Simple audio generation
This generates sound effects for your video
Talking not supported
I think this needs the latest torch version 2.51 if you dont have that and want it it can be be updated via the comfy ui dir update folder. Update python dependencies.
Uses MMaudio nodes and models
https://github.com/kijai/ComfyUI-MMAudio
Models
https://huggingface.co/Kijai/MMAudio_safetensors/tree/main
Bigvgan - not needed
Description
FAQ
Comments (1)
God damn that was some deep pain to get it to run. Torch 2.5.1 had tons of dependencies that conflicted with other custom nodes. Torch 2.5.0 cu124 worked well!
I'd suggest to backup your python_embeded folder in case things goes super wrong with torch installation.
I used this cmd to get it running (make sure to uninstall Torch first):
.\ComfyUI_windows_portable\python_embeded\python.exe -m pip install torch==2.5.0+cu124 torchvision==0.20.0 torchaudio==2.5.0 --index-url https://download.pytorch.org/whl/cu124
Then needed to pip install -r requirements.txt in the ComfyUI folder to apply dependencies.
Tons of other dependencies had to be recalibrated to specific versions to work with one another.
I made the mistake of upgrading to python 3.12 to fix a specific custom node and that was another a heachache to fix back. Just keep 3.11.
Anyways, this is super worth the trouble! Time to txt2vid HunYuan and plug this baby in for automatic sound!
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.