neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/stable-diffusion/stabilityai/stable-diffusion-xl-base-1.0/a8218e1ae23f2aaf8834.json

{
  "_entry_class": "MultiModelCacheEntry",
  "_model_id": "stabilityai/stable-diffusion-xl-base-1.0",
  "_task": null,
  "text_encoder": {
    "architectures": [
      "CLIPTextModel"
    ],
    "attention_dropout": 0.0,
    "dropout": 0.0,
    "hidden_act": "quick_gelu",
    "hidden_size": 768,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-05,
    "max_position_embeddings": 77,
    "model_type": "clip_text_model",
    "neuron": {
      "auto_cast": "matmul",
      "auto_cast_type": "bf16",
      "compiler_type": "neuronx-cc",
      "compiler_version": "2.17.194.0+d312836f",
      "dynamic_batch_size": false,
      "inline_weights_to_neff": false,
      "optlevel": "2",
      "output_attentions": false,
      "output_hidden_states": false,
      "static_batch_size": 1,
      "static_sequence_length": 77,
      "task": "feature-extraction",
      "tensor_parallel_size": 1
    },
    "num_attention_heads": 12,
    "num_hidden_layers": 12,
    "output_hidden_states": true,
    "vocab_size": 49408
  },
  "text_encoder_2": {
    "architectures": [
      "CLIPTextModelWithProjection"
    ],
    "attention_dropout": 0.0,
    "dropout": 0.0,
    "hidden_act": "gelu",
    "hidden_size": 1280,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 5120,
    "layer_norm_eps": 1e-05,
    "max_position_embeddings": 77,
    "model_type": "clip_text_model",
    "neuron": {
      "auto_cast": "matmul",
      "auto_cast_type": "bf16",
      "compiler_type": "neuronx-cc",
      "compiler_version": "2.17.194.0+d312836f",
      "dynamic_batch_size": false,
      "inline_weights_to_neff": false,
      "optlevel": "2",
      "output_attentions": false,
      "output_hidden_states": false,
      "static_batch_size": 1,
      "static_sequence_length": 77,
      "task": "feature-extraction",
      "tensor_parallel_size": 1
    },
    "num_attention_heads": 20,
    "num_hidden_layers": 32,
    "output_hidden_states": true,
    "vocab_size": 49408
  },
  "unet": {
    "_class_name": "UNet2DConditionModel",
    "act_fn": "silu",
    "addition_embed_type": "text_time",
    "addition_embed_type_num_heads": 64,
    "addition_time_embed_dim": 256,
    "attention_head_dim": [
      5,
      10,
      20
    ],
    "attention_type": "default",
    "block_out_channels": [
      320,
      640,
      1280
    ],
    "center_input_sample": false,
    "class_embed_type": null,
    "class_embeddings_concat": false,
    "conv_in_kernel": 3,
    "conv_out_kernel": 3,
    "cross_attention_dim": 2048,
    "cross_attention_norm": null,
    "down_block_types": [
      "DownBlock2D",
      "CrossAttnDownBlock2D",
      "CrossAttnDownBlock2D"
    ],
    "downsample_padding": 1,
    "dropout": 0.0,
    "dual_cross_attention": false,
    "encoder_hid_dim": null,
    "encoder_hid_dim_type": null,
    "flip_sin_to_cos": true,
    "freq_shift": 0,
    "in_channels": 4,
    "layers_per_block": 2,
    "mid_block_only_cross_attention": null,
    "mid_block_scale_factor": 1,
    "mid_block_type": "UNetMidBlock2DCrossAttn",
    "neuron": {
      "auto_cast": "matmul",
      "auto_cast_type": "bf16",
      "compiler_type": "neuronx-cc",
      "compiler_version": "2.17.194.0+d312836f",
      "dynamic_batch_size": false,
      "inline_weights_to_neff": true,
      "optlevel": "2",
      "output_attentions": false,
      "output_hidden_states": false,
      "static_batch_size": 1,
      "static_height": 128,
      "static_num_channels": 4,
      "static_sequence_length": 77,
      "static_vae_scale_factor": 8,
      "static_width": 128,
      "task": "semantic-segmentation",
      "tensor_parallel_size": 1
    },
    "norm_eps": 1e-05,
    "norm_num_groups": 32,
    "num_attention_heads": null,
    "num_class_embeds": null,
    "only_cross_attention": false,
    "out_channels": 4,
    "projection_class_embeddings_input_dim": 2816,
    "resnet_out_scale_factor": 1.0,
    "resnet_skip_time_act": false,
    "resnet_time_scale_shift": "default",
    "reverse_transformer_layers_per_block": null,
    "time_cond_proj_dim": null,
    "time_embedding_act_fn": null,
    "time_embedding_dim": null,
    "time_embedding_type": "positional",
    "timestep_post_act": null,
    "transformer_layers_per_block": [
      1,
      2,
      10
    ],
    "up_block_types": [
      "CrossAttnUpBlock2D",
      "CrossAttnUpBlock2D",
      "UpBlock2D"
    ],
    "upcast_attention": null,
    "use_linear_projection": true
  }
}