File size: 2,526 Bytes
89d090e |
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 |
{
"_class_name": "ControlNetModel",
"_commit_hash": null,
"_diffusers_version": "0.28.2",
"_name_or_path": "lllyasviel/control_v11p_sd15_openpose",
"_use_default_values": [
"num_attention_heads",
"transformer_layers_per_block",
"mid_block_type",
"addition_embed_type",
"encoder_hid_dim",
"encoder_hid_dim_type",
"conditioning_channels",
"addition_embed_type_num_heads",
"global_pool_conditions",
"addition_time_embed_dim"
],
"act_fn": "silu",
"addition_embed_type": null,
"addition_embed_type_num_heads": 64,
"addition_time_embed_dim": null,
"attention_head_dim": 8,
"block_out_channels": [
320,
640,
1280,
1280
],
"class_embed_type": null,
"conditioning_channels": 3,
"conditioning_embedding_out_channels": [
16,
32,
96,
256
],
"controlnet_conditioning_channel_order": "rgb",
"cross_attention_dim": 768,
"down_block_types": [
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"DownBlock2D"
],
"downsample_padding": 1,
"encoder_hid_dim": null,
"encoder_hid_dim_type": null,
"flip_sin_to_cos": true,
"freq_shift": 0,
"global_pool_conditions": false,
"in_channels": 4,
"layers_per_block": 2,
"mid_block_scale_factor": 1,
"mid_block_type": "UNetMidBlock2DCrossAttn",
"neuron": {
"auto_cast": "matmul",
"auto_cast_type": "bf16",
"compiler_type": "neuronx-cc",
"compiler_version": "2.14.227.0+2d4f85be",
"dynamic_batch_size": false,
"inline_weights_to_neff": true,
"input_names": [
"sample",
"timestep",
"encoder_hidden_states",
"controlnet_cond",
"conditioning_scale"
],
"model_type": "controlnet",
"optlevel": "2",
"output_attentions": false,
"output_hidden_states": false,
"output_names": [
"down_block_res_samples",
"mid_block_res_sample"
],
"static_batch_size": 1,
"static_encoder_hidden_size": 768,
"static_height": 64,
"static_num_channels": 4,
"static_sequence_length": 77,
"static_vae_scale_factor": 8,
"static_width": 64
},
"norm_eps": 1e-05,
"norm_num_groups": 32,
"num_attention_heads": null,
"num_class_embeds": null,
"only_cross_attention": false,
"projection_class_embeddings_input_dim": null,
"resnet_time_scale_shift": "default",
"task": "semantic-segmentation",
"transformer_layers_per_block": 1,
"transformers_version": null,
"upcast_attention": false,
"use_linear_projection": false
}
|