aeiou alias-free-torch==0.0.6 auraloss==0.4.0 descript-audio-codec==1.0.0 decord==0.6.0 einops einops_exts ema-pytorch==0.2.3 encodec==0.1.1 huggingface_hub importlib-resources==5.12.0 k-diffusion==0.1.1 laion-clap==1.1.6 local-attention==1.8.6 pandas==2.0.2 pedalboard==0.9.14 prefigure==0.0.9 pytorch_lightning==2.4.0 PyWavelets==1.4.1 safetensors sentencepiece==0.1.99 torch>=2.0.1 torchaudio>=2.0.2 torchmetrics==0.11.4 tqdm transformers v-diffusion-pytorch==0.0.2 vector-quantize-pytorch==1.9.14 wandb webdataset==0.2.48 x-transformers<1.27.0
Make AudioX avialbe in ComfyUI.
AudioX: Diffusion Transformer for Anything-to-Audio Generation.
cd ComfyUI/custom_nodes
git clone https://github.com/Yuan-ManX/ComfyUI-AudioX.gitcd ComfyUI-AudioX
pip install -r requirements.txt
conda install -c conda-forge ffmpeg libsndfileDownload the pretrained model from 🤗 AudioX on Hugging Face:
mkdir -p model
wget https://huggingface.co/HKUSTAudio/AudioX/resolve/main/model.ckpt -O model/model.ckpt
wget https://huggingface.co/HKUSTAudio/AudioX/resolve/main/config.json -O model/config.json