configs/ae/video.yaml

target: sgm.models.autoencoder.AutoencodingEngine
params:
  loss_config:
    target: torch.nn.Identity
  regularizer_config:
    target: sgm.modules.autoencoding.regularizers.DiagonalGaussianRegularizer
  encoder_config: 
    target: sgm.modules.diffusionmodules.model.Encoder
    params:
      attn_type: vanilla
      double_z: True
      z_channels: 4
      resolution: 256
      in_channels: 3
      out_ch: 3
      ch: 128
      ch_mult: [1, 2, 4, 4]
      num_res_blocks: 2
      attn_resolutions: []
      dropout: 0.0
  decoder_config:
    target: sgm.modules.autoencoding.temporal_ae.VideoDecoder
    params:
      attn_type: vanilla
      double_z: True
      z_channels: 4
      resolution: 256
      in_channels: 3
      out_ch: 3
      ch: 128
      ch_mult: [1, 2, 4, 4]
      num_res_blocks: 2
      attn_resolutions: []
      dropout: 0.0
      video_kernel_size: [3, 1, 1]