- tensorflow-cpu==2.15.0 only supports Python <=3.11; relax to >=2.16.0
- capture_output=False so pip errors are visible in ComfyUI logs
- clean up incomplete venv dir before retrying install
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
vae.ckpt is a full training checkpoint containing discriminator, STFT
loss modules, and EMA wrappers that are absent from the inference
AudioAutoencoder. strict=False ignores these training-only keys while
still loading all encoder/decoder/bottleneck weights correctly.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
einops-exts, vector-quantize-pytorch, scipy were imported by prismaudio_core
but not listed in requirements.txt.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
ComfyUI does not add the custom node directory to sys.path automatically,
so prismaudio_core (a package inside the plugin dir) was not found at runtime.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
PrismAudioFeatureExtractor now creates and populates a managed venv
(_extract_env/) automatically when python_env is left as the default
'python'. Also adds scripts/install_extract_env.sh for manual/Docker
setup without conda.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
MMDiTWrapper was removed from diffusion.py during cleanup but the import
in factory.py was missed, causing ImportError on every model load.
Also stub wavelet and diffusion_prior paths that reference deleted modules.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Ethanfel