Unofficial Dreamtalk support for ComfyUI.

• 2024/03/29: Added installation from ComfyUI Manager
• 2024/03/28: Added ComfyUI nodes and workflow examples

This workflow shows the basic usage on making an image into a talking face video.

This workflow shows the advanced usage on making the whole image talking, instead of just a cropped face.

• Install from ComfyUI Manager (search for dreamtalk, make sure ffmpeg is installed)

• Download or git clone this repository into the ComfyUI/custom_nodes/ directory and run:

sudo apt install ffmpeg
pip install -r requirements.txt

Put the downloaded denoising_network.pth and renderer.pt into checkpoints folder.

Above two files can be requested from the original author as follows:

In light of the social impact, we have ceased public download access to checkpoints. If you want to obtain the checkpoints, please request it by emailing [email protected] . It is important to note that sending this email implies your consent to use the provided method solely for academic research purposes.