convert_droid.py builds a set where the first frame is similar but motion is
diverse, the design that forces trace reliance: it scans DROID (LeRobot mirror),
clusters frame-0 embeddings, and writes the tightest cluster as 121-frame libx264
mp4s + manifest with ONE generic caption, dropping straight into extract_tracks ->
i2v_track preprocess. Adds finetune_wantrack_droid_overfit.yaml (Fun-Control init,
WANTRACK_AUG=0 clean overfit, fresh output_dir) and gitignores .gradio/.
shaoxiongduan
b588be05d1