Commit graph

117 commits

Author SHA1 Message Date
hxwang
5730060f41
[ckpt] mitigate gpu mem peak when loading ckpt 2025-03-26 18:04:16 +08:00
hxwang
bc4aa4f217 [ckpt] fix shape error when gathering weights under sp + dp parallelism 2025-03-26 15:43:00 +08:00
Zheng Zangwei (Alex Zheng)
febf3ad4b2
Update Open-Sora 2.0 (#807)
* upload v2.0

* update docs

* [hotfix] fit latest fa3 (#802)

* update readme

* update readme

* update readme

* update train readme

* update readme

* update readme: motion score

* cleaning video dc ae WIP

* update config

* add dependency functions

* undo cleaning

* use latest dcae

* complete high compression training

* update hcae config

* cleaned up vae

* update ae.md

* further cleanup

* update vae & ae paths

* align naming of ae

* [hotfix] fix ring attn bwd for fa3 (#803)

* train ae default without wandb

* update config

* update evaluation results

* added hcae report

* update readme

* update readme demo

* update readme demo

* update readme gif

* display demo directly in readme

* update paper

* delete files

---------

Co-authored-by: Hongxin Liu <lhx0217@gmail.com>
Co-authored-by: Shen-Chenhui <shen_chenhui@u.nus.edu>
Co-authored-by: wuxiwen <wuxiwen.simon@gmail.com>
2025-03-12 13:14:22 +08:00
Zheng Zangwei (Alex Zheng)
f1c6b8b88e open-sora v1.3 code upload (#786)
Co-authored-by: gxyes <gxynoz@gmail.com>
2025-02-20 16:50:24 +08:00
Gao, Ruiyuan
df5668cdf1 fix bug at mha, MaskGenerator; improve ckpt_utils.py (#609)
* fix bug at mha in blocks.py

* fix bug in MaskGenerator

* align logging style in ckpt_utils.py
2025-02-20 16:40:47 +08:00
Hongxin Liu
70ca63f30b [feature] support async ckpt & pin memory cache (#760)
* [feature] support async ckpt

* [feature] support pin memory cache

* [doc] update readme
2024-12-20 10:30:49 +08:00
ZXMMD
a29424c237 fix ckpt_utils.py (#580) 2024-07-12 14:52:21 +08:00
Hongxin Liu
332d9fc9c9 [feature] make timer optional and make reduce bucket size configurable (#549)
* [feature] make reduce bucket size configurable

* [feature] make timer optional
2024-06-27 13:37:54 +08:00
zhengzangw
525e29abbe reformat and update docs 2024-06-17 15:37:23 +00:00
zhengzangw
30e276166c update 2024-06-17 13:42:27 +00:00
zhengzangw
dc577e98b9 Merge branch 'dev/v1.2' of github.com:hpcaitech/Open-Sora-dev into dev/v1.2 2024-06-17 07:01:35 +00:00
zhengzangw
41f772d1f8 [docs] update readme 2024-06-17 07:01:27 +00:00
Frank Lee
4d243955ca [checkpoint] adapted vae to hf (#145) 2024-06-17 14:59:33 +08:00
zhengzangw
b6b2535c79 update inference 2024-06-17 05:57:25 +00:00
Frank Lee
be61f44a29 [gradio] udpated inference logic (#138)
* [gradio] udpated inference logic

* polish
2024-06-15 22:43:33 +08:00
zhengzangw
b70b749e55 [fix] loop support for score and refinement 2024-06-14 17:18:29 +00:00
Frank Lee
41e6e9492e [gradio] supported random prompt and watermark (#136) 2024-06-14 17:57:44 +08:00
zhengzangw
c5e0475749 [feat] support for random sample 2024-06-14 08:50:40 +00:00
zhengzangw
c93e846017 [feat] fps control 2024-06-14 07:44:35 +00:00
zhengzangw
992aae7d8f [feat] prompt refine 2024-06-14 07:37:00 +00:00
Frank Lee
a887f54711 added sp for stdit3 (#131) 2024-06-14 11:10:43 +08:00
Frank Lee
9dde960b95 added gradio (#133)
* added gradio

* added gradio
2024-06-13 16:56:30 +08:00
zhengzangw
a8a34d56b9 [fix] inference with score 2024-06-13 02:37:45 +00:00
zhengzangw
51cdd377cc reformat 2024-06-12 09:24:53 +00:00
zhengzangw
a271faa131 [fix] condition sampling 2024-06-11 07:49:00 +00:00
Shen-Chenhui
bd182d93dd format 2024-06-10 06:02:36 +00:00
zhengzangw
6094f5fe92 [feat] add score for inference 2024-06-09 12:01:26 +00:00
zhengzangw
ce601066c5 [stage2] update config 2024-06-05 15:49:51 +00:00
Frank Lee
ea96cdb5e4 added warmup lr scheduler (#121) 2024-06-05 10:12:52 +08:00
Zheng Zangwei (Alex Zheng)
9370fbe02d update timer (#115) 2024-05-29 14:46:14 +08:00
Frank Lee
2e1e26a2e4 added timer for benchmarking (#114) 2024-05-29 14:43:15 +08:00
zhengzangw
5b9e753039 [feat] unify dataloader api 2024-05-20 08:40:45 +00:00
zhengzangw
5aad90acaf [feat] extract feature 2024-05-17 09:53:48 +00:00
zhengzangw
a016325a8e [feat] enable freezing y_embedder 2024-05-17 06:40:44 +00:00
zhengzangw
9fd4554f55 [fix] vae dtype 2024-05-16 08:50:24 +00:00
zhengzangw
0592723022 [feat] update bs search and loss eval 2024-05-15 13:05:53 +00:00
zhengzangw
f489cb0915 [feat] accelerate search batch size 2024-05-15 08:07:49 +00:00
zhengzangw
a36f80f847 [feat] notebook for inference 2024-05-14 07:24:56 +00:00
zhengzangw
e1e379d898 [feat] update inference config 2024-05-14 05:40:17 +00:00
zhengzangw
3a01cb440d [feat] inference for rf 2024-05-13 11:39:16 +00:00
zhengzangw
6194da6504 [fix] update inference and datautil 2024-05-13 06:33:12 +00:00
zhengzangw
74dfaa879c [fix] ema ckpt save 2024-05-12 05:15:06 +00:00
zhengzangw
2a55d672a7 [feat] update logging and bucket 2024-05-09 08:07:56 +00:00
zhengzangw
e9db7b3af1 update training script 2024-05-09 05:53:19 +00:00
zhengzangw
31228fe9c8 [refactor] fix train warnings 2024-05-09 03:10:26 +00:00
zhengzangw
322e566aed update 2024-05-09 03:10:26 +00:00
Zangwei Zheng
eb5ff82fc5 quick update 2024-05-09 11:09:52 +08:00
Shen Chenhui
dc7b7fd64a fix bug (#95)
Co-authored-by: Shen-Chenhui <shen_chenhui@u.nus.edu>
2024-05-08 17:39:21 +08:00
Zheng Zangwei (Alex Zheng)
f047d5786a [refactor] clean train.py code (#94) 2024-05-08 16:07:57 +08:00
Frank Lee
fe19568a49 fixed race condition in exp workspace (#91) 2024-05-07 17:17:43 +08:00