 Jinzhe Pan
|
7b6c8aee99
|
[2/3][Preprocess] refactor pipeline registry & file structure (#639)
|
2025-07-27 23:30:17 -07:00 |
|
|
Yongqi Chen
|
6284eaa363
|
[Feature][Distill]Add DMD+VSA joint training example (#654)
|
2025-07-27 18:18:01 -04:00 |
|
|
Yongqi Chen
|
636524e87f
|
[Feature] Add Wan-14B-T2V-VSA CLI inference; add master port args (#653)
|
2025-07-27 07:13:44 -04:00 |
|
|
Yongqi Chen
|
202b2f3972
|
[Feature] Ignore [union-attr] and [override] mypy check and remove from training (#652)
|
2025-07-27 04:34:38 -04:00 |
|
|
Yongqi Chen
|
247fe273d8
|
[Feature] Add DMD T2V training pipeline (#651)
|
2025-07-27 03:35:51 -04:00 |
|
|
William Lin
|
cb320dfa3a
|
[bugfix] VideoGenerator improperly extracts output_video_name (#649)
|
2025-07-26 19:46:26 -07:00 |
|
|
Kevin Lin
|
d8bb5abc46
|
[CI] Fix ComfyUI publisher ID (#648)
|
2025-07-25 19:02:52 -07:00 |
|
|
Kevin Lin
|
cc703eca51
|
[CI] Add publish workflow for ComfyUI (#647)
|
2025-07-25 18:39:05 -07:00 |
|
|
William Lin
|
81c9df629c
|
[core] Add offloading for vae and image encoder and rename offloading args (#643)
|
2025-07-25 17:55:03 -07:00 |
|
|
Yongqi Chen
|
d3c0c52208
|
[Feature] Add prompt_txt support for CLI inference; Add DMD CLI inference (#646)
|
2025-07-25 19:44:10 -04:00 |
|
|
William Lin
|
744e0555c0
|
[misc] Use FASTVIDEO_STAGE_LOGGING for perf timing of stage (#644)
|
2025-07-25 16:20:53 -07:00 |
|
|
Jinzhe Pan
|
3a38f7dfdc
|
[1/3][Preprocess] refactor preprocessing configs (#638)
|
2025-07-25 14:27:12 -07:00 |
|
|
William Lin
|
f572319bd9
|
[Feature] Remove V1 folder (#642)
|
2025-07-24 22:43:12 -07:00 |
|
|
Wenxuan TanandWei Feng
|
48528f468c
|
[Feature] Multi-lora inference (#640)
Co-authored-by: Wei (Will) Feng <134637289+weifengpy@users.noreply.github.com>
|
2025-07-24 21:01:28 -07:00 |
|
|
Yongqi ChenandSolitaryThinker
|
4264a80ca9
|
[Feature] Add DMD inference pipeline (#637)
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
|
2025-07-24 21:00:47 -07:00 |
|
|
William Lin
|
8573d4f05e
|
[Docs] Docs update for Training and MPS (#641)
|
2025-07-24 19:23:58 -07:00 |
|
|
Wenxuan Tan
|
210a733515
|
[Bugfix] Fix LoRA trainable params and training ckpt loading (#630)
|
2025-07-23 20:01:40 -07:00 |
|
|
William Lin
|
0aef0e6f63
|
[bugfix] Fix preprocessing pipelines and nightly tests (#633)
|
2025-07-22 22:44:25 -07:00 |
|
|
Kevin Lin
|
dd022ad9be
|
[CI] Fix CI for pull request targets other than main (#632)
|
2025-07-22 21:00:03 -07:00 |
|
|
William Lin
|
832ad61e5b
|
[bugfix] fa3 no longer returns lse (#631)
|
2025-07-22 18:31:34 -07:00 |
|
|
Wenxuan Tan
|
9419c04ee3
|
Fix lora train steps (#627)
|
2025-07-21 23:29:30 -05:00 |
|
|
Zhang Peiyuanandroot
|
a37b39d83c
|
Py/add triton block sparse (#593)
Co-authored-by: root <a1286225768@gmail,com>
|
2025-07-17 16:50:40 -07:00 |
|
|
Wenxuan Tan
|
bb8c769c8e
|
[LoRA] Support v1 LoRA training (#576)
|
2025-07-17 15:52:09 -05:00 |
|
|
William Lin
|
576c214f28
|
[v0] Remove V0 code (#621)
|
2025-07-15 22:05:16 -07:00 |
|
|
RandNMR73
|
b79d1fc15b
|
video gen working on apple silicon (addressed issues from prior pr) (#595)
|
2025-07-15 22:04:27 -07:00 |
|
|
William Lin
|
eb66e1c18d
|
[chore] release 0.1.2 (#622)
|
2025-07-15 14:42:54 -07:00 |
|
|
William Lin
|
616d43c1cf
|
[bugfix] [training] use separate generator for validation (#610)
|
2025-07-15 13:19:38 -07:00 |
|
|
Wenxuan Tan
|
7244a4b27f
|
[CI] Add LoRA inference tests (#546)
|
2025-07-15 15:06:44 -05:00 |
|
|
Yongqi Chen
|
7e5ebb4582
|
[Feature][Training]Update example fine-tuning scripts to enable gradient checkpointing (#618)
v0.1.2
|
2025-07-15 11:22:56 -07:00 |
|
|
Wenxuan Tan
|
65ed588570
|
Set encoder TP size to 1 by default (#569)
|
2025-07-09 17:44:24 -05:00 |
|
|
Wenxuan Tan
|
14adfe2edc
|
Remove all unnecessary torch.cuda.empty_cache (#606)
|
2025-07-09 16:45:20 -05:00 |
|
|
William Lin
|
6198c6a640
|
[docs] update dev guide runpod image to py3.12 (#602)
|
2025-07-07 19:56:07 -05:00 |
|
|
William Lin
|
e6b71b531b
|
[docs] Update slack invite (#601)
|
2025-07-07 14:20:42 -05:00 |
|
|
William Lin
|
ae1d112c6a
|
[bugfix] [training] fix deadlock in latent datasets and init error in multi-node training (#598)
|
2025-07-06 01:34:15 -05:00 |
|
|
William Lin
|
bf4de1f38f
|
[chore] Upgrade min Python version from 3.8 to 3.10 (#597)
|
2025-07-04 22:08:31 -05:00 |
|
|
William Lin
|
66fdcc8e76
|
[Training] Use inference pipeline for training validation (#585)
|
2025-07-04 17:23:55 -05:00 |
|
|
Wenxuan Tan
|
ed1e8d6bad
|
[Feature] Offload all text encoders by default (#594)
|
2025-07-03 19:30:14 -05:00 |
|
|
Kevin Lin
|
b9423ca3f8
|
Add ComfyUI custom node for inference (#596)
|
2025-07-03 16:09:03 -05:00 |
|
|
Wenxuan Tan
|
ad16289871
|
[LoRA] Fix lora merge weights (#579)
|
2025-07-02 00:12:52 -05:00 |
|
|
Wenxuan Tan
|
2a41da1e6b
|
Fix VAE precisions (#588)
|
2025-07-01 14:49:04 -05:00 |
|
|
William Lin
|
32133171da
|
[chore] Release 0.1.1 (#592)
v0.1.1
|
2025-07-01 01:43:12 -05:00 |
|
|
Kevin Lin
|
19674c6f29
|
[CI] Fix fork builds (#590)
|
2025-07-01 01:03:34 -05:00 |
|
|
Yongqi Chen
|
508afb7002
|
[docs] Update Readme (#591)
|
2025-06-30 23:48:45 -05:00 |
|
|
Yongqi Chen
|
288ea88105
|
[Feat][Training] Rename weight conversion function and update gradient checkpoint in scripts (#589)
|
2025-07-01 00:20:02 -04:00 |
|
|
Jinzhe Pan
|
eb0f1318f3
|
[Feat] activation checkpointing (#584)
|
2025-06-30 15:24:29 -05:00 |
|
|
William Lin
|
ce9b5910cc
|
[Training] add caption to validation log (#582)
|
2025-06-30 02:42:17 -05:00 |
|
|
William Lin
|
d0e5a6214a
|
[misc] [training] Add --video_length_tolerance_range 10 to preprocessing scripts (#581)
|
2025-06-30 02:21:22 -05:00 |
|
|
Wenxuan Tan
|
834562b2db
|
[CI] Fix pre-commit CI (#578)
|
2025-06-29 16:52:29 -05:00 |
|
|
Wei (Will) Feng
|
060cc7b9ba
|
fully_shard usage on RMSNorm (#577)
|
2025-06-29 16:35:24 -05:00 |
|
|
Yongqi Chen
|
6c58a5ba62
|
[Bugfix]Fix VSA sp for training/inference (#574)
|
2025-06-29 13:44:33 -05:00 |
|