configs/inference_512_v1.0.yaml

model:
  target: lvdm.models.ddpm3d.LatentVisualDiffusion
  params:
    rescale_betas_zero_snr: True
    parameterization: "v"
    linear_start: 0.00085
    linear_end: 0.012
    num_timesteps_cond: 1
    timesteps: 1000
    first_stage_key: video
    cond_stage_key: caption
    cond_stage_trainable: False
    conditioning_key: hybrid
    image_size: [40, 64]
    channels: 4
    scale_by_std: False
    scale_factor: 0.18215
    use_ema: False
    uncond_type: 'empty_seq'
    use_dynamic_rescale: true
    base_scale: 0.7
    fps_condition_type: 'fps'
    perframe_ae: True
    loop_video: true
    unet_config:
      target: cldm.cldm.ControlledUnetModel
      params:
        in_channels: 8
        out_channels: 4
        model_channels: 320
        attention_resolutions:
        - 4
        - 2
        - 1
        num_res_blocks: 2
        channel_mult:
        - 1
        - 2
        - 4
        - 4
        dropout: 0.1
        num_head_channels: 64
        transformer_depth: 1
        context_dim: 1024
        use_linear: true
        use_checkpoint: True
        temporal_conv: True
        temporal_attention: True
        temporal_selfatt_only: true
        use_relative_position: false
        use_causal_attention: False
        temporal_length: 16
        addition_attention: true
        image_cross_attention: true
        default_fs: 24
        fs_condition: true

    first_stage_config:
      target: lvdm.models.autoencoder.AutoencoderKL_Dualref
      params:
        embed_dim: 4
        monitor: val/rec_loss
        ddconfig:
          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
        lossconfig:
          target: torch.nn.Identity

    cond_stage_config:
      target: lvdm.modules.encoders.condition.FrozenOpenCLIPEmbedder
      params:
        freeze: true
        layer: "penultimate"

    img_cond_stage_config:
      target: lvdm.modules.encoders.condition.FrozenOpenCLIPImageEmbedderV2
      params:
        freeze: true
    
    image_proj_stage_config:
      target: lvdm.modules.encoders.resampler.Resampler
      params:
        dim: 1024
        depth: 4
        dim_head: 64
        heads: 12
        num_queries: 16
        embedding_dim: 1280
        output_dim: 1024
        ff_mult: 4
        video_length: 16