microsoft

/

VibeVoice-1.5B

like 2.24k

Follow

Microsoft 18.9k

follow the instruction from the ComfyUI-VibeVoice
Put the full VibeVoice-1.5B into the "ComfyUI/models/tts/VibeVoice/"

I've installed this one: https://github.com/Enemyx-net/VibeVoice-ComfyUI
Is there a difference between the two?

Also, the repo:https://huggingface.co/microsoft/VibeVoice-1.5B/tree/main contains multiple files, I assume I'll have to put all of them in the same folder, right?
It's referred to as the model everywhere, makes me think it's a single file rather than a set of files.

For anyone stuck in my situation, you have to create a subfolder named VibeVoice-1.5B and put the files in that.

I've downloaded the 7b model can you help me

I have downloaded vibevoice large pt, and I have put everything in the folder named “VibeVoice-Large-pt“” via path：ComfyUI-V51-0355\ComfyUI\models\tts\VibeVoice\， and it complains about not having found the large model, I have been racking my brains about it, just can't find a solution to this prob, can anybody pull it off for me, thaaaaaaaaaaaaaaanks.

我已经下载了VibeVoice-Large所有的模型文件，存放目录为E:\comfyui\models\tts\VibeVoice\VibeVoice-Large，运行comfyui后提示，谁能给个解决方案

i have the same problem
i follow this

ComfyUI/models/vibevoice/
├── tokenizer/ # Place Qwen tokenizer files here
│ ├── tokenizer_config.json
│ ├── vocab.json
│ ├── merges.txt
│ └── tokenizer.json
├── VibeVoice-1.5B/ # Model folder
│ ├── config.json
│ ├── model-00001-of-00003.safetensors
│ ├── model-00002-of-00003.safetensors
│ └── ... (other model files)
├── VibeVoice-Large/
│ └── ... (model files)
└── my-custom-vibevoice/ # custom names are supported
└── ... (model files)

this no model found so i move it to this

ComfyUI/models/tts/vibevoice/
├── tokenizer/ # Place Qwen tokenizer files here
│ ├── tokenizer_config.json
│ ├── vocab.json
│ ├── merges.txt
│ └── tokenizer.json
├── VibeVoice-1.5B/ # Model folder
│ ├── config.json
│ ├── model-00001-of-00003.safetensors
│ ├── model-00002-of-00003.safetensors
│ └── ... (other model files)
├── VibeVoice-Large/
│ └── ... (model files)
└── my-custom-vibevoice/ # custom names are supported
└── ... (model files)

still no medel found

any solution?