ComfyOnline
AniPortrait_Audio2Video

ComfyUI Node: Audio Gen Video šŸŽ„AniPortrait

Authored by frankchieng

Created 7 months ago

Updated about a month ago

53 stars

Category

AniPortrait šŸŽ„Video

Inputs

ref_image IMAGE

height INT

width INT

seed INT

cfg FLOAT

steps INT

vae_path

  • pretrained_model/sd-vae-ft-mse

model

  • pretrained_model/stable-diffusion-v1-5

weight_dtype

  • fp16
  • fp32

accelerate BOOLEAN

length INT

fi_step INT

motion_module_path

  • pretrained_model/motion_module.pth

image_encoder_path

  • pretrained_model/image_encoder

denoising_unet_path

  • pretrained_model/denoising_unet.pth

reference_unet_path

  • pretrained_model/reference_unet.pth

pose_guider_path

  • pretrained_model/pose_guider.pth

images IMAGE

audio_path Audio_Path

fps INT

Outputs

IMAGE

Extension: ComfyUI_Aniportrait

implementation of a/AniPortrait generating of videos, includes self driven, face reenacment and audio driven with a reference image

Authored by frankchieng

related extension: