human_place / config.json
dyamagishi's picture
End of training
96ac46e verified
{
"_class_name": "ControlNetModel",
"_diffusers_version": "0.30.0.dev0",
"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
],
"block_out_channels": [
320,
640,
1280
],
"class_embed_type": null,
"conditioning_channels": 3,
"conditioning_embedding_out_channels": [
16,
32,
96,
256
],
"controlnet_conditioning_channel_order": "rgb",
"cross_attention_dim": 2048,
"down_block_types": [
"DownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D"
],
"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",
"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": 2816,
"resnet_time_scale_shift": "default",
"transformer_layers_per_block": [
1,
2,
10
],
"upcast_attention": false,
"use_linear_projection": true
}