jackj 435e9fd667 Fix: Shape mismatch in extend mode causing AssertionError ...

- Added automatic shape alignment for target_latents and x0
- Handles both shorter (padding) and longer (trimming) cases
- Fixes crash in extend mode with long audio files
- Minimal impact on audio quality (~0.05-0.15 sec)

Resolves issue where extend mode fails with AssertionError
when target_latents shape doesn't match x0 shape after
padding/trimming operations.

2026-01-23 23:15:42 +05:00

..

language_segmentation

move language filters

2025-05-19 04:51:22 +02:00

models

Enable gradient checkpointing

2025-05-17 20:40:21 +08:00

music_dcae

fix decode_overlap_shorter

2025-05-11 15:04:40 +08:00

schedulers

fix audio2audio

2025-05-15 08:15:15 +00:00

ui

Add lora weight

2025-05-20 08:59:00 +03:00

__init__.py

format w/ black

2025-05-06 21:38:25 -07:00

apg_guidance.py

format w/ black

2025-05-06 21:38:25 -07:00

cpu_offload.py

int4 weight only quantized model using torchao

2025-05-09 20:27:25 +08:00

data_sampler.py

add more examples

2025-05-12 17:50:37 +00:00

gui.py

asign cuda device

2025-05-14 03:37:07 +00:00

pipeline_ace_step.py

Fix: Shape mismatch in extend mode causing AssertionError

2026-01-23 23:15:42 +05:00

text2music_dataset.py

fix imports

2025-05-11 11:28:12 -07:00