af78c759f1
[new-model] Add Wan2.2-Animate-14B character animation/replacement inference ( #1765 )
...
Co-authored-by: SuhaanCommits <suhaan@cedar.build >
Co-authored-by: Claude Fable 5 <noreply@anthropic.com >
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-10-07 04:19:37 -07:00
Haochen Jiang and Claude Opus 5.5
299d0f6838
[bugfix] wrap the generic DenoisingStage in the inference_denoising profiler region ( #1707 )
...
profiler_region_inference_denoising was wrapped in exactly one place (minimax_h3_denoising.py), so every model using the generic DenoisingStage (Wan among them) exported a trace with no denoising region. Wrap the denoising loops in DenoisingStage and DmdDenoisingStage with profiler_region("inference_denoising"); the loop bodies are untouched.
These are the two classes STAGE_METRIC_MAP names directly. The perf harness also reports dit_time_s for every stage that inherits performance_component_metric, and those forward overrides (Cosmos*, LongCat*, Gen3C, GameCraft, HYWorld, MatrixGame2/3, Causal*, DreamXWorldAR, LingBot, GlmImage) remain outside the region for now. With no profiler configured the wrap is a no-op; SSIM is exactly 1.0 on FLASH_ATTN and TORCH_SDPA.
Caveat: the region span now appears in exported traces, but a pre-existing profiler behaviour (region exit toggles CUDA collection off, fastvideo/profiler.py) may leave GPU kernel rows out of the trace.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-07 03:19:42 -07:00
5d515ee617
[perf]: remove per-step host syncs and repeated work from causal inference ( #1687 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-07 03:18:56 -07:00
6e4813f8b4
[bugfix] use in-process executor for num_gpus=1 ( #1755 ) ( #1879 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-07 02:18:23 -07:00
ef62ac48d1
[new-model] Add Wan2.2-S2V-14B speech-to-video (model port + checkpoint converter) ( #1683 )
...
Co-authored-by: SuhaanCommits <suhaan@cedar.build >
Co-authored-by: Claude Fable 5 <noreply@anthropic.com >
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-10-07 01:36:01 -07:00
William Lin
556ac7088e
[refactor] Simplify Wan sampling and tests ( #1825 )
2026-09-07 15:57:19 -07:00
Aryan Kumar and Aryan Kumar
7f539424cb
[feat]: add Lucy Edit inference scaffold ( #1363 )
...
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com >
2026-06-09 15:21:43 -07:00
William Lin
145a3f166b
[feat] [4/n] Improve API: refactor sampling param and merge with presets ( #1234 )
2026-04-16 14:10:02 -07:00
alexzms
14261bc98c
[feat] pre-commit support 120 col num ( #1167 )
2026-03-11 20:19:30 -07:00
alexzms and Peiyuan Zhang
bc27a032c5
[feat] Refactor training framework into fastvideo/train ( #1159 )
...
Co-authored-by: Peiyuan Zhang <a1286225768@gmail.com >
2026-03-09 15:16:42 -07:00
alexzms
2b13e117f0
[Feat] Add causal Wan pipeline with multi-step denoising ( #1161 )
2026-03-08 13:32:04 -07:00
William Lin
3ff640b2e6
[bigfix] [distillation] Fix DMD inference pipeline noise initialization shape ( #921 )
2025-12-08 13:00:48 -08:00
e3b4564d5a
[feat] Add inference for MoE SF ( #880 )
...
Co-authored-by: RandNMR73 <notomatthew31@gmail.com >
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2025-11-19 13:16:24 -08:00
Jiali Chen
404314d00f
[Feature]Add video-to-video (V2V) pipeline ( #829 )
2025-10-12 21:53:05 -07:00
dc7596b973
[self-forcing][8/n] Self-Forcing For Wan2.2-A14B + torch.compile training and distillation support ( #818 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-10-02 15:01:45 -07:00
31f000d1cc
[self-forcing] [5/n] Add Self-Forcing distillation pipeline ( #808 )
...
Co-authored-by: RandNMR73 <notomatthew31@gmail.com >
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2025-09-20 19:32:10 -07:00
William Lin and RandNMR73
ac11127397
[Self-forcing] [1/n] Handle extra dim in time embedding and add timestep warping ( #792 )
...
Co-authored-by: RandNMR73 <notomatthew31@gmail.com >
2025-09-09 02:52:02 -07:00
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
6ceb4942a0
[bugfix] [dmd] Fix backward simulation and also naming in wan_i2v_dmd_pipeline ( #731 )
2025-08-10 21:13:30 -07:00
Jinzhe Pan
86604a684b
[3/3][Preprocess] add preprocessing workflows ( #645 )
2025-08-07 01:49:07 -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
Yongqi Chen
c9005045dc
[Feature[[Readme] Add VSA/DMD doc ( #673 )
2025-08-02 02:35:46 -04:00
Yongqi Chen
109e2e7e9d
[Bugfix]Fix DMD wan pipeline ( #659 )
2025-07-28 21:50:44 -07:00
Jinzhe Pan
7b6c8aee99
[2/3][Preprocess] refactor pipeline registry & file structure ( #639 )
2025-07-27 23:30:17 -07:00
