
Powered By RTX 4090
Input a photo with a portrait, which can be a real person or a cartoon
Then input a piece of audio, which can be a narration or singing
Combine them to generate a digital human or a cartoon digital human
Sonic: Shifting Focus to Global Audio Perception in Portrait Animation
Epsilon
2025-02-14 Update
Epsilon
2025-02-14 Update
Workflow introduction
Input a photo with a portrait, which can be a real person or a cartoon
Then input a piece of audio, which can be a narration or singing
Combine them to generate a digital human or a cartoon digital human
Sonic: Shifting Focus to Global Audio Perception in Portrait Animation
Nodes Information
10
LoadImage
PreviewImage
ImageOnlyCheckpointLoader
ImageResizeKJ
LoadAudio
SONICSampler
SONICTLoader
SONIC_PreData
VHS_VideoCombine
easy cleanGpuUsed