config/infer.yaml

data:
  n_sample_frames: 16
  width: 512
  height: 512

pretrained_model_name_or_path: "models/stable-video-diffusion-img2vid-xt"
unet_checkpoint_path: "models/face_restoration/unet.pth"
id_linear_checkpoint_path: "models/face_restoration/id_linear.pth"
net_arcface_checkpoint_path: "models/face_restoration/insightface_glint360k.pth"
# output_dir: 'result' 


# test config
weight_dtype: 'fp16'
num_inference_steps: 30
decode_chunk_size: 16
overlap: 3
noise_aug_strength: 0.00
min_appearance_guidance_scale: 2.0
max_appearance_guidance_scale: 2.0
i2i_noise_strength: 1.0