shaoxiongduan ac919b1c87 [feat] WanTrack: OpenVid preprocess + Wan2.2 synthetic-gen pipeline, training configs, first-frame saturation fix ...

- data_pipeline: SAM+CoTracker preprocessing, sharded Slurm launchers, OpenVid download/filter,
  and a data-parallel Wan2.2-T2V-A14B synthetic video generator with the first-frame
  over-brightness fix (over-generate 129 -> drop first 8 -> keep 121).
- examples/train: OpenVid bidir/stage2/stage3 launchers + finetune YAMLs (sparse, merged,
  merged_bias, stage2v2 hi-lr, stage3A/B/C).
- research_log: first-frame saturation root-cause writeup (DiT position-0 latent, not VAE decode).
- fastvideo: trackwan model / track-encoder / preprocessing updates, dcp_to_diffusers export, FA4.

2026-07-14 08:58:22 +00:00

..

hyworld

[Refactor] SP Mask --> original seq len; HunyuanVideo 1.5 does not need mask (#1142)

2026-03-04 11:44:47 +08:00

lingbotworld

[Refactor] SP Mask --> original seq len; HunyuanVideo 1.5 does not need mask (#1142)

2026-03-04 11:44:47 +08:00

matrixgame2

[misc] Rename MatrixGame to MatrixGame2 (#1357)

2026-05-17 22:57:03 -07:00

matrixgame3

[feat] Add MatrixGame3.0 (#1201)

2026-05-27 21:07:01 +00:00

trackwan

[feat] WanTrack: OpenVid preprocess + Wan2.2 synthetic-gen pipeline, training configs, first-frame saturation fix

2026-07-14 08:58:22 +00:00

base.py

[Misc] Remove Teacache (#1121)

2026-02-22 16:53:07 -08:00

causal_wanvideo.py

[fix] Fix causal self-forcing attention settings (#1355)

2026-05-17 22:59:47 -07:00

cosmos2_5.py

[feat] Add Cosmos 2.5 T2W training pipeline (LoRA + full fine-tune) (#1227)

2026-05-11 19:15:00 -07:00

cosmos.py

[feat] Cosmos 2.5 training support in fastvideo.train (#1224)

2026-05-01 01:15:02 +00:00

flux_2.py

[model] Flux2 Klein Port (#1349)

2026-06-09 14:55:55 -07:00

gen3c.py

[feat] add gen3c (cosmos-7b) model and pipeline support (#1059)

2026-04-01 11:42:02 +00:00

hunyuangamecraft.py

[Misc] Remove Teacache (#1121)

2026-02-22 16:53:07 -08:00

hunyuanvideo15.py

[Refactor] SP Mask --> original seq len; HunyuanVideo 1.5 does not need mask (#1142)

2026-03-04 11:44:47 +08:00

hunyuanvideo.py

[Refactor] SP Mask --> original seq len; HunyuanVideo 1.5 does not need mask (#1142)

2026-03-04 11:44:47 +08:00

kandinsky5.py

Kandinsky5 lite dit clean (#1088)

2026-03-26 08:07:11 +08:00

longcat.py

[feat]: add LongCat bidirectional finetuning support (#1244)

2026-05-09 12:20:43 -07:00

ltx2.py

[feat] dreamverse: sequence parallelism for serving (#1424)

2026-06-01 23:13:49 -07:00

magi_human.py

[feat]: MagiHuman DiT (transformer) port + parity tests (3/8) (#1297)

2026-05-12 14:49:03 -07:00

sd3.py

[feat] pre-commit support 120 col num (#1167)

2026-03-11 20:19:30 -07:00

stable_audio.py

[feat] Stable Audio Open 1.0: T2A + A2A + RePaint inpainting (native) (#1260)

2026-05-01 00:07:11 -07:00

wanvideo.py

[refactor]: linear/mlp FP4 path additions for Wan-2.1 (Attn-QAT 6/12) (#1390)

2026-06-08 14:51:57 -07:00