Files

T

Aryan Kumar 6e2cd716f0 [misc]: summarize wrapped layers an adapter has no weights for

An adapter that trains a subset of the wrapped linears (Pika skips the
AdaLN projections) logged one warning per layer, about 200 per run.
Log one summary with the count and a few names.

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

basic

[bugfix]: keep released lazy modules released when an adapter attaches

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

preprocess

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

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

stages

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

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

training

[feat] Optimize distributed weight loading in multi-node training (#572 )

2026-05-21 16:59:48 +00:00

__init__.py

[misc] Support partial Hugging Face model downloads (#1684 )

2026-08-06 16:09:46 -07:00

AGENTS.md

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

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

composed_pipeline_base.py

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

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

lazy_module.py

[bugfix]: don't reload a lazy module from inside its own materialize transform

2026-10-29 17:37:52 -07:00

lora_pipeline.py

[misc]: summarize wrapped layers an adapter has no weights for

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

pipeline_batch_info.py

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

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

pipeline_registry.py

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

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

README.md

[Feature] Remove V1 folder (#642 )

2025-07-24 22:43:12 -07:00

README.md

Adding a New Custom Pipeline

Please see documentation here