{
  "_class_name": "AutoencoderKL",
  "_diffusers_version": "0.14.0",
  "_name_or_path": "/root/.cache/huggingface/hub/models--tvergho--audio-diffusion-512/snapshots/aa03eb5771f70c0b090e2dfdb6b00d2f20d1f41e/vqvae",
  "act_fn": "silu",
  "block_out_channels": [
    128,
    256,
    512,
    512
  ],
  "down_block_types": [
    "DownEncoderBlock2D",
    "DownEncoderBlock2D",
    "DownEncoderBlock2D",
    "DownEncoderBlock2D"
  ],
  "in_channels": 1,
  "latent_channels": 1,
  "layers_per_block": 2,
  "norm_num_groups": 32,
  "out_channels": 1,
  "sample_size": 256,
  "scaling_factor": 0.18215,
  "up_block_types": [
    "UpDecoderBlock2D",
    "UpDecoderBlock2D",
    "UpDecoderBlock2D",
    "UpDecoderBlock2D"
  ]
}