Ivan Zorin 965d0ed509 fix: remove normalization of audio in LTX Mel spectrogram creation (#11990) ...

For LTX Audio VAE, remove normalization of audio during MEL spectrogram creation.
This aligs inference with training and prevents loud audio from being attenuated.

2026-01-20 18:44:28 -05:00

..

vae

fix: remove normalization of audio in LTX Mel spectrogram creation (#11990)

2026-01-20 18:44:28 -05:00

vocoders

Support the LTXV 2 model. (#11632)

2026-01-05 01:58:59 -05:00

av_model.py

Reduce LTX2 VRAM use by more efficient timestep embed handling (#11829)

2026-01-12 17:28:59 -05:00

embeddings_connector.py

Fix lowvram issue with ltxv2 text encoder. (#11675)

2026-01-06 17:33:03 -05:00

latent_upsampler.py

Support the LTXV 2 model. (#11632)

2026-01-05 01:58:59 -05:00

model.py

Support the LTXV 2 model. (#11632)

2026-01-05 01:58:59 -05:00

symmetric_patchifier.py

Support the LTXV 2 model. (#11632)

2026-01-05 01:58:59 -05:00