vae/encoder/config.json

{
    "convolution_dimensions": 3,
    "encoder_blocks": [
        [
            "res_x",
            {
                "num_layers": 4
            }
        ],
        [
            "compress_space_res",
            {
                "multiplier": 2
            }
        ],
        [
            "res_x",
            {
                "num_layers": 6
            }
        ],
        [
            "compress_time_res",
            {
                "multiplier": 2
            }
        ],
        [
            "res_x",
            {
                "num_layers": 6
            }
        ],
        [
            "compress_all_res",
            {
                "multiplier": 2
            }
        ],
        [
            "res_x",
            {
                "num_layers": 2
            }
        ],
        [
            "compress_all_res",
            {
                "multiplier": 2
            }
        ],
        [
            "res_x",
            {
                "num_layers": 2
            }
        ]
    ],
    "encoder_spatial_padding_mode": "zeros",
    "in_channels": 3,
    "latent_log_var": "uniform",
    "norm_layer": "pixel_norm",
    "out_channels": 128,
    "patch_size": 4
}