{
    "_class_name": "UNet2DModel",
    "sample_size": 32,
    "in_channels": 3,
    "out_channels": 3,
    "layers_per_block": 2,
    "block_out_channels": [
        64,
        128,
        128,
        256
    ],
    "down_block_types": [
        "DownBlock2D",
        "DownBlock2D",
        "AttnDownBlock2D",
        "AttnDownBlock2D"
    ],
    "up_block_types": [
        "AttnUpBlock2D",
        "AttnUpBlock2D",
        "UpBlock2D",
        "UpBlock2D"
    ],
    "act_fn": "silu",
    "attention_head_dim": 8,
    "norm_num_groups": 32
}