bubbliiiing
a0eb3971fe
Support 16G with out int8 qwen2_vl
2025-02-10 09:07:57 +00:00
bubbliiiing
be8f0e08cc
Update 7b and remove useless info in training
2025-02-10 03:46:28 +00:00
Bubbliiiing and hkunzhe
9f34f7c8c5
Update to V5.1 ( #179 )
...
* Update Flow
* Update Flow
* Update Flow
* add image recaptioning
* Fix bug in t2v
* update train_reward_lora.py
* update reward training
* Update V5.1 and mix multi text_encoders to one pipeline
* Update V5.1 training Code
* Update ComfyUI
* Update Comment
* Delete files
* update reward training
* Update Readme
* fix extract frames in compute_semantic_consistency
* Update Readme && Remove to in prediction
* Update Demo
* Update Readme
* Update ui
* support vae gradient checkpointing in reward training
* Update Training Readme
---------
Co-authored-by: hkunzhe <huangkunzhe.hkz@alibaba-inc.com >
2025-01-22 15:30:47 +08:00
Bubbliiiing
45c298af71
Update Readme && Update lora cache && Lora merge with CUDA ( #173 )
...
* Update Readme
* Fix bug in training
* Update Readme
* Update Readme && Update lora cache
* Update Readme
* Update error info in sampler
* Fix Memory bug in 12b
2024-12-26 15:41:21 +08:00
hkz
485e771acf
Fix train reward lora and video caption ( #165 )
2024-12-10 14:23:33 +08:00
Bubbliiiing
ccbdce4492
Update Readme ( #161 )
...
* Update Readme
* Fix bug in training
* Update Readme
2024-12-02 11:27:57 +08:00
hkz and bubbliiiing
17c1f02ba8
Add reward LoRA training ( #160 )
...
* Add reward lora
* Fix bug in lora utils && Update Readme
---------
Co-authored-by: bubbliiiing <3323290568@qq.com >
2024-11-28 13:59:53 +08:00
Bubbliiiing
62de94e2f1
Update V5 ( #128 )
...
Update V5
2024-11-08 19:46:50 +08:00
Bubbliiiing
d3b8bbbd14
Fix bug in v3 training ( #98 )
2024-08-22 16:03:14 +08:00
e4f1a4fe97
Update V4 version ( #92 )
...
* update train_lora && update deepspeed && update training with max token length
* fix bug in train.py
* fix bug in training_with_video_token_length
* update v2v && update v2v api
* add rope2d embedding precomputation; move text encoder to dataloader to reduce gpu memory consumpution
* add cuda multi-stream to speedup vae encode
* update new vae && new comfyui
* fix some bug in training code
* Add lcm lora (#89 )
Co-authored-by: xuanyuan.lb <xuanyuan.lb@alibaba-inc.com >
* Update Training Code and fix bug in low vram mode
* fix bug in low vram mode
* update report
* update cfg
* actual text clip
---------
Co-authored-by: mengli.cml <mengli.cml@alibaba-inc.com >
Co-authored-by: liubo0902 <38622806+liubo0902@users.noreply.github.com >
Co-authored-by: xuanyuan.lb <xuanyuan.lb@alibaba-inc.com >
2024-08-19 11:22:17 +08:00
bubbliiiing
039d67acf1
support float16 && add reference && fix bug in training
2024-07-24 13:19:03 +08:00
bubbliiiing
2eef3f9f78
update v4
2024-07-18 16:33:56 +08:00
Bubbliiiing
616a35425d
Fix the issue where Lora training cannot load state, fix the issue where training cannot eval ( #66 )
...
* rename the comfyui files and new readme
* fix bug in eval and load lora state dict
2024-07-18 15:47:51 +08:00
Bubbliiiing
6ed8619ad4
Rename the files ( #45 )
...
* add update readme
* update demo show and prompt
* rename the train code
2024-07-10 17:46:02 +08:00
Bubbliiiing
f1e013619c
Update Readme and Gallery ( #42 )
...
* add update readme
* update demo show and prompt
2024-07-06 13:10:13 +08:00
Bubbliiiing and chenyunkuo.cyk
f9eeabe231
Updated to v3 version, supports image generated videos, with a maximum support of 960x960x144 video generation. ( #40 )
...
* update v3
* Fix frame start_idx bug, see issue #41 .
* update readme and fix bug in training
* update requirements
* update ui
* fix bug in inpaint
* update new ui
* fix bug in auto resize
* fix bug in auto resize
* fix bug in modelscope and eas
* update low gpu memory mode
---------
Co-authored-by: chenyunkuo.cyk <chenyunkuo.cyk@alibaba-inc.com >
2024-07-05 20:27:24 +08:00
Bubbliiiing
58d793659d
Update 768x768 Link and new gallery ( #15 )
...
update readme and model link
2024-06-04 10:47:57 +08:00
Bubbliiiing and zouxinyi0625
fb0916f4da
Update EasyAnimateV2 ( #5 )
...
* update EasyAnimateV2
* update datasets loader
* update datasets loader
* update fast api
* complete data preprocess pipeline.
* update lots of readme
* update readme bans
* fix bug in validation while training
* provide example for video cut
* update text box
* add arxiv
* delete IDDPM
* update gallery
* update arxiv
* update readme
* update readme
* link fix
* update vae readme
---------
Co-authored-by: zouxinyi0625 <zouxinyi.zxy@alibaba-inc.com >
2024-05-31 10:33:14 +08:00
bubbliiiing
1a1720cfa5
update readme and default params
2024-04-13 15:02:01 +08:00
bubbliiiing
ebe1a64a1c
Create Code
2024-04-12 17:42:52 +08:00
bubbliiiing