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

fix: remove FlashSR (audiosr incompatible with Python 3.12), add training loss CSV

Browse Source 
- Drop SelvaFlashSR node — audiosr pins numpy<=1.23.5 which cannot build
  on Python 3.12 (pkgutil.ImpImporter removed); use Saganaki22/ComfyUI-AudioSR instead
- BigVGAN trainer now writes <output_stem>_training_log.csv alongside the
  checkpoint: step, total, fm, mel, stft, phase, l2sp columns, line-buffered
  so loss can be tailed live during training

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Ethanfel
2026-04-09 17:18:34 +02:00
parent 8371466e44
commit 8ccc2438e4
3 changed files with 12 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nodes/__init__.py
-1
View File
@@ -30,7 +30,6 @@ _NODES = {
"SelvaDatasetItemExtractor": (".selva_dataset_pipeline", "SelvaDatasetItemExtractor", "SelVA Dataset Item Extractor"),
"SelvaDatasetSaver": (".selva_dataset_pipeline", "SelvaDatasetSaver", "SelVA Dataset Saver"),
"SelvaHarmonicExciter": (".selva_audio_postprocess", "SelvaHarmonicExciter", "SelVA Harmonic Exciter"),
"SelvaFlashSR": (".selva_audio_postprocess", "SelvaFlashSR", "SelVA FlashSR"),
"SelvaOutputNormalizer": (".selva_audio_postprocess", "SelvaOutputNormalizer", "SelVA Output Normalizer"),
}