unet/config.json
1.7 KB · 73 lines · json Raw
1 {
2 "_class_name": "UNet2DConditionModel",
3 "_diffusers_version": "0.29.0",
4 "act_fn": "silu",
5 "addition_embed_type": "text_time",
6 "addition_embed_type_num_heads": 64,
7 "addition_time_embed_dim": 256,
8 "attention_head_dim": [
9 5,
10 10,
11 20
12 ],
13 "attention_type": "default",
14 "block_out_channels": [
15 320,
16 640,
17 1280
18 ],
19 "center_input_sample": false,
20 "class_embed_type": null,
21 "class_embeddings_concat": false,
22 "conv_in_kernel": 3,
23 "conv_out_kernel": 3,
24 "cross_attention_dim": 2048,
25 "cross_attention_norm": null,
26 "down_block_types": [
27 "DownBlock2D",
28 "CrossAttnDownBlock2D",
29 "CrossAttnDownBlock2D"
30 ],
31 "downsample_padding": 1,
32 "dropout": 0.0,
33 "dual_cross_attention": false,
34 "encoder_hid_dim": null,
35 "encoder_hid_dim_type": null,
36 "flip_sin_to_cos": true,
37 "freq_shift": 0,
38 "in_channels": 4,
39 "layers_per_block": 2,
40 "mid_block_only_cross_attention": null,
41 "mid_block_scale_factor": 1,
42 "mid_block_type": "UNetMidBlock2DCrossAttn",
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 "out_channels": 4,
49 "projection_class_embeddings_input_dim": 2816,
50 "resnet_out_scale_factor": 1.0,
51 "resnet_skip_time_act": false,
52 "resnet_time_scale_shift": "default",
53 "reverse_transformer_layers_per_block": null,
54 "sample_size": 128,
55 "time_cond_proj_dim": null,
56 "time_embedding_act_fn": null,
57 "time_embedding_dim": null,
58 "time_embedding_type": "positional",
59 "timestep_post_act": null,
60 "transformer_layers_per_block": [
61 1,
62 2,
63 10
64 ],
65 "up_block_types": [
66 "CrossAttnUpBlock2D",
67 "CrossAttnUpBlock2D",
68 "UpBlock2D"
69 ],
70 "upcast_attention": null,
71 "use_linear_projection": true
72 }
73