OleehyO
60f6a3d7ee
feat: add base trainer implementation and training script
...
- Add Trainer base class with core training loop functionality
- Implement distributed training setup with Accelerate
- Add training script with model/trainer initialization
- Support LoRA fine-tuning with checkpointing and validation
2025-01-01 15:10:41 +00:00
OleehyO
a505f2e312
Add constants.py
2025-01-01 15:10:40 +00:00
OleehyO
78f655a9a4
Add utils
2025-01-01 15:10:40 +00:00
OleehyO
85e00a1082
feat(models): add scaffolding
2025-01-01 15:10:40 +00:00
OleehyO
918ebb5a54
feat(datasets): implement video dataset modules
...
- Add dataset implementations for text-to-video and image-to-video
- Include bucket sampler for efficient batch processing
- Add utility functions for data processing
- Create dataset package structure with proper initialization
2025-01-01 15:10:40 +00:00
OleehyO
e3f6def234
feat: add video frame extraction tool
...
Add utility script to extract first frames from videos, helping users convert T2V datasets to I2V format
2025-01-01 15:10:39 +00:00
OleehyO
7b282246dd
chore: remove unused configuration files after refactoring
...
Delete accelerate configs, deepspeed config and host file that are no longer needed
2025-01-01 15:10:39 +00:00
OleehyO
5cb9303286
chore: update .gitignore
...
- Add new ignore patterns for dataset and model directories
- Update rules for development files
2025-01-01 15:10:32 +00:00
OleehyO
ba85627577
[docs] improve help messages in argument parser
...
Fix and clarify help documentation in parser.add_argument() to better describe command-line arguments.
2025-01-01 15:10:31 +00:00
OleehyO
2508c8353b
[bugfix] fix specific resolution setting
...
Different models use different resolutions, for example, for the CogVideoX1.5 series models, the optimal generation resolution is 1360x768， But for CogVideoX, the best resolution is 720x480.
2025-01-01 15:10:31 +00:00
Gforky
48ac9c1066
[fix]fix typo in train_cogvideox_image_to_video_lora.py
2025-01-01 15:10:30 +00:00
Zheng Guang Cong
21693ca770
fix bugs of image-to-video without image-condition
2025-01-01 15:10:30 +00:00
三洋三洋
a6e611e354
docs: update TOC and add friendly link in README files
...
- Update table of contents in README.md, README_ja.md and README_zh.md
- Add friendly link section to all README files
2024-12-27 19:37:08 +08:00
Yuxuan.Zhang
7935bd58a1
Merge pull request #615 from THUDM/CogVideoX_dev
...
Cog video x dev
2024-12-19 12:57:56 +08:00
OleehyO
1811c50e73
[docs] improve help messages in argument parser
...
Fix and clarify help documentation in parser.add_argument() to better describe command-line arguments.
2024-12-18 12:30:13 +00:00
OleehyO
92a589240f
[bugfix] fix specific resolution setting
...
Different models use different resolutions, for example, for the CogVideoX1.5 series models, the optimal generation resolution is 1360x768， But for CogVideoX, the best resolution is 720x480.
2024-12-18 12:25:43 +00:00
OleehyO
7add8f8437
Merge pull request #607 from THUDM/CogVideoX_dev
...
Add resolution warning
2024-12-17 09:58:10 +08:00
OleehyO
cfaca91cde
Merge remote-tracking branch 'upstream/main' into dev
2024-12-16 11:38:26 +00:00
OleehyO
d3a7d2dc91
Add resolution warning
2024-12-16 11:34:51 +00:00
Yuxuan.Zhang
46098f446b
Merge pull request #603 from Gforky/fix-demo-issue
...
[fix]fix typo in train_cogvideox_image_to_video_lora.py
2024-12-15 22:00:41 +08:00
Gforky
5a03e6fa79
[fix]fix typo in train_cogvideox_image_to_video_lora.py
2024-12-14 16:12:57 +08:00
Yuxuan.Zhang
1605e95033
Merge pull request #599 from THUDM/CogVideoX_dev
...
Cog video x dev
2024-12-13 15:03:48 +08:00
OleehyO
7b4c9db6d9
Fix for CogVideoX-{2B,5B}
...
When loading CogVideX-{2B,5B}, `patch_size_t` is None,
which results in the `prepare_rotary_position_embeddings` function.
2024-12-13 04:02:27 +00:00
OleehyO
36f1333788
Fix for deepspeed training
2024-12-13 04:02:26 +00:00
OleehyO
4d1b9fd166
Fix for Disney video dataset
2024-12-13 04:02:21 +00:00
OleehyO
3ff9d3049d
docs: change "read this in English" to "中文阅读"
...
Update README.md to use Chinese text for language switch link
2024-12-11 05:10:28 +00:00
Yuxuan.Zhang
496e220463
Merge pull request #585 from ZGCTroy/patch-1
...
fix bugs of image-to-video without image-condition
2024-12-08 19:31:59 +08:00
Zheng Guang Cong
a46d762cd9
fix bugs of image-to-video without image-condition
2024-12-06 20:14:43 +08:00
Yuxuan.Zhang
87ccd38cea
Merge pull request #567 from THUDM/main
...
New Finetune
2024-12-02 11:30:20 +08:00
Yuxuan.Zhang
5aa6d3a9ee
Merge pull request #515 from Gforky/fix_finetune_demo
...
[fix]fix deepspeed initialization issue in finetune examples
2024-12-02 11:29:42 +08:00
Yuxuan.Zhang
a094b34425
Merge pull request #565 from THUDM/CogVideoX_dev
...
Cog video x dev
2024-11-30 12:45:25 +08:00
zR
0fe46df21f
new jobs of friendly link
2024-11-30 12:40:07 +08:00
Yuxuan.Zhang
f1a2b48974
Merge pull request #556 from THUDM/main
...
new announced
2024-11-27 12:11:12 +08:00
Yuxuan.Zhang
d82922cc79
Merge pull request #538 from spacegoing/fix_rope_finetune_shape
...
[Fix] fix rope temporal patch size
2024-11-23 21:24:39 +08:00
spacegoing
2fb763d25f
[Fix] fix rope temporal patch size
2024-11-21 16:26:45 +00:00
luwen.miao
ac2f2c78f7
[fix]fix deepspeed initialization issue in finetune examples
2024-11-18 09:49:31 +00:00
Yuxuan.Zhang
2fdc59c3ce
Merge pull request #507 from THUDM/CogVideoX_dev
...
diffusers version
2024-11-17 21:54:47 +08:00
zR
17996f11f8
update
2024-11-16 10:06:22 +08:00
Yuxuan.Zhang
5e3e3aabe0
Merge pull request #500 from THUDM/main
...
Merge
2024-11-13 21:15:49 +08:00
zR
e7a35ea33b
update friendly link
2024-11-13 17:06:16 +08:00
zR
cd5ceca22b
fix resolution docs
2024-11-12 00:41:23 +08:00
zR
bb2cb130a0
add width and height
2024-11-12 00:17:19 +08:00
zR
2151a3bdfb
update with diffusers
2024-11-11 22:41:28 +08:00
zR
68d93ce8fc
fix
2024-11-09 22:51:39 +08:00
zR
155456befa
update
2024-11-09 22:49:03 +08:00
zR
2475902027
friendly link
2024-11-09 22:43:02 +08:00
zR
fb806eecce
update table
2024-11-09 22:29:36 +08:00
zR
c8c7b62aa1
update diffusers code
2024-11-09 22:07:32 +08:00
Yuxuan.Zhang
e2987ff565
Merge pull request #474 from THUDM/CogVideoX_dev
...
Fix #472 #473
2024-11-09 00:18:01 +08:00
zR
a8205b575d
Update cp_enc_dec.py
2024-11-08 23:27:44 +08:00
