
AI Singing Digital Human Lip Sync RCM Infinite Talk
Note: A 2-minute song takes about 20 to 30 minutes to generate, and a 4-minute song takes nearly over 50 minutes.
迎风
2026-04-08 Update
Follow
迎风
2026-04-08 Update
Follow
Workflow introduction
AI Singing Digital Human Lip Sync RCM Infinite Talk
Note: A 2-minute song takes about 20 to 30 minutes to generate, and a 4-minute song takes nearly over 50 minutes.
Nodes Information
32
CLIPVisionLoader
LoadImage
AudioSeparation
DownloadAndLoadWav2VecModel
Fast Groups Muter (rgthree)
FlashVSRNode
Float to Int
Int
LayerUtility: ImageScaleByAspectRatio V2
LayerUtility: PurgeVRAM V2
LoadAudio
MultiTalkModelLoader
MultiTalkWav2VecEmbeds
Note
PrimitiveStringMultiline
RH_GetAudioDuration
SimpleMath+
SoundFlow_TrimAudio
VHS_VideoCombine
WanVideoBlockSwap
WanVideoClipVisionEncode
WanVideoDecode
WanVideoEasyCache
WanVideoEnhanceAVideo
WanVideoExperimentalArgs
WanVideoImageToVideoMultiTalk
WanVideoLoraSelect
WanVideoModelLoader
WanVideoSLG
WanVideoSampler
WanVideoTextEncodeCached
WanVideoVAELoader