Ethanfel 6474e2816c fix: two bugs in SelVA nodes ...

- selva_feature_extractor: cache hash now includes resolved duration;
  same video + different duration override no longer returns stale features
- selva_sampler: MPS-safe noise generation (torch.Generator on CPU then
  move to device, same pattern as PrismAudioSampler)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-04-04 15:39:57 +02:00

..

__init__.py

feat: SelvaModelLoader node — loads TextSynch + MMAudio + FeaturesUtils

2026-04-04 15:21:03 +02:00

feature_extractor.py

fix: return fps from non-cache extraction path

2026-03-28 11:26:15 +01:00

feature_loader.py

feat: PrismAudioFeatureLoader node for pre-computed .npz files

2026-03-27 18:04:32 +01:00

model_loader.py

debug: fix VAE load_state_dict diagnostic — load into .model directly

2026-03-27 21:56:06 +01:00

sampler.py

chore: update default steps=100 and cfg_scale=7.0

2026-03-28 11:03:48 +01:00

selva_feature_extractor.py

fix: two bugs in SelVA nodes

2026-04-04 15:39:57 +02:00

selva_model_loader.py

feat: SelvaModelLoader node — loads TextSynch + MMAudio + FeaturesUtils

2026-04-04 15:21:03 +02:00

selva_sampler.py

fix: two bugs in SelVA nodes

2026-04-04 15:39:57 +02:00

text_only.py

chore: update default steps=100 and cfg_scale=7.0

2026-03-28 11:03:48 +01:00

utils.py

feat: project scaffolding with shared utils and node registration

2026-03-27 16:59:21 +01:00