model: target: lvdm.models.ddpm3d.T2VAdapterDepth params: linear_start: 0.00085 linear_end: 0.012 num_timesteps_cond: 1 log_every_t: 200 timesteps: 1000 first_stage_key: video cond_stage_key: caption image_size: - 32 - 32 video_length: 16 channels: 4 cond_stage_trainable: false conditioning_key: crossattn scale_by_std: false scale_factor: 0.18215 unet_config: target: lvdm.models.modules.openaimodel3d.UNetModel params: image_size: 32 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_heads: 8 transformer_depth: 1 context_dim: 768 use_checkpoint: true legacy: false kernel_size_t: 1 padding_t: 0 temporal_length: 16 use_relative_position: 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: 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.models.modules.condition_modules.FrozenCLIPEmbedder depth_stage_config: target: extralibs.midas.api.MiDaSInference params: model_type: "dpt_hybrid" model_path: models/adapter_t2v_depth/dpt_hybrid-midas.pt adapter_config: target: lvdm.models.modules.adapter.Adapter cond_name: depth params: cin: 64 channels: [320, 640, 1280, 1280] nums_rb: 2 ksize: 1 sk: True use_conv: False