tianwei-moandClaude Opus 5.5 229c43c8d3 [feat] MiniMax-H3 Ref2VA SFT: train each clip at its own canvas and frame count (#2003) ...

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

2026-11-05 01:12:34 +00:00

..

callbacks

[feat] Add H3 PDD/DMPDD training and packed Ref2VA preprocessing (#1984)

2026-10-20 11:15:57 -07:00

fixtures

[misc] Remove DreamX World, HunyuanGameCraft, GLM-Image, LongCat, TurboDiffusion, and Z-Image (#1926)

2026-10-14 23:16:32 -07:00

methods

[ci] Run single-GPU CI lanes on a DGX Spark runner; weekly full suite on main (#2007)

2026-10-22 13:44:55 -07:00

models

[feat] MiniMax-H3 Ref2VA SFT: train each clip at its own canvas and frame count (#2003)

2026-11-05 01:12:34 +00:00

trainer

[feat] Add H3 PDD/DMPDD training and packed Ref2VA preprocessing (#1984)

2026-10-20 11:15:57 -07:00

utils

[feat]: shared FastH3 NVFP4 FP4-attention QAD recipe (OmniRef + V2 T2AV) (#1989)

2026-11-03 00:54:28 -08:00

__init__.py

[ci] add CPU unit tests for fastvideo.train load_run_config (#1264)

2026-04-28 01:06:18 +00:00