Commit Graph
40 Commits
Author SHA1 Message Date
Leojc 8f8c85693d Fix VAE and transformer loading for 5B model (#297) 2025-08-27 15:28:01 +08:00
Leojc 15d6fd8137 Fix typos (#298) 2025-08-27 15:27:28 +08:00
Bubbliiiing 6a13aa5116 Update 5b fun, fix bug in 5b multi gpus and fix bug in cogvideox-fun inference. (#289)
* Update 5b fun, fix bug in 5b multi gpus and fix bug in cogvideox-fun inference.
2025-08-20 11:20:37 +08:00
Bubbliiiing 7157cdd48a Update 5b comfyui && Update Camera control && Update fun training and Readme (#284)
Update 5b comfyui && Update Camera control && Update fun training and Readme
2025-08-13 19:20:11 +08:00
Bubbliiiing 24a5eed03b Update Wan 2.2 5b (#278) 2025-08-11 14:59:34 +08:00
Bubbliiiing 5631a8cac4 Update Wan2.2 Fun (#279)
* Update Wan2.2 Fun
2025-08-08 07:54:45 +08:00
Bubbliiiing 976121891e Merge pull request #274 from aigc-apps/saving
Convert model to weight dtype in saving
2025-08-04 14:49:46 +08:00
Bubbliiiing e7d3b597fb Fix offload bug in wan2.2 inference && Fix boundary bug in training (#271)
* Fix offload bug in wan2.2 inference

* Update boundary
2025-08-01 14:11:23 +08:00
flyingshan ee8c09416b fix(wan2.2 train): Fix high/low noise timestep schedule. (#270) 2025-08-01 13:38:15 +08:00
Bubbliiiing 4dc94d2b95 Update Wan2.2 UI && Add auto_tile_batch_size args in training && Rewrite Wan2.2 init (#269) 2025-07-30 19:54:27 +08:00
Bubbliiiing 9c05f3a741 Fix bug in Wan2.2 (#265) 2025-07-29 20:22:28 +08:00
Bubbliiiing 2d3a5cc7d6 Update Wan2.2 (#264) 2025-07-29 00:06:55 +08:00
Bubbliiiing 9702fc9db6 Merge pull request #246 from aigc-apps/comfyui_json
Update Readme and json
2025-07-04 15:52:53 +08:00
Bubbliiiing 541f789188 Fix last bug in saving (#241) 2025-07-02 12:14:14 +08:00
liubo0902and宣源 c2d0c7ae21 add ac (#225)
Co-authored-by: 宣源 <xuanyuan.lb@alibaba-inc.com>
2025-06-26 16:17:03 +08:00
Bubbliiiing 86028a9ce6 Update fix sample size && Fix vram memory bug in wan2.1 lora training (#227) 2025-06-24 10:09:23 +08:00
bubbliiiing a4476549e4 Update Training Code 2025-06-10 03:54:11 +00:00
bubbliiiing 72c2792139 Update Training 2025-06-09 09:42:32 +00:00
bubbliiiing e4c74a12f2 Update phantom && add fsdp training && Fix bug in image encoder while using sage attention 2025-06-09 08:25:49 +00:00
bubbliiiing a6a8383c45 Update Training Readme 2025-06-03 07:55:35 +00:00
Bubbliiiing ed4f10beef Fix bug in lora training && Update zero3 cpu offload && Teacache thresholds (#209) 2025-05-13 20:54:20 +08:00
Bubbliiiing f26f0a809b Update cfg skip to wrapper && Update Teacache && Update Reamde (#200) 2025-05-09 18:11:53 +08:00
Bubbliiiing 5e2f7fcdac Update Wan Fun V1.1 (#179) 2025-04-27 15:06:36 +08:00
Bubbliiiing 991e7cd2bd Api infer support (#167) 2025-04-14 18:54:13 +08:00
Bubbliiiing f149dba611 Update Riflex && Pipeline callback bug fix && Training Code bug fix (#150) 2025-04-09 15:23:38 +08:00
hkz f865b60e0a Update Reward LoRA (#155) 2025-04-07 15:00:47 +08:00
hkzandbubbliiiing 09e7bd2bd0 Support low_cpu_mem_usage=True for the text encoder of Wan2.1 (#146)
---------

Co-authored-by: bubbliiiing <3323290568@qq.com>
2025-04-01 11:35:42 +08:00
Bubbliiiing 10076a3aee Update control training code (#130) 2025-03-27 11:52:15 +08:00
Bubbliiiingandhuangkunzhe.hkz e1e7145c87 Update Wan and Wan-Fun (#125)
Update Wan and Wan-Fun

---------

Co-authored-by: huangkunzhe.hkz <huangkunzhe.hkz@alibaba-inc.com>
2025-03-26 17:49:51 +08:00
6c39567168 Update V1.5 (#79)
* Update V1.5

---------

Co-authored-by: huangkunzhe.hkz <huangkunzhe.hkz@alibaba-inc.com>
Co-authored-by: 梧岚 <lijiatong.ljt@alibabapictures.com>
2024-12-16 10:41:18 +08:00
hkz 8efec19966 Update reward backpropagation (#80) 2024-11-28 13:59:23 +08:00
hkz 2114d906df Add Reward LoRA Training (#71) 2024-11-22 09:45:59 +08:00
Bubbliiiing 24f6209b6d Fix bug in control model validation (#63)
* fix bug in control model validation

* fix bug in control model validation
2024-11-06 20:54:51 +08:00
hkz 2aa923b65c Fix validation bugs in training (#34) 2024-10-11 10:34:02 +08:00
Bubbliiiingandyunkchen 0a9b013f39 Update to V1.1 (#24)
* update README

* Update V1.1

* update v2v mask

* update contro model && update comyui && update ui && update readme

* Update README_zh-CN.md

* readme

* Update README.md

* readme

* Update Readme

* update readme

* Update README_TRAIN_CONTROL.md

Add DWPose suggest.

* Update tips in control video

---------

Co-authored-by: yunkchen <chenyunkuo.cyk@alibaba-inc.com>
2024-09-30 13:49:18 +08:00
Wang Qiang 937bac68fb Fix train.py: error: unrecognized arguments: --enable_xformers_memory_efficient_attention (#6)
Fix train.py: error: unrecognized arguments: --enable_xformers_memory_efficient_attention
2024-09-18 23:14:14 +08:00
Bubbliiiing 2e8d316e6e Update readme and report, fix bug in training code, gallery and 5b model (#2) 2024-09-18 11:56:37 +08:00
bubbliiiing 4ee00bb26b Rename && Update Readme 2024-09-10 11:26:18 +08:00
bubbliiiing ef55bd3bbe Rename && Update Readme 2024-09-10 11:22:35 +08:00
bubbliiiing f660725fa5 Create Code 2024-09-10 10:29:13 +08:00