Video Sound Generator-Hunyuan Foley-workflow

You can click on the link below to try it out directly. If the effect is good, you can deploy it locally

https://www.runninghub.ai/post/1966507850908512257/?inviteCode=1cqzbf7a

Fan benefits,register to get 1000 points,daily login 100 points,play 4090!Experience the super power of 48G.

This is Hunyuan+Foley, Video Sound Generator workflow. After testing, its sound generation effect is excellent, and the required video memory for operation is not high. It is worth recommending! If there is a higher demand for sound quality, it can be achieved by increasing the number of steps.

Local deployment installation steps:
1. Download Hunyuan+Foley model:
https://huggingface.co/tencent/HunyuanVideo-Foley/tree/main
Place folder: models \ hunyuan_foley
2. Download the siglip2 model:
https://huggingface.co/google/siglip2-base-patch16-512/tree/main
Place folder: models \ hunyuan_foley \ siglip2
3. Download the CLAP text model:
https://huggingface.co/laion/larger_clap_general/tree/refs%2Fpr%2F2
Place folder: models \ hunyuan_foley \ clap
4. Install plugins
https://github.com/vantagewithai/Vantage-HunyuanFoley?tab=readme -ov-file
Place folder: custom_nodes
5. Run the command in the plugin directory (custom_nodes \ Vantage HunyuanFoley):
pip install -r requirements.txt

Attention: If there is a dependency conflict prompt during the requirements process, you can try running the command:
pip install protobuf==3.19.6 diffusers timm transformers descript-audiotools omegaconf

Please refer to the original author's introduction of the plugin for details. It should be noted that this model requires a lot of dependencies and is difficult to install.