

Enter a photo and text, and you can get a digital person who broadcasts the text
You can also combine the following flow and clone the sound, so that you can get a digital person with highly customized "sound", "text" and "image"
https://runninghub.cn/#/workflow/1837084301916794881
Isabella
2024-10-14 Update
Follow
Isabella
2024-10-14 Update
Follow
Workflow introduction
Enter a photo and text, and you can get a digital person who broadcasts the text
You can also combine the following flow and clone the sound, so that you can get a digital person with highly customized "sound", "text" and "image"
https://runninghub.cn/#/workflow/1837084301916794881
Nodes Information
10
LoadImage
CosyVoiceNode
Echo_LoadModel
Echo_Sampler
JWImageResizeToSquare
Label (rgthree)
PreviewAudio
SaveAudio
TextNode
VHS_VideoCombine