hao-ai-lab-FastVideo

Files

T

SolitaryThinker bbbb7ab021 [refactor]: migrate examples/scripts to typed VideoGenerator API; rename api/compat.py to api/translation.py

Move all examples/inference and scripts off the legacy
VideoGenerator.from_pretrained(model, **kwargs) +
generate_video(prompt, **kwargs) surface onto the typed
from_config(GeneratorConfig(...)) + generate(GenerationRequest(...))
convention, including the Kandinsky-5 and DreamX-World examples added
on main after the original migration. git-mv api/compat.py to
api/translation.py ('compat' implied a temporary shim; the forward
translation is its honest permanent role) and repoint all importers,
tests, and doc links.

2026-07-11 03:26:24 -07:00

checkpoint_conversion

[refactor]: migrate examples/scripts to typed VideoGenerator API; rename api/compat.py to api/translation.py

2026-07-11 03:26:24 -07:00

dataset_preparation

[3/3][Preprocess] add preprocessing workflows (#645 )

2025-08-07 01:49:07 -07:00

distill

[bugfix] [misc] Use training_state_checkpointing_steps in scripts/ (#846 )

2025-10-19 20:20:53 -07:00

finetune

[Misc] clean up VSA finetuning examples. (#1111 )