github/ai-toolkit
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Fix audio issues with ltx2 models. Silent codec fails now raised. Auto convert surround sound audio to stereo. Invalidate old caches just to be safe so they recache now.

Browse Source
This commit is contained in:
Jaret Burkett
2026-03-23 20:08:33 +00:00
parent 561e6f201c
commit 5642b656b9
8 changed files with 36 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
toolkit/data_loader.py
View File

@@ -491,6 +491,8 @@ class AiToolkitDataset(LatentCachingMixin, ControlCachingMixin, CLIPCachingMixin
latent_space_version = "sd1"
if self.sd is not None and self.sd.model_config.latent_space_version is not None:
latent_space_version = self.sd.model_config.latent_space_version
elif self.sd is not None and self.sd.latent_space_version is not None:
latent_space_version = self.sd.latent_space_version
elif self.sd.is_xl:
latent_space_version = 'sdxl'
elif self.sd.is_v3: