This is an unofficial ComfyUI node that adds sound to silent video using Tencent’s HunyuanVideo Foley model.
You drop in a quiet clip, give it a tiny prompt like “ocean sound” or “burning tree”, and it generates audio that syncs to the picture — waves rise and fade with water, fire crackles in rhythm with flames, thunder rolls under storm shots, even light background music when it fits.
Credit: https://aistudynow.com/hunyuanvideo-foley-comfyui-workflow-turn-quiet-video-into-sound/
Description
FAQ
Comments (4)
There is literally no good way AI can do Foley sound effects. Speech yes. Music yes. Sound effects NO! And this is because diffusion does not work- our brains cannot except morphed sound effects and think them correct.
So all AI can do is act like a very poor library of recorded sounds- with very poor mixing ability. This is one task anyone can do infinitely better using conventional tools, and a decent library of recordings. Diffusion is simply not appropriate for everything.
I git clone https://github.com/aistudynow/Comfyui-HunyuanFoley on custom nodes folder, moved the model files to the specified folder in github, checked the requirements.txt and updated the files, but when i load the workflow it's missing many HunyuanFoley nodes, any help?
i had updated the node so it work on low vram, and new workflow is added
@ComfyWorkflows4U thanks i'll check it out