unet/config.json

{
  "_class_name": "UNetMidBlock3DCrossAttn",
  "_diffusers_version": "0.2.2",
  "act_fn": "silu",
  "attention_head_dim": 8,
  "block_out_channels": [
    320,
    640,
    1280,
    1280
  ],
  "center_input_sample": false,
  "cross_attention_dim": 768,
  "down_block_types": [
    "CrossAttnDownBlock3D",
    "CrossAttnDownBlock3D",
    "CrossAttnDownBlock3D",
    "DownBlock3D"
  ],
  "downsample_padding": 1,
  "flip_sin_to_cos": true,
  "freq_shift": 0,
  "in_channels": 4,
  "layers_per_block": 2,
  "mid_block_scale_factor": 1,
  "norm_eps": 1e-05,
  "norm_num_groups": 32,
  "out_channels": 4,
  "sample_size": 64,
  "up_block_types": [
    "UpBlock3D",
    "CrossAttnUpBlock3D",
    "CrossAttnUpBlock3D",
    "CrossAttnUpBlock3D"
  ],
  "addition_embed_type": "motion_ids",
  "addition_time_embed_dim": 256
}