|
|
|
pretrained_base_model_path: "./pretrained_weights/sd-image-variations-diffusers" |
|
pretrained_vae_path: "./pretrained_weights/sd-vae-ft-mse" |
|
audio_model_path: "./pretrained_weights/audio_processor/whisper_tiny.pt" |
|
|
|
|
|
denoising_unet_path: "./pretrained_weights/denoising_unet_pose_acc.pth" |
|
reference_unet_path: "./pretrained_weights/reference_unet_pose.pth" |
|
face_locator_path: "./pretrained_weights/face_locator_pose.pth" |
|
motion_module_path: "./pretrained_weights/motion_module_pose_acc.pth" |
|
|
|
|
|
inference_config: "./configs/inference/inference_v2.yaml" |
|
weight_dtype: 'fp16' |
|
|
|
|
|
test_cases: |
|
"./assets/test_pose_demo/d.jpg": |
|
- "./assets/test_pose_demo_audios/movie_0_clip_0.wav" |
|
- "./assets/test_pose_demo_pose" |
|
|
|
|