Wan2.1 and FantasyTalking - Image2Video Lipsync
Create high quality lipsync video from image inputs with Wan2.1 FantasyTalking Key Inputs Load Image: Select an image of a person with their face in clear view Load Audio: Choose audio file Frames: How many frames generated
FantasyTalking
Image2Video
Lipsync
Wan2.1
2
735
Nodes & Models
INTConstant
INTConstant
ImageResizeKJv2
WanVideoBlockSwap
WanVideoTorchCompileSettings
DownloadAndLoadWav2VecModel
WanVideoTeaCache
FantasyTalkingModelLoader
fantasytalking_fp16.safetensors
LoadWanVideoT5TextEncoder
umt5-xxl-enc-bf16.safetensors
CreateCFGScheduleFloatList
WanVideoTextEncode
FantasyTalkingWav2VecEmbeds
WanVideoClipVisionEncode
WanVideoModelLoader
Wan2_1-I2V-14B-720P_fp8_e4m3fn.safetensors
WanVideoSampler
WanVideoImageToVideoEncode
WanVideoDecode
DownloadAndLoadWav2VecModel
FantasyTalkingModelLoader
fantasytalking_fp16.safetensors
FantasyTalkingWav2VecEmbeds
DownloadAndLoadWav2VecModel
FantasyTalkingModelLoader
fantasytalking_fp16.safetensors
FantasyTalkingWav2VecEmbeds
ImageResizeKJv2
VHS_VideoCombine
Create high quality lipsync video from image inputs with Wan2.1 FantasyTalking
Key Inputs
Load Image: Select an image of a person with their face in clear view
Load Audio: Choose audio file
Frames: How many frames generated
Read more
N