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

Initial release: ComfyUI-UniverSR

Browse Source 
ComfyUI nodes for UniverSR (ICASSP 2026) — vocoder-free audio
super-resolution (8/12/16/24 kHz → 48 kHz) via flow matching.

- UniverSR Model Loader: presets auto-download to models/universr,
  plus local dir / raw .pth (from_local) loading, with caching.
- UniverSR Super-Resolution: chunked overlap-add for long audio,
  per-channel stereo, seed control with global-RNG isolation,
  wet/dry blend, and an optional before/after spectrogram.
- Vendors the universr inference package under vendor/ (prefers an
  installed copy); only extra dep beyond ComfyUI's stack is torchdiffeq.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Ethanfel
2026-06-01 12:59:42 +02:00
commit 5f29b225b7
20 changed files with 2129 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
requirements.txt
+8
View File
@@ -0,0 +1,8 @@
# ComfyUI-UniverSR runtime deps.
# torch / torchaudio / numpy / matplotlib are already shipped by ComfyUI.
# The vendored `universr` package only needs these extras on top of ComfyUI's stack:
torchdiffeq>=0.2.3
einops>=0.7
timm>=0.9
huggingface_hub>=0.20
pyyaml>=6.0