Commit graph

280 commits

Author SHA1 Message Date
Shen-Chenhui
c59b499085 Merge branch 'vae-clean-new' of https://github.com/hpcaitech/Open-Sora-dev into vae-clean-new 2024-04-29 18:10:03 +08:00
Shen-Chenhui
c631358bbf add z nll loss 2024-04-29 18:09:42 +08:00
zhengzangw
9632b5bcf8 merged 2024-04-29 10:07:09 +00:00
zhengzangw
5c8139521a update 2024-04-29 10:02:42 +00:00
Shen-Chenhui
b78b469420 fix merge 2024-04-29 17:58:59 +08:00
Shen-Chenhui
f81d8648cf move out losses to different file 2024-04-29 17:53:03 +08:00
zhengzangw
a2dc903863 update 2024-04-29 09:41:39 +00:00
Shen-Chenhui
4d69671663 clean up code 2024-04-29 17:18:45 +08:00
zhengzangw
1171e5b6f9 update config 2024-04-29 07:27:15 +00:00
zhengzangw
f3dcb4d6fb complete 3b backbone 2024-04-29 06:00:14 +00:00
Shen-Chenhui
ffc306c4fb latest inference script 2024-04-28 16:07:25 +08:00
Shen-Chenhui
8d914707f8 enable end to end loss training 2024-04-27 21:46:09 +08:00
zhengzangw
84465c0e44 add config for PixArt 1.6B 2024-04-27 13:41:21 +00:00
Shen-Chenhui
a04a7d7fbe debug 2024-04-27 21:00:40 +08:00
Shen-Chenhui
0d35fb4953 debug 2024-04-27 20:59:07 +08:00
Shen-Chenhui
52e869079c debug 2024-04-27 20:57:48 +08:00
Shen-Chenhui
0198ea8a52 fixed inference 2024-04-27 17:21:45 +08:00
Shen-Chenhui
6fb4e3cd22 debug 2024-04-27 17:18:19 +08:00
Shen-Chenhui
7b134d71dc modify inference 2024-04-27 17:02:24 +08:00
Shen-Chenhui
38c46ac721 fix bug 2024-04-27 15:25:03 +08:00
Shen-Chenhui
d7b278d4b5 removed breakpoint 2024-04-27 14:59:42 +08:00
Shen-Chenhui
2c391a636b dataset trainscript 2024-04-27 14:55:47 +08:00
zhengzangw
478b585024 [wip] debug vae 2024-04-26 07:27:26 +00:00
zhengzangw
a4652a8aef Merge branch 'main' into vae 2024-04-26 06:56:22 +00:00
Shen-Chenhui
c7a698e85b fix dist issue 2024-04-26 13:50:56 +08:00
Shen-Chenhui
c83ee95b8d fix bug 2024-04-26 11:57:16 +08:00
Shen-Chenhui
1d6cee302f add lecam support 2024-04-26 11:27:20 +08:00
Shen-Chenhui
c20955e5b3 lecam support 2024-04-26 10:41:40 +08:00
Shen-Chenhui
bf1999f9b1 issue opt saving 2024-04-26 10:34:31 +08:00
zhengzangw
44e618bbbc a bunch of update 2024-04-24 09:23:24 +00:00
Shen-Chenhui
9683ec66c7 inference script update 2024-04-24 17:04:53 +08:00
Shen-Chenhui
0138be6e21 grad penalty expr 2024-04-24 14:52:47 +08:00
zhengzangw
9e0b314dab update config 2024-04-24 02:33:27 +00:00
Shen-Chenhui
90775e52bd debug 2024-04-24 10:12:52 +08:00
Shen-Chenhui
988bc3bb65 config lc gp 2024-04-24 10:03:58 +08:00
zhengzangw
1e702a3088 fix start from scratch 2024-04-23 11:34:35 +00:00
Zangwei Zheng
e009e89e1a add start from scratch 2024-04-23 19:24:22 +08:00
Shen-Chenhui
da0a875389 debug 2024-04-23 15:21:33 +08:00
Shen-Chenhui
d565477680 disable non-master print 2024-04-23 14:43:02 +08:00
zhengzangw
a80808b6c4 update eval api and docs 2024-04-23 03:48:40 +00:00
Shen-Chenhui
486593f137 LeCam Loss working 2024-04-23 10:58:09 +08:00
Shen-Chenhui
8b3b96f85a config wandb 2024-04-23 09:27:45 +08:00
Shen-Chenhui
f4fe9b5eca add lecam 2024-04-23 09:22:05 +08:00
zhengzangw
9686395ade support vbench-i2v 2024-04-21 14:12:58 +00:00
zhengzangw
2b42ca82d8 [wip] prompt with json 2024-04-21 11:07:59 +00:00
zhengzangw
6073af6444 merge video edit 2024-04-20 15:47:48 +00:00
Zheng Zangwei (Alex Zheng)
341b12f9bf Dev/v1.0.1 (#58)
* update (#57)

* update

* update datautil

* add VBench prompt

* update eval

* update eval

* update intepolation

* add vbench eval

* Dev/sdedit implementation (#56)

* Update utils.py

* update

* update

* update

---------

Co-authored-by: YuKun Zhou <90625606+1zeryu@users.noreply.github.com>
2024-04-20 21:23:10 +08:00
Zangwei Zheng
f6574f1509 hotfix exp 2024-04-19 18:15:06 +08:00
Shen-Chenhui
96a42e08db config 2024-04-19 17:49:50 +08:00
Zangwei Zheng
15f9d702ed [exp] update 2024-04-19 17:43:44 +08:00
Zangwei Zheng
dce2ef4a1c [exp] new config 2024-04-19 15:21:00 +08:00
Shen-Chenhui
eafabaee78 debug disc loss 2024-04-19 14:47:34 +08:00
Shen-Chenhui
b16001e5e3 debug 2024-04-19 14:28:53 +08:00
Zheng Zangwei (Alex Zheng)
d2a782efac Dev/fps (#55)
* support fps

* update fps
2024-04-19 13:18:52 +08:00
Zangwei Zheng
0e6c15d50b Merge branch 'main' into dev/v1.0.1 2024-04-19 12:48:22 +08:00
Zheng Zangwei (Alex Zheng)
069ea0d687 Feat/fast bucket (#54)
* [wip] bucket

* [bug] not parallel

* update eval

* update sample.sh

* accelerate bucket build with pandarallel
2024-04-19 11:42:02 +08:00
Shen-Chenhui
136304eb61 debug 2024-04-19 11:15:53 +08:00
Shen-Chenhui
c36d747b2f inference script 2024-04-19 11:06:13 +08:00
Shen-Chenhui
a78ffe95a6 debug 2024-04-19 10:51:11 +08:00
Shen-Chenhui
41a600b61b inference config 2024-04-19 10:47:09 +08:00
Shen-Chenhui
0ad337178a debug 2024-04-19 10:29:25 +08:00
Zheng Zangwei (Alex Zheng)
1f99b9ba4b complete eval pipeline (#53) 2024-04-18 15:49:14 +08:00
Shen-Chenhui
6ecc858350 pipeline config for trial data 2024-04-18 15:06:28 +08:00
Shen-Chenhui
246eddecdd enable pipeline vae training 2024-04-18 14:13:56 +08:00
Shen-Chenhui
aba1de6eb3 add pipeline 2024-04-18 13:49:54 +08:00
Zangwei Zheng
ee2e4083e4 [feat] update eval 2024-04-17 17:35:44 +08:00
Zangwei Zheng
8cb6d2f0bd [feat] update eval 2024-04-17 17:05:08 +08:00
Shen-Chenhui
95517d7fb5 inference v2 working 2024-04-16 18:30:31 +08:00
Shen-Chenhui
becff9d86f inference v2 2024-04-16 18:15:12 +08:00
Frank Lee
79dabf8bdf added seed to dataloader args (#52) 2024-04-16 17:45:53 +08:00
Shen-Chenhui
aae08a2841 debug 2024-04-16 17:31:57 +08:00
Shen-Chenhui
235d195dac add logvar 2024-04-16 17:25:48 +08:00
Shen-Chenhui
36b754b047 debug 2024-04-16 15:06:17 +08:00
Shen-Chenhui
afd3f823d4 debug 2024-04-16 15:00:31 +08:00
Frank Lee
db94454645 Feature/timeout (#50)
* added large nccl timeout

* polish

* polish
2024-04-15 23:55:58 +08:00
Shen-Chenhui
af1b1e484d reimplement blurpool 2024-04-15 17:47:33 +08:00
Shen-Chenhui
686829969f debug 2024-04-15 15:13:29 +08:00
Zangwei Zheng
63e86f6dd6 hotfix inference 2024-04-15 13:44:30 +08:00
Shen-Chenhui
c71e04daaa add lecam and gradient penalty loss to discriminator 2024-04-15 11:13:39 +08:00
Zangwei Zheng
e88185fb9f update notebook 2024-04-14 02:02:59 +08:00
Shen-Chenhui
79bff13099 debug 2024-04-13 10:51:56 +08:00
Shen-Chenhui
fb0f59171c debug 2024-04-13 09:36:39 +08:00
Shen-Chenhui
06aa4589f2 debug 2024-04-12 18:39:31 +08:00
Shen-Chenhui
dbd3982ee8 debug 2024-04-12 18:37:28 +08:00
Shen-Chenhui
28f3f4b597 debug 2024-04-12 18:30:40 +08:00
Shen-Chenhui
c80459b72f debug 2024-04-12 18:27:51 +08:00
Shen-Chenhui
f905a1b69d debug 2024-04-12 18:16:22 +08:00
Shen-Chenhui
d53245a98c debug 2024-04-12 18:14:18 +08:00
Shen-Chenhui
de9fffacfd gan training 2024-04-12 17:57:35 +08:00
Shen-Chenhui
e004d43f69 gan optimizer 2024-04-12 15:10:19 +08:00
Shen-Chenhui
ab59033f20 gan 2024-04-12 12:42:02 +08:00
Shen-Chenhui
63f3737eb0 add simple discriminator 2024-04-11 15:14:16 +08:00
Hongxin Liu
2393c63083 [feature] add batch size search script (#47) 2024-04-11 14:23:13 +08:00
Shen-Chenhui
ee58ec16b4 add image encoding support 2024-04-11 10:50:23 +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
a1808be460 debug 2024-04-08 18:18:05 +08:00
Shen-Chenhui
4861e6beaf debug 2024-04-08 18:13:15 +08:00
Shen-Chenhui
9f211646f3 debug 2024-04-08 18:11:27 +08:00
Shen-Chenhui
ab38a411a8 debug 2024-04-08 18:07:50 +08:00
Shen-Chenhui
55821937d9 debug 2024-04-08 18:04:32 +08:00
Shen-Chenhui
a485925dbd debug 2024-04-08 18:02:02 +08:00
Shen-Chenhui
45ea2bd29d debug 2024-04-08 18:00:30 +08:00
Shen-Chenhui
e151b64319 debug 2024-04-08 17:58:33 +08:00
Shen-Chenhui
dba5de3d90 debug 2024-04-08 17:54:31 +08:00
Shen-Chenhui
bbeacb491d debug 2024-04-08 17:50:41 +08:00
Shen-Chenhui
0d497994cd debug 2024-04-08 17:42:27 +08:00
Shen-Chenhui
ce0b1928e6 debug 2024-04-08 17:41:08 +08:00
Shen-Chenhui
08fac69c38 debug 2024-04-08 17:39:19 +08:00
Shen-Chenhui
616e2b4fe5 debug 2024-04-08 17:37:29 +08:00
Shen-Chenhui
04a0e4769b debug 2024-04-08 17:33:54 +08:00
Shen-Chenhui
fb64216b45 debug 2024-04-08 17:32:30 +08:00
Shen-Chenhui
25707a9d7d debug 2024-04-08 17:28:31 +08:00
Shen-Chenhui
9c8d084ec5 debug 2024-04-08 17:26:36 +08:00
Shen-Chenhui
eae30f9f89 debug 2024-04-08 17:23:53 +08:00
Shen-Chenhui
4ef813555c debug 2024-04-08 17:22:44 +08:00
Shen-Chenhui
827a0b2c55 debug 2024-04-08 17:21:26 +08:00
Shen-Chenhui
a634f7327e debug 2024-04-08 17:17:22 +08:00
Shen-Chenhui
a401630e7a debug 2024-04-08 17:03:27 +08:00
Shen-Chenhui
3eb96a2793 debug 2024-04-08 16:58:54 +08:00
Shen-Chenhui
dfae10e32b debug 2024-04-08 16:56:28 +08:00
Shen-Chenhui
78f9ec8710 debug 2024-04-08 16:54:27 +08:00
Shen-Chenhui
47b51ba07d debug 2024-04-08 16:53:18 +08:00
Shen-Chenhui
d927acc19d debug 2024-04-08 16:51:06 +08:00
Shen-Chenhui
475762cdb2 debug 2024-04-08 16:37:26 +08:00
Shen-Chenhui
c6181ebdfd debug 2024-04-08 16:36:54 +08:00
Shen-Chenhui
90fc92ee9c debug 2024-04-08 16:14:00 +08:00
Shen-Chenhui
ab1970ca24 debug 2024-04-08 16:05:15 +08:00
Shen-Chenhui
0a5c767fc7 debug 2024-04-08 15:54:03 +08:00
Shen-Chenhui
b2148d5505 debug 2024-04-08 15:52:25 +08:00
Shen-Chenhui
7e3951300f debug 2024-04-08 15:43:06 +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
1b66919091 debug 2024-04-08 10:53:44 +08:00
Shen-Chenhui
ad02d28d9c debug inference running loss 2024-04-08 10:22:07 +08:00
Frank Lee
27a627373a updated gradio app (#260) 2024-04-06 23:34:55 +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
bc095aa492 debug 2024-04-04 15:26:56 +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
ebb3dc4d59 enable wandb 2024-04-02 11:47:56 +08:00
Shen-Chenhui
562a966a77 debug 2024-04-01 16:14:11 +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
Hongxin Liu
5e82d1493b [feature] refactor sampler (#4)
* [feature] refactor sampler

* [feature] support sampler resuming

* [feature] support sampler resuming
2024-03-29 23:32:12 +08:00
Shen-Chenhui
d1e57cbfd5 debug 2024-03-29 10:30:56 +08:00
Shen-Chenhui
4795fd5354 debug 2024-03-28 23:27:26 +08:00
Zangwei Zheng
a01f6da20e [feat] support for stdit2 sampling 2024-03-28 21:35:33 +08:00