Aryan Kumar 4d06f795dc [feat]: Pika H3 Flex FL2VA QAD data path (T2VA / I2VA / L2VA / FL2VA keyframe rows) ...

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.

2026-10-31 11:04:04 -07:00

..

datasets

[misc]: consolidate dataset download scripts under examples/datasets/ (#1667)

2026-08-02 14:21:24 -07:00

distill

[misc]: Refactor separate training pipeline runner (#1696)

2026-10-07 03:19:21 -07:00

inference

[docs]: document FA4, bucket, duration, and offload choices for Pika H3 Flex

2026-10-29 18:51:52 -07:00

serving

Revert "[new-model] Add PAN2 text-to-video and image-to-video" (#2025)

2026-10-27 18:03:59 -07:00

train

[feat]: Pika H3 Flex FL2VA QAD data path (T2VA / I2VA / L2VA / FL2VA keyframe rows)

2026-10-31 11:04:04 -07:00

training

[feat] Add end-to-end MMAudio V2A training, inference, and evaluation (#1648)

2026-10-07 04:25:00 -07:00