unet/config.json

{
  "_class_name": "UNet2DConditionModel",
  "_commit_hash": null,
  "_diffusers_version": "0.30.3",
  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--diffusers--stable-diffusion-xl-1.0-inpainting-0.1/snapshots/115134f363124c53c7d878647567d04daf26e41e/unet",
  "_use_default_values": [
    "reverse_transformer_layers_per_block",
    "dropout"
  ],
  "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,
  "decay": 0.9999,
  "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": 9,
  "inv_gamma": 1.0,
  "layers_per_block": 2,
  "mid_block_only_cross_attention": null,
  "mid_block_scale_factor": 1,
  "mid_block_type": "UNetMidBlock2DCrossAttn",
  "min_decay": 0.0,
  "neuron": {
    "auto_cast": "matmul",
    "auto_cast_type": "bf16",
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.15.128.0+56dc5a86",
    "dynamic_batch_size": false,
    "inline_weights_to_neff": true,
    "input_names": [
      "sample",
      "timestep",
      "encoder_hidden_states",
      "text_embeds",
      "time_ids"
    ],
    "model_type": "unet",
    "optlevel": "2",
    "output_attentions": false,
    "output_hidden_states": false,
    "output_names": [
      "sample"
    ],
    "static_batch_size": 1,
    "static_height": 128,
    "static_num_channels": 9,
    "static_sequence_length": 77,
    "static_vae_scale_factor": 8,
    "static_width": 128
  },
  "norm_eps": 1e-05,
  "norm_num_groups": 32,
  "num_attention_heads": null,
  "num_class_embeds": null,
  "only_cross_attention": false,
  "optimization_step": 37000,
  "out_channels": 4,
  "power": 0.6666666666666666,
  "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,
  "sample_size": 128,
  "task": "semantic-segmentation",
  "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
  ],
  "transformers_version": null,
  "up_block_types": [
    "CrossAttnUpBlock2D",
    "CrossAttnUpBlock2D",
    "UpBlock2D"
  ],
  "upcast_attention": null,
  "update_after_step": 0,
  "use_ema_warmup": false,
  "use_linear_projection": true
}