INNER CODE UNIT · Python

Net

jdh-algo/JoyHallo · scripts/app.py:69

class Net(nn.Module):
    """
    The Net class defines a neural network model that combines a reference UNet2DConditionModel,
    a denoising UNet3DConditionModel, a face locator, and other components to animate a face in a static image.

    Args:
        reference_unet (UNet2DConditionModel): The reference UNet2DConditionModel used for face animation.
        denoising_unet (UNet3DConditionModel): The denoising UNet3DConditionModel used for face animation.
        face_locator (FaceLocator): The face locator model used for face animation.
        reference_control_writer: The reference control writer component.
        reference_control_reader: The reference control reader component.
        imageproj: The image projection model.
        audioproj: The audio projection model.

    Forward method:
        noisy_latents (torch.Tensor): The noisy latents tensor.
        timesteps (torch.Tensor): The timesteps tensor.
        ref_image_latents (torch.Tensor): The reference image latents tensor.

View source record →

📰 Research Paper
Loading…
⏳ Fetching content…