|
|
|
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.pth" |
|
reference_unet_path: "./pretrained_weights/reference_unet.pth" |
|
face_locator_path: "./pretrained_weights/face_locator.pth" |
|
motion_module_path: "./pretrained_weights/motion_module.pth" |
|
|
|
|
|
inference_config: "./configs/inference/inference_v2.yaml" |
|
weight_dtype: 'fp16' |
|
|
|
|
|
test_cases: |
|
"./assets/test_imgs/a.png": |
|
- "./assets/test_audios/echomimic_en.wav" |
|
"./assets/test_imgs/b.png": |
|
- "./assets/test_audios/echomimic_en_girl.wav" |
|
"./assets/test_imgs/c.png": |
|
- "./assets/test_audios/echomimic_en_girl.wav" |
|
"./assets/test_imgs/d.png": |
|
- "./assets/test_audios/echomimic_en_girl.wav" |
|
"./assets/test_imgs/e.png": |
|
- "./assets/test_audios/echomimic_en.wav" |