Files
hao-ai-lab-FastVideo/examples/inference
shaoxiongduan 21f25791e2 [feat] WanTrack: MotionStream-aligned track sampling + motion-CFG + Wan-200 cfg
- _augment_tracks: default random 1000-2500 track sampling (was 1-200), contiguous
  chunk masking (was per-frame), diversity weighting (favor moving/unique tracks,
  keep some static), and an object-coverage hook (>=1 track per SAM segment via
  optional object_ids). Sampling ON by default; CFG dropout now default off.
- trackwan_infer.generate: motion classifier-free guidance (guidance_scale) using
  the base no-tracks I2V branch as the unconditional.
- test_motion_cfg.py: quick guidance-scale EPE sweep.
- finetune_wantrack_wan200.yaml: 50->200 data-scale run (same params).
2026-07-02 07:05:14 +00:00
..
2026-02-23 15:14:42 -08:00