File size: 3,414 Bytes
609c068 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 |
{
"_class_name": "UNet2DConditionModel",
"_commit_hash": null,
"_diffusers_version": "0.28.2",
"_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--hf-internal-testing--tiny-stable-diffusion-torch/snapshots/a88cdfbd91f96ec7f61eb7484b652ff0f4ee701d/unet",
"_use_default_values": [
"dropout",
"dual_cross_attention",
"mid_block_type",
"class_embeddings_concat",
"addition_embed_type",
"transformer_layers_per_block",
"addition_embed_type_num_heads",
"resnet_out_scale_factor",
"attention_type",
"cross_attention_norm",
"addition_time_embed_dim",
"num_attention_heads",
"reverse_transformer_layers_per_block",
"timestep_post_act",
"conv_in_kernel",
"encoder_hid_dim_type",
"resnet_skip_time_act",
"resnet_time_scale_shift",
"num_class_embeds",
"encoder_hid_dim",
"upcast_attention",
"class_embed_type",
"time_embedding_act_fn",
"conv_out_kernel",
"only_cross_attention",
"use_linear_projection",
"time_cond_proj_dim",
"projection_class_embeddings_input_dim",
"time_embedding_dim",
"time_embedding_type",
"mid_block_only_cross_attention"
],
"act_fn": "silu",
"addition_embed_type": null,
"addition_embed_type_num_heads": 64,
"addition_time_embed_dim": null,
"attention_head_dim": 8,
"attention_type": "default",
"block_out_channels": [
32,
64
],
"center_input_sample": false,
"class_embed_type": null,
"class_embeddings_concat": false,
"conv_in_kernel": 3,
"conv_out_kernel": 3,
"cross_attention_dim": 32,
"cross_attention_norm": null,
"down_block_types": [
"DownBlock2D",
"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": {
"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"
],
"model_type": "unet",
"optlevel": "2",
"output_attentions": false,
"output_hidden_states": false,
"output_names": [
"sample"
],
"static_batch_size": 4,
"static_height": 32,
"static_num_channels": 4,
"static_sequence_length": 77,
"static_vae_scale_factor": 2,
"static_width": 32
},
"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": null,
"resnet_out_scale_factor": 1.0,
"resnet_skip_time_act": false,
"resnet_time_scale_shift": "default",
"reverse_transformer_layers_per_block": null,
"sample_size": 64,
"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,
"transformers_version": null,
"up_block_types": [
"CrossAttnUpBlock2D",
"UpBlock2D"
],
"upcast_attention": false,
"use_linear_projection": false
}
|