ComfyUI_DICE_Talk

★ 25

会说话人像情感一致性DICE-TalkComfyUI插件

在ComfyUI中使用DICE-Talk方法生成情感相关且唇动一致的会说话人像，提高情绪一致性与自然感

💡 为视频或动画生成情绪对齐的会说话人像

🍴 1 Forks💻 Python🔄 2025-05-07

🔗 GitHub 原文

📦

网盘下载

复制链接后前往夸克网盘下载

https://pan.quark.cn/s/c1eafc754fbb

📦 requirements.txt

#accelerate==0.28.0
#av==11.0.0
diffusers
einops==0.7.0
#pydantic==2.10.6
#gradio==4.44.1
imageio
imageio-ffmpeg
librosa
#numpy==1.26.4
omegaconf
opencv-python
#sk-video==1.1.10
#tqdm==4.65.2
transformers

📄 README

ComfyUI_DICE_Talk

Use DICE-Talk in ComfyUI，which is a method about ‘Correlation-Aware Emotional Talking Portrait Generation’.

Update

fix GPU Unload error

1. Installation

In the ./ComfyUI/custom_node directory, run the following:

git clone https://github.com/smthemex/ComfyUI_DICE_Talk.git

2. Requirements

pip install -r requirements.txt

3.Model

3.1.1 download checkpoints from EEEELY/DICE-Talk 从抱脸下载必须的模型,文件结构如下图

3.1.2 download openai/whisper-tiny

--  ComfyUI/models/dice_talk/
    |-- audio_linear.pth
    |-- emo_model.pth
    |-- pose_guider.pth
    |-- unet.pth
    |-- yoloface_v5m.pt  #can use sonic 可以用sonic的，不需要复制
    |-- whisper-tiny/  #can use sonic 可以用sonic的，不需要复制
        |--config.json
        |--model.safetensors
        |--preprocessor_config.json
    |-- RIFE/  #can use sonic 可以用sonic的，不需要复制
        |--flownet.pkl

3.2 SVD checkpoints svd_xt.safetensors or svd_xt_1_1.safetensors

--   ComfyUI/models/checkpoints
    ├── svd_xt.safetensors  or  svd_xt_1_1.safetensors

4.Example

5 .Citation

@misc{tan2025disentangleidentitycooperateemotion,
      title={Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait Generation}, 
      author={Weipeng Tan and Chuming Lin and Chengming Xu and FeiFan Xu and Xiaobin Hu and Xiaozhong Ji and Junwei Zhu and Chengjie Wang and Yanwei Fu},
      year={2025},
      eprint={2504.18087},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2504.18087}, 
}