Ethanfel 578b501d38 feat: SelvaFeatureExtractor — inline CLIP + TextSynchformer feature extraction ...

CLIP frames at 8fps→384px (normalize inside FeaturesUtils).
Sync frames at 25fps→224px, normalized to [-1,1] externally.
T5 text encoded via FeaturesUtils, sup tokens prepended, then text-conditioned
sync features extracted via TextSynch.encode_video_with_sync(). Results cached
as .npz keyed by hash(frames[:1MB] + prompt + fps + variant).

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

2026-04-04 15:23:40 +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

feat: SelvaFeatureExtractor — inline CLIP + TextSynchformer feature extraction

2026-04-04 15:23:40 +02:00

selva_model_loader.py

feat: SelvaModelLoader node — loads TextSynch + MMAudio + FeaturesUtils

2026-04-04 15:21:03 +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