mld_config.json

{
  "model_type": "mld",
  "text_encoder_name": "text_encoder/sentence-t5-large",
  "guidance_scale": 7.5,
  "num_inference_steps": 50,
  "config": {
    "vae": {
      "nfeats": 263,
      "latent_dim": [
        1,
        256
      ],
      "ff_size": 1024,
      "num_layers": 9,
      "num_heads": 4,
      "dropout": 0.1,
      "arch": "encoder_decoder",
      "normalize_before": false,
      "activation": "gelu",
      "position_embedding": "learned"
    },
    "denoiser": {
      "latent_dim": [
        1,
        256
      ],
      "ff_size": 1024,
      "num_layers": 9,
      "num_heads": 4,
      "dropout": 0.1,
      "normalize_before": false,
      "activation": "gelu",
      "flip_sin_to_cos": true,
      "return_intermediate_dec": false,
      "position_embedding": "learned",
      "arch": "trans_enc",
      "freq_shift": 0,
      "text_encoded_dim": 768,
      "time_cond_proj_dim": null
    },
    "scheduler": {
      "num_train_timesteps": 1000,
      "beta_start": 0.00085,
      "beta_end": 0.012,
      "beta_schedule": "scaled_linear",
      "clip_sample": false,
      "set_alpha_to_one": false,
      "steps_offset": 1,
      "eta": 0.0
    }
  },
  "text_encoder_stored_in_artifact": true
}