Spaces:

dimensionalpulsar
/

cinemai

Sleeping

cinemai / packages

522 kB

Ctrl+K

7 contributors

dimensionalpulsar

fix: use original user audio directly in output video for accurate lip-sync (bypass audio VAE decoder); fix _write_audio mono-to-stereo auto-conversion to prevent ValueError on single-channel input

c8adf51 about 2 months ago

ltx-core
fix: wrap flash_attn_interface import in try/except (OSError/ImportError) - prevents libcudart.so.12 crash at module load time on ZeroGPU; add graceful FA3 fallback to PyTorch SDPA in DEFAULT attention about 2 months ago
ltx-pipelines
fix: use original user audio directly in output video for accurate lip-sync (bypass audio VAE decoder); fix _write_audio mono-to-stereo auto-conversion to prevent ValueError on single-channel input about 2 months ago