configs/inference_t2v_512_v2.0.yaml

model:
  target: lvdm.models.ddpm3d.LatentDiffusion
  params:
    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: crossattn
    image_size:
    - 40
    - 64
    channels: 4
    scale_by_std: false
    scale_factor: 0.18215
    use_ema: false
    uncond_type: empty_seq
    use_scale: true
    scale_b: 0.7
    unet_config:
      target: lvdm.modules.networks.openaimodel3d.UNetModel
      params:
        in_channels: 4
        out_channels: 4
        model_channels: 320
        attention_resolutions:
        - 4
        - 2
        - 1
        num_res_blocks: 2
        channel_mult:
        - 1
        - 2
        - 4
        - 4
        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
        fps_cond: true
    first_stage_config:
      target: lvdm.models.autoencoder.AutoencoderKL
      params:
        embed_dim: 4
        monitor: val/rec_loss
        ddconfig:
          double_z: true
          z_channels: 4
          resolution: 512
          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