) 2024-03-15 22:00:46 +08:00