Ethanfel
5acaffab92
Adapted from HunyuanVideo-FoleyTune for the audio-SR workflow: - UniverSR Load Video Audio: extract a video's audio track via ffmpeg (WAV pipe + soundfile, no torchcodec) and carry a UNIVERSR_VIDEO reference forward, with an inline video preview. - UniverSR Video Combiner: mux the enhanced audio back onto the source video without re-encoding video (-c:v copy), trim-aware, with output auto-increment and preview. Both registered alongside the SR nodes; ffmpeg + soundfile required only for these. Adds README docs and an example video workflow. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
12 lines
416 B
Plaintext
12 lines
416 B
Plaintext
# 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
|
|
# Video loader/combiner nodes only — read/write WAV for ffmpeg muxing.
|
|
# (ffmpeg itself must be installed separately and on PATH.)
|
|
soundfile>=0.12
|