Ethanfel/ComfyUI-SelVA
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: SelvaModelLoader node — loads TextSynch + MMAudio + FeaturesUtils

Browse Source 
Resolves weights from models/selva/. Reuses synchformer_state_dict.pth from
models/prismaudio/ (no duplicate download). Supports four variants:
small_16k / small_44k / medium_44k / large_44k.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Ethanfel
2026-04-04 15:21:03 +02:00
parent 6bc3fd6443
commit fe94438356
2 changed files with 122 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nodes/__init__.py
+3
View File
@@ -7,6 +7,9 @@ _NODES = {
"PrismAudioFeatureExtractor": (".feature_extractor", "PrismAudioFeatureExtractor", "PrismAudio Feature Extractor"),
"PrismAudioSampler": (".sampler", "PrismAudioSampler", "PrismAudio Sampler"),
"PrismAudioTextOnly": (".text_only", "PrismAudioTextOnly", "PrismAudio Text Only"),
"SelvaModelLoader": (".selva_model_loader", "SelvaModelLoader", "SelVA Model Loader"),
"SelvaFeatureExtractor": (".selva_feature_extractor", "SelvaFeatureExtractor", "SelVA Feature Extractor"),
"SelvaSampler": (".selva_sampler", "SelvaSampler", "SelVA Sampler"),
}
for key, (module_path, class_name, display_name) in _NODES.items():