nicolabs/Open-Sora
1
0
Fork 0
mirror of https://github.com/hpcaitech/Open-Sora.git synced 2026-05-20 09:22:22 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
217 commits 8 branches 4 tags 504 MiB
Commit graph

217 commits

This branch
This branch
All branches
Author SHA1 Message Date
xyupeng
d6a4aeda74 update scoring 2024-04-02 11:13:41 +08:00
xyupeng
ca53b1a21b update data processing 2024-04-02 10:51:40 +08:00
xyupeng
833c70f2ae add optical flow 2024-04-01 20:00:27 +08:00
Zangwei Zheng
5ade5e5984 [fix] use decord for tools 2024-04-01 16:45:23 +08:00
Zangwei Zheng
ff15a0acfb [docs] data processing 2024-04-01 16:08:53 +08:00
Zangwei Zheng
c553ee274f better aspect ratio 2024-04-01 14:27:13 +08:00
Zangwei Zheng
37aa96e76c Merge branch 'dev/v1.0.1' of https://github.com/hpcaitech/Open-Sora-dev into dev/v1.0.1 2024-04-01 11:45:46 +08:00
Zangwei Zheng
4bfb90295b update csvutil 2024-04-01 11:45:38 +08:00
Frank Lee
a9e8220c7c fixed image size in sampler (#15) 
* fixed image size in sampler

* polish
 2024-04-01 11:43:56 +08:00
Zangwei Zheng
cdd3b5eb74 llava fix and config modification 2024-03-31 23:44:37 +08:00
Zheng Zangwei (Alex Zheng)
f1ee27ba2f [feat] llava support image and text (#13) 
* [feat] llava support image and text

* add resize for image

* update gpt4 caption

* update prompt for llava image captioning
 2024-03-31 20:59:33 +08:00
Frank Lee
46f9af34fc fixed multiprocessing dataloader (#14) 2024-03-31 20:59:22 +08:00
Frank Lee
0f2bb1700b refactored llava captioning (#12) 2024-03-31 01:11:03 +08:00
Zangwei Zheng
fb6bd34443 delete intepolate 2024-03-30 23:57:03 +08:00
Zangwei Zheng
d7811a1a0e update config 2024-03-30 17:27:44 +08:00
Zangwei Zheng
353f84c253 Merge branch 'dev/zangwei' into dev/v1.0.1 2024-03-30 17:06:43 +08:00
Zangwei Zheng
987283fa1b [fix] transform may not fit enough 2024-03-30 17:05:15 +08:00
Zheng Zangwei (Alex Zheng)
a289bced09 Dev/zangwei (#10) 
* format and some fix

* support csv for llava
 2024-03-30 13:46:23 +08:00
Zangwei Zheng
b44acc022c support csv for llava 2024-03-30 13:45:24 +08:00
Zheng Zangwei (Alex Zheng)
f9f539f07e format and some fix (#8) 2024-03-30 13:34:19 +08:00
Zangwei Zheng
fd22c286fb Merge branch 'dev/v1.0.1' of https://github.com/hpcaitech/Open-Sora-dev into dev/zangwei 2024-03-30 13:03:21 +08:00
Frank Lee
a0bdaced4e replaced numpy ops with torch ops (#9) 
* replaced numpy ops with torch ops

* polish

* polish
 2024-03-30 13:01:58 +08:00
Zangwei Zheng
52aeb3769f format and some fix 2024-03-30 12:02:48 +08:00
Frank Lee
223cc34c46 Merge pull request #7 from hpcaitech/dev/variable 
Dev/variable
 2024-03-30 10:57:07 +08:00
Zheng Zangwei (Alex Zheng)
2679bad9a0 update readme (#6) 2024-03-29 23:34:53 +08:00
Zheng Zangwei (Alex Zheng)
682a699aec Update image process (#5) 
* [docs] update tool docs

* update aes
 2024-03-29 23:34:10 +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
Hongxin Liu
c0fe4b384c [hotfix] fix caption embedder (#3) 2024-03-29 23:30:47 +08:00
Zangwei Zheng
889788dd49 [wip] image wrong with flashattn 2024-03-28 22:35:07 +08:00
Zangwei Zheng
2d4a5df287 [wip] image wrong with flashattn 2024-03-28 22:04:43 +08:00
Zangwei Zheng
a01f6da20e [feat] support for stdit2 sampling 2024-03-28 21:35:33 +08:00
Zangwei Zheng
1d9036b3ed Merge branch 'dev/variable' of https://github.com/hpcaitech/Open-Sora-dev into dev/variable 2024-03-28 19:27:24 +08:00
Zangwei Zheng
8b778213d1 [feat] complete dynamic pos 2024-03-28 19:27:17 +08:00
Zangwei Zheng
cba02e8a58 [feat] dynamic for video (base_size not completed) 2024-03-28 17:58:36 +08:00
Hongxin Liu
8d5278b99a [feature] impl cached pos embedding (#1) 
* [feature] impl cached pos embedding

* [feature] update pos emb

* [feature] update pos emb
 2024-03-28 17:30:47 +08:00
Zangwei Zheng
94e686177e [wip] multi ar 2024-03-27 23:04:12 +08:00
Frank Lee
b704d6c0f8 Feature/llava speedup (#2) 
* [caption] accelerated llava with flash attention and parallel frame extraction

* supported dp and tp in llava

* code formatting
 2024-03-27 16:55:25 +08:00
Zangwei Zheng
7392d2e551 [feat] multiple frames with 360p 2024-03-27 00:24:46 +08:00
Zangwei Zheng
62097da2d3 refactor temporal_random_crop 2024-03-26 17:32:15 +08:00
Zangwei Zheng
3a0b85456c fix 2024-03-26 17:15:59 +08:00
Zangwei Zheng
552b7e8f79 register dataset 2024-03-26 17:02:41 +08:00
Zangwei Zheng
01728dc28a refactor datasets 2024-03-26 16:50:36 +08:00
Zangwei Zheng
c93390a001 fix stdit2 2024-03-26 15:47:29 +08:00
Zangwei Zheng
f3ace2b341 merge stdit2 2024-03-26 15:46:31 +08:00
Zangwei Zheng
11665b86a3 update mask loss calculation 2024-03-26 14:20:06 +08:00
Zangwei Zheng
0dcf1ff888 add speediffusion 2024-03-25 22:20:10 +08:00
Zangwei Zheng
b1496b3e17 Merge branch 'main' into dev/v1.0.1 2024-03-25 21:19:36 +08:00
Zangwei Zheng
e478c4328d Merge branch 'main' of https://github.com/hpcaitech/Open-Sora 2024-03-25 21:15:32 +08:00
Zheng Zangwei (Alex Zheng)
e826311de4 fix cfg_channel (#217) 2024-03-25 21:15:16 +08:00
Zangwei Zheng
4d3b68e3ad accelerate aesthetic 2024-03-25 20:54:02 +08:00