configs/prompts/animation_audio.yaml

pretrained_base_model_path: './pretrained_model/stable-diffusion-v1-5'
pretrained_vae_path: './pretrained_model/sd-vae-ft-mse'
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"
motion_module_path: "./pretrained_model/motion_module.pth"

audio_inference_config: "./configs/inference/inference_audio.yaml"
inference_config: "./configs/inference/inference_v2.yaml"
weight_dtype: 'fp16'

pose_temp: "./configs/inference/head_pose_temp/pose_temp.npy"