hao-ai-lab-FastVideo

Files

T

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

checkpoint_conversion

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

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

dataset_preparation

[3/3][Preprocess] add preprocessing workflows (#645 )

2025-08-07 01:49:07 -07:00

distill

[bugfix] [misc] Use training_state_checkpointing_steps in scripts/ (#846 )

2025-10-19 20:20:53 -07:00

finetune

[Misc] clean up VSA finetuning examples. (#1111 )