transformer/config.json

{
  "_class_name": "StepVideoModel",
  "_diffusers_version": "0.31.0",
  "attention_head_dim": 128,
  "attention_type": "parallel",
  "caption_channels": [
    6144,
    1024
  ],
  "dropout": 0.0,
  "in_channels": 64,
  "norm_elementwise_affine": false,
  "norm_eps": 1e-06,
  "norm_type": "ada_norm_single",
  "num_attention_heads": 48,
  "num_layers": 48,
  "out_channels": 64,
  "patch_size": 1,
  "use_additional_conditions": true
}