floyo logo
Powered by
ThinkDiffusion
floyo logo
Powered by
ThinkDiffusion

InfiniteTalk | Image to Video: Unlimited Talking Avatar with Lip-sync

954

Create ultra-realistic AI talking-head videos using just one image and your voice with InfiniteTalk

Read more

N
Generates in about 4 secs

Nodes & Models

GetNode
Note
MarkdownNote
LoadImage
CLIPVisionLoader
clip_vision_h.safetensors
LoadAudio
SetNode
PreviewAny
WanVideoTorchCompileSettings
WanVideoBlockSwap
WanVideoLoraSelect
lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors
WanVideoVAELoader
Wan2_1_VAE_bf16.safetensors
WanVideoModelLoader
wan2.1_i2v_720p_14B_fp8_scaled.safetensors
WanVideoTorchCompileSettings
WanVideoBlockSwap
WanVideoTextEncodeCached
umt5-xxl-enc-bf16.safetensors
WanVideoLoraSelect
lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors
Wav2VecModelLoader
wav2vec2-chinese-base_fp16.safetensors
DownloadAndLoadWav2VecModel
MultiTalkModelLoader
Wan2_1-InfiniteTalk-Multi_fp8_e4m3fn_scaled_KJ.safetensors
WanVideoVAELoader
Wan2_1_VAE_bf16.safetensors
WanVideoModelLoader
wan2.1_i2v_720p_14B_fp8_scaled.safetensors
WanVideoClipVisionEncode
MultiTalkWav2VecEmbeds
WanVideoImageToVideoMultiTalk
WanVideoSampler
WanVideoPassImagesFromSamples
INTConstant
INTConstant
ImageResizeKJv2
GetImageSizeAndCount
MelBandRoFormerModelLoader
MelBandRoformer_fp16.safetensors
MelBandRoFormerSampler
DownloadAndLoadWav2VecModel
MultiTalkModelLoader
Wan2_1-InfiniteTalk-Multi_fp8_e4m3fn_scaled_KJ.safetensors
MultiTalkWav2VecEmbeds
WanVideoImageToVideoMultiTalk
DownloadAndLoadWav2VecModel
ImageResizeKJv2
GetImageSizeAndCount
VHS_VideoCombine

Create ultra-realistic AI talking-head videos using just one image and your voice with InfiniteTalk

Read more

N