diffusers/controlnet-depth-sdxl-1.0-mid

1{2  "_class_name": "ControlNetModel",3  "_diffusers_version": "0.20.0.dev0",4  "_name_or_path": "valhalla/d-n-1a",5  "act_fn": "silu",6  "addition_embed_type": "text_time",7  "addition_embed_type_num_heads": 64,8  "addition_time_embed_dim": 256,9  "attention_head_dim": [10    5,11    10,12    2013  ],14  "block_out_channels": [15    320,16    640,17    128018  ],19  "class_embed_type": null,20  "conditioning_channels": 3,21  "conditioning_embedding_out_channels": [22    16,23    32,24    96,25    25626  ],27  "controlnet_conditioning_channel_order": "rgb",28  "cross_attention_dim": 2048,29  "down_block_types": [30    "DownBlock2D",31    "CrossAttnDownBlock2D",32    "CrossAttnDownBlock2D"33  ],34  "downsample_padding": 1,35  "encoder_hid_dim": null,36  "encoder_hid_dim_type": null,37  "flip_sin_to_cos": true,38  "freq_shift": 0,39  "global_pool_conditions": false,40  "in_channels": 4,41  "layers_per_block": 2,42  "mid_block_scale_factor": 1,43  "norm_eps": 1e-05,44  "norm_num_groups": 32,45  "num_attention_heads": null,46  "num_class_embeds": null,47  "only_cross_attention": false,48  "projection_class_embeddings_input_dim": 2816,49  "resnet_time_scale_shift": "default",50  "transformer_layers_per_block": [51    0,52    0,53    154  ],55  "upcast_attention": null,56  "use_linear_projection": true57}58