Aryan Kumar
4d06f795dc
The FL2VA profile reads keyframe-anchor rows (build_packed_sequence anchors, noised like inference); the coverage builder's --mode fl2va makes them from the v4 rows' exact first/last frames re-encoded at the canvas size with the FL2VA Qwen3-VL presentation; the keyframe-fidelity guard covers the FL2VA tasks.
Training Configs
Single-step training configurations organized by method and model.
configs/
├── fine_tuning/ # Standard finetuning and DFSFT
├── distribution_matching/ # DMD2 and Self-Forcing
├── knowledge_distillation/ # KD from teacher to student
└── example.yaml # Annotated reference config with all fields
Each method directory contains per-model subdirectories (e.g. wan/, hunyuan/).
Launch any config with:
bash examples/train/run.sh examples/train/configs/<method>/<model>/<config>.yaml
For multi-step training pipelines, see examples/train/scenario/.