Upload 2 files
Browse files- config.json +184 -0
- diffusion_pytorch_model.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,184 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "ControlNetXSModel",
|
3 |
+
"_diffusers_version": "0.24.0.dev0",
|
4 |
+
"_name_or_path": "/Users/umer/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1-base/snapshots/5ede9e4bf3e3fd1cb0ef2f7a3fff13ee514fdf06/unet",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"attention_head_dim": [
|
8 |
+
1,
|
9 |
+
1,
|
10 |
+
2,
|
11 |
+
2
|
12 |
+
],
|
13 |
+
"attention_type": "default",
|
14 |
+
"base_model_channel_sizes": {
|
15 |
+
"down": [
|
16 |
+
[
|
17 |
+
4,
|
18 |
+
320
|
19 |
+
],
|
20 |
+
[
|
21 |
+
320,
|
22 |
+
320
|
23 |
+
],
|
24 |
+
[
|
25 |
+
320,
|
26 |
+
320
|
27 |
+
],
|
28 |
+
[
|
29 |
+
320,
|
30 |
+
320
|
31 |
+
],
|
32 |
+
[
|
33 |
+
320,
|
34 |
+
640
|
35 |
+
],
|
36 |
+
[
|
37 |
+
640,
|
38 |
+
640
|
39 |
+
],
|
40 |
+
[
|
41 |
+
640,
|
42 |
+
640
|
43 |
+
],
|
44 |
+
[
|
45 |
+
640,
|
46 |
+
1280
|
47 |
+
],
|
48 |
+
[
|
49 |
+
1280,
|
50 |
+
1280
|
51 |
+
],
|
52 |
+
[
|
53 |
+
1280,
|
54 |
+
1280
|
55 |
+
],
|
56 |
+
[
|
57 |
+
1280,
|
58 |
+
1280
|
59 |
+
],
|
60 |
+
[
|
61 |
+
1280,
|
62 |
+
1280
|
63 |
+
]
|
64 |
+
],
|
65 |
+
"mid": [
|
66 |
+
[
|
67 |
+
1280,
|
68 |
+
1280
|
69 |
+
]
|
70 |
+
],
|
71 |
+
"up": [
|
72 |
+
[
|
73 |
+
2560,
|
74 |
+
1280
|
75 |
+
],
|
76 |
+
[
|
77 |
+
2560,
|
78 |
+
1280
|
79 |
+
],
|
80 |
+
[
|
81 |
+
2560,
|
82 |
+
1280
|
83 |
+
],
|
84 |
+
[
|
85 |
+
2560,
|
86 |
+
1280
|
87 |
+
],
|
88 |
+
[
|
89 |
+
2560,
|
90 |
+
1280
|
91 |
+
],
|
92 |
+
[
|
93 |
+
1920,
|
94 |
+
1280
|
95 |
+
],
|
96 |
+
[
|
97 |
+
1920,
|
98 |
+
640
|
99 |
+
],
|
100 |
+
[
|
101 |
+
1280,
|
102 |
+
640
|
103 |
+
],
|
104 |
+
[
|
105 |
+
960,
|
106 |
+
640
|
107 |
+
],
|
108 |
+
[
|
109 |
+
960,
|
110 |
+
320
|
111 |
+
],
|
112 |
+
[
|
113 |
+
640,
|
114 |
+
320
|
115 |
+
],
|
116 |
+
[
|
117 |
+
640,
|
118 |
+
320
|
119 |
+
]
|
120 |
+
]
|
121 |
+
},
|
122 |
+
"block_out_channels": [
|
123 |
+
4,
|
124 |
+
8,
|
125 |
+
16,
|
126 |
+
16
|
127 |
+
],
|
128 |
+
"center_input_sample": false,
|
129 |
+
"conditioning_block_sizes": [
|
130 |
+
16,
|
131 |
+
32,
|
132 |
+
96,
|
133 |
+
256
|
134 |
+
],
|
135 |
+
"conditioning_channels": 3,
|
136 |
+
"controlnet_conditioning_channel_order": "rgb",
|
137 |
+
"conv_in_kernel": 3,
|
138 |
+
"conv_out_kernel": 3,
|
139 |
+
"cross_attention_dim": 1024,
|
140 |
+
"cross_attention_norm": null,
|
141 |
+
"down_block_types": [
|
142 |
+
"CrossAttnDownBlock2D",
|
143 |
+
"CrossAttnDownBlock2D",
|
144 |
+
"CrossAttnDownBlock2D",
|
145 |
+
"DownBlock2D"
|
146 |
+
],
|
147 |
+
"downsample_padding": 1,
|
148 |
+
"dropout": 0.0,
|
149 |
+
"dual_cross_attention": false,
|
150 |
+
"encoder_hid_dim": null,
|
151 |
+
"encoder_hid_dim_type": null,
|
152 |
+
"in_channels": 4,
|
153 |
+
"layers_per_block": 2,
|
154 |
+
"learn_embedding": true,
|
155 |
+
"mid_block_only_cross_attention": null,
|
156 |
+
"mid_block_scale_factor": 1,
|
157 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
158 |
+
"norm_eps": 1e-05,
|
159 |
+
"norm_num_groups": 4,
|
160 |
+
"num_attention_heads": null,
|
161 |
+
"only_cross_attention": false,
|
162 |
+
"out_channels": 4,
|
163 |
+
"resnet_out_scale_factor": 1.0,
|
164 |
+
"resnet_skip_time_act": false,
|
165 |
+
"resnet_time_scale_shift": "default",
|
166 |
+
"reverse_transformer_layers_per_block": null,
|
167 |
+
"sample_size": 64,
|
168 |
+
"time_cond_proj_dim": null,
|
169 |
+
"time_embedding_act_fn": null,
|
170 |
+
"time_embedding_dim": 1280,
|
171 |
+
"time_embedding_input_dim": 320,
|
172 |
+
"time_embedding_mix": 1.0,
|
173 |
+
"time_embedding_type": "positional",
|
174 |
+
"timestep_post_act": null,
|
175 |
+
"transformer_layers_per_block": 1,
|
176 |
+
"up_block_types": [
|
177 |
+
"UpBlock2D",
|
178 |
+
"CrossAttnUpBlock2D",
|
179 |
+
"CrossAttnUpBlock2D",
|
180 |
+
"CrossAttnUpBlock2D"
|
181 |
+
],
|
182 |
+
"upcast_attention": false,
|
183 |
+
"use_linear_projection": true
|
184 |
+
}
|
diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f27b5d3e97c8c31123245fe25306526a2fd5e6268508b77d073f2df10f079be
|
3 |
+
size 56794056
|