RandNMR73
aabf1fe135
inference works after changes added
...
new branch
Stop backprop through kv_cache
Enable timestep warping & using SelfForcing scheduler
checkpoint
text preprocessing ready
fix rotary embedding
Change Wan DiT to have 0 numerical diff with SF's Wan
wan2.2 training doesn't crash
training hangs
2025-09-23 22:20:29 +00:00
Wei Zhou and SolitaryThinker
359151d9a0
[Feature] Add wan2.2 5b i2v ( #760 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2025-08-28 18:15:59 -07:00
Wei Zhou and SolitaryThinker
ce67cd3729
[Feat] Support Self-Forcing's Causal Inference for Wan2.1 T2V 1.3B ( #766 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2025-08-28 16:47:49 -07:00
William Lin
3ef04f1654
[misc] [docs] Various fixes for logging and docs ( #758 )
2025-08-23 21:13:50 -07:00
Wenxuan Tan
989a03532c
Optionally use unmerged weights for inference ( #745 )
2025-08-22 15:20:31 -07:00
William Lin and RandNMR73
8cae5e4708
[feature] add Gradio live serving demo code ( #727 )
...
Co-authored-by: RandNMR73 <notomatthew31@gmail.com >
2025-08-10 15:34:03 -07:00
Wenxuan Tan
5357f63327
Fix LoRA load from training checkpoint ( #719 )
2025-08-09 20:46:00 -05:00
Wenxuan Tan
6c6bcd914d
Remove all empty_cache ( #713 )
2025-08-07 22:50:38 -07:00
Wei Zhou and SolitaryThinker
c41305ad18
[Feat] Add Wan2.2 14B MoE ( #688 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2025-08-06 20:31:03 -07:00
Wei Zhou
3b1b54a74d
Modify args to make sure the scripts are runnable on 4090 ( #671 )
2025-07-30 14:55:08 -07:00
Zhang Peiyuan
cbc3a6bb9d
[Feat] Support VSA with any resolution. ( #650 )
2025-07-28 20:14:40 -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
William Lin
f572319bd9
[Feature] Remove V1 folder ( #642 )
2025-07-24 22:43:12 -07:00
Wenxuan Tan and Wei 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 Chen and SolitaryThinker
4264a80ca9
[Feature] Add DMD inference pipeline ( #637 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2025-07-24 21:00:47 -07:00
Wenxuan Tan
210a733515
[Bugfix] Fix LoRA trainable params and training ckpt loading ( #630 )
2025-07-23 20:01:40 -07:00
Wenxuan Tan
bb8c769c8e
[LoRA] Support v1 LoRA training ( #576 )
2025-07-17 15:52:09 -05:00
RandNMR73
b79d1fc15b
video gen working on apple silicon (addressed issues from prior pr) ( #595 )
2025-07-15 22:04:27 -07:00
Wenxuan Tan
7244a4b27f
[CI] Add LoRA inference tests ( #546 )
2025-07-15 15:06:44 -05:00
Wenxuan Tan
ed1e8d6bad
[Feature] Offload all text encoders by default ( #594 )
2025-07-03 19:30:14 -05:00
William Lin
5f938b5844
[Revert] "[Feature] Load weights from distributed" ( #571 )
2025-06-28 20:55:14 -05:00
Wenxuan Tan
c5155b256e
[Feature] Load weights from distributed ( #470 )
2025-06-27 22:52:40 -05:00
Yongqi Chen
7664dd0de3
[Bugfix][Inference]Fix envs.attn_backend ( #525 )
2025-06-17 18:38:06 -05:00
Kevinzz and BrianChen1129
e3d0cbe185
[STA] Implement mask search for V1's Wan2.1 ( #415 )
...
Co-authored-by: BrianChen1129 <yongqich@umich.edu >
2025-06-05 15:03:31 -04:00
Wenxuan Tan
66b8b8561e
[LoRA] Support V1 LoRA inference ( #451 )
2025-06-04 16:19:29 -05:00
William Lin
0cf001986a
[Docs] More docs update ( #394 )
2025-05-11 16:19:47 -07:00
applesaucethebun and Brayden Zhong
51956369a5
[Misc] Replace instances of time.time() with time.perf_counter() ( #396 )
...
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca >
2025-05-11 15:56:39 -07:00
William Lin
9a91021c56
[Docs] Add collect_env.py and various docs update ( #393 )
2025-05-10 13:42:42 -07:00
William Lin
c69afce2f6
[Docs] Update for V1 ( #381 )
2025-05-06 16:34:44 -07:00
William Lin
2bf69b6f92
[Docs] Initial examples setup and more docs ( #332 )
2025-04-14 16:53:57 -07:00
RandNMR73