zm_config.json

{
  "library_name": "zeromodels",
  "zeromodels_version": "1.3.3",
  "model_module": "zeromodels.models.stable_diffusion_2",
  "model_class": "StableDiffusion2Model",
  "variant": "stable-diffusion-2",
  "weights": "model.weights.h5",
  "schema_version": 2,
  "weight_dtype": "float32",
  "model_type": "stable_diffusion_2",
  "unet_config": {
    "sample_size": 96,
    "in_channels": 4,
    "out_channels": 4,
    "down_block_types": [
      "CrossAttnDownBlock2D",
      "CrossAttnDownBlock2D",
      "CrossAttnDownBlock2D",
      "DownBlock2D"
    ],
    "up_block_types": [
      "UpBlock2D",
      "CrossAttnUpBlock2D",
      "CrossAttnUpBlock2D",
      "CrossAttnUpBlock2D"
    ],
    "block_out_channels": [
      320,
      640,
      1280,
      1280
    ],
    "layers_per_block": 2,
    "cross_attention_dim": 1024,
    "num_attention_heads": [
      5,
      10,
      20,
      20
    ],
    "norm_num_groups": 32,
    "use_linear_projection": true,
    "transformer_layers_per_block": 1,
    "addition_embed_type": null,
    "addition_time_embed_dim": 256,
    "projection_class_embeddings_input_dim": null,
    "num_time_ids": 6,
    "text_seq_len": 77
  },
  "vae_config": {
    "in_channels": 3,
    "out_channels": 3,
    "latent_channels": 4,
    "block_out_channels": [
      128,
      256,
      512,
      512
    ],
    "layers_per_block": 2,
    "norm_num_groups": 32,
    "sample_size": 768,
    "scaling_factor": 0.18215,
    "force_upcast": false,
    "shift_factor": 0.0,
    "use_quant_conv": true,
    "use_post_quant_conv": true
  },
  "text_config": {
    "hidden_dim": 1024,
    "num_heads": 16,
    "num_layers": 23,
    "mlp_ratio": 4.0,
    "vocab_size": 49408,
    "max_seq_len": 77
  },
  "hidden_act": "gelu",
  "layer_norm_eps": 1e-05,
  "bos_token_id": 49406,
  "eos_token_id": 49407,
  "pad_token_id": 0,
  "scheduler_config": {
    "_class_name": "DDIMScheduler",
    "beta_end": 0.012,
    "beta_schedule": "scaled_linear",
    "beta_start": 0.00085,
    "clip_sample": false,
    "num_train_timesteps": 1000,
    "prediction_type": "v_prediction",
    "set_alpha_to_one": false,
    "skip_prk_steps": true,
    "steps_offset": 1,
    "trained_betas": null
  },
  "generate_args": {
    "num_inference_steps": 50,
    "guidance_scale": 7.5
  }
}