Hugging Face's logo

crumb
/
genshin-stable-inversion

Text-to-Image
English
stable-diffusion
Model card Files Community
crumb commited on
Commit
2e6335a
•
1 Parent(s): bf60456

Upload stable_inversion (1).ipynb

Browse files
Files changed (1) hide show
  1. stable_inversion (1).ipynb +1714 -0
stable_inversion (1).ipynb ADDED
@@ -0,0 +1,1714 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "markdown",
5
+ "source": [
6
+ "# Trinket! Stable Inversion\n",
7
+ "A cheap alternative to finetuning stable diffusion, by [crumb](https://twitter.com/aicrumb)\n",
8
+ "\n",
9
+ "Finetunes the embedding layer like Textual-Inversion does, but on CLIP Text/Image pairs instead of reconstruction loss from Stable Diffusion. Lower memory requirements + (sometimes) faster than finetuning the traditional way."
10
+ ],
11
+ "metadata": {
12
+ "id": "mSXDq5-qTSF6"
13
+ },
14
+ "id": "mSXDq5-qTSF6"
15
+ },
16
+ {
17
+ "cell_type": "code",
18
+ "source": [
19
+ "!pip install git+https://github.com/openai/CLIP -q\n",
20
+ "!pip install bitsandbytes -q"
21
+ ],
22
+ "metadata": {
23
+ "id": "yB-XeS51NmI2"
24
+ },
25
+ "id": "yB-XeS51NmI2",
26
+ "execution_count": 1,
27
+ "outputs": []
28
+ },
29
+ {
30
+ "cell_type": "code",
31
+ "source": [
32
+ "import bitsandbytes as bnb\n",
33
+ "import torchvision\n",
34
+ "from torchvision import transforms\n",
35
+ "from tqdm.auto import *\n",
36
+ "from torch import nn, optim\n",
37
+ "from torch.nn import functional as F\n",
38
+ "from PIL import Image\n",
39
+ "import requests\n",
40
+ "from io import BytesIO\n",
41
+ "import torch\n",
42
+ "import random\n",
43
+ "import clip\n",
44
+ "import pandas as pd"
45
+ ],
46
+ "metadata": {
47
+ "id": "x1OogszooEi6",
48
+ "colab": {
49
+ "base_uri": "https://localhost:8080/"
50
+ },
51
+ "outputId": "a55a628d-aafc-407e-a2a9-fb03b8a0896a"
52
+ },
53
+ "id": "x1OogszooEi6",
54
+ "execution_count": 2,
55
+ "outputs": [
56
+ {
57
+ "output_type": "stream",
58
+ "name": "stdout",
59
+ "text": [
60
+ "\n",
61
+ "===================================BUG REPORT===================================\n",
62
+ "Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues\n",
63
+ "For effortless bug reporting copy-paste your error into this form: https://docs.google.com/forms/d/e/1FAIpQLScPB8emS3Thkp66nvqwmjTEgxp8Y9ufuWTzFyr9kJ5AoI47dQ/viewform?usp=sf_link\n",
64
+ "================================================================================\n",
65
+ "CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching /usr/local/cuda/lib64...\n",
66
+ "CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so\n",
67
+ "CUDA SETUP: Highest compute capability among GPUs detected: 7.5\n",
68
+ "CUDA SETUP: Detected CUDA version 111\n",
69
+ "CUDA SETUP: Loading binary /usr/local/lib/python3.7/dist-packages/bitsandbytes/libbitsandbytes_cuda111.so...\n"
70
+ ]
71
+ },
72
+ {
73
+ "output_type": "stream",
74
+ "name": "stderr",
75
+ "text": [
76
+ "/usr/local/lib/python3.7/dist-packages/bitsandbytes/cuda_setup/paths.py:99: UserWarning: /usr/lib64-nvidia did not contain libcudart.so as expected! Searching further paths...\n",
77
+ " f'{candidate_env_vars[\"LD_LIBRARY_PATH\"]} did not contain '\n",
78
+ "/usr/local/lib/python3.7/dist-packages/bitsandbytes/cuda_setup/paths.py:21: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('{\"kernelManagerProxyPort\"'), PosixPath('\"/usr/local/bin/dap_multiplexer\",\"enableLsp\"'), PosixPath('\"172.28.0.3\",\"jupyterArgs\"'), PosixPath('[\"--ip=172.28.0.2\"],\"debugAdapterMultiplexerPath\"'), PosixPath('true}'), PosixPath('6000,\"kernelManagerProxyHost\"')}\n",
79
+ " \"WARNING: The following directories listed in your path were found to \"\n",
80
+ "/usr/local/lib/python3.7/dist-packages/bitsandbytes/cuda_setup/paths.py:21: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/env/python')}\n",
81
+ " \"WARNING: The following directories listed in your path were found to \"\n",
82
+ "/usr/local/lib/python3.7/dist-packages/bitsandbytes/cuda_setup/paths.py:21: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('module'), PosixPath('//ipykernel.pylab.backend_inline')}\n",
83
+ " \"WARNING: The following directories listed in your path were found to \"\n"
84
+ ]
85
+ }
86
+ ]
87
+ },
88
+ {
89
+ "cell_type": "code",
90
+ "execution_count": 3,
91
+ "id": "22b6861e-289f-4779-bbf1-40bfd1327823",
92
+ "metadata": {
93
+ "colab": {
94
+ "base_uri": "https://localhost:8080/"
95
+ },
96
+ "id": "22b6861e-289f-4779-bbf1-40bfd1327823",
97
+ "outputId": "fd96d25d-8cbf-43d2-8d5b-983856bf2a3a"
98
+ },
99
+ "outputs": [
100
+ {
101
+ "output_type": "stream",
102
+ "name": "stdout",
103
+ "text": [
104
+ "Loaded CLIP\n"
105
+ ]
106
+ }
107
+ ],
108
+ "source": [
109
+ "# the stable diffusion model uses L/14 by default\n",
110
+ "clip_model, _ = clip.load(\"ViT-L/14\", jit=False)\n",
111
+ "clip_model = clip_model.cuda()\n",
112
+ "print(\"Loaded CLIP\")"
113
+ ]
114
+ },
115
+ {
116
+ "cell_type": "code",
117
+ "execution_count": 4,
118
+ "id": "eaa9bde8-3fdd-48df-aa36-8b88cec285be",
119
+ "metadata": {
120
+ "id": "eaa9bde8-3fdd-48df-aa36-8b88cec285be"
121
+ },
122
+ "outputs": [],
123
+ "source": [
124
+ "bs = 16 # need a large batch size for the contrastive loss to work properly\n",
125
+ "steps = 64\n",
126
+ "epochs = 4\n",
127
+ "lr = 1e-3"
128
+ ]
129
+ },
130
+ {
131
+ "cell_type": "code",
132
+ "execution_count": 5,
133
+ "id": "0667d187-2c3e-40b8-a2fd-b408d5f144c5",
134
+ "metadata": {
135
+ "colab": {
136
+ "base_uri": "https://localhost:8080/",
137
+ "height": 206
138
+ },
139
+ "id": "0667d187-2c3e-40b8-a2fd-b408d5f144c5",
140
+ "outputId": "b8f6056a-c2ac-4b89-e222-0d47705617e9"
141
+ },
142
+ "outputs": [
143
+ {
144
+ "output_type": "execute_result",
145
+ "data": {
146
+ "text/plain": [
147
+ " Unnamed: 0 url \\\n",
148
+ "0 0 https://cdn.donmai.us/original/51/bb/51bb44d69... \n",
149
+ "1 1 https://cdn.donmai.us/original/4f/8e/4f8e5eaba... \n",
150
+ "2 2 https://cdn.donmai.us/original/c8/54/c85428d89... \n",
151
+ "3 3 https://cdn.donmai.us/original/e9/fc/e9fcc788e... \n",
152
+ "4 4 https://cdn.donmai.us/original/8a/63/8a639d21b... \n",
153
+ "\n",
154
+ " prompt \n",
155
+ "0 genshin_impact boo_tao_(genshin_impact) hu_tao... \n",
156
+ "1 genshin_impact arlecchino_(genshin_impact) cap... \n",
157
+ "2 genshin_impact fischl_(ein_immernachtstraum)_(... \n",
158
+ "3 genshin_impact eula_(genshin_impact) 1girl :o ... \n",
159
+ "4 genshin_impact kuki_shinobu 1girl breasts brid... "
160
+ ],
161
+ "text/html": [
162
+ "\n",
163
+ " <div id=\"df-b1359ba3-d298-4260-9864-de09e0a61fd0\">\n",
164
+ " <div class=\"colab-df-container\">\n",
165
+ " <div>\n",
166
+ "<style scoped>\n",
167
+ " .dataframe tbody tr th:only-of-type {\n",
168
+ " vertical-align: middle;\n",
169
+ " }\n",
170
+ "\n",
171
+ " .dataframe tbody tr th {\n",
172
+ " vertical-align: top;\n",
173
+ " }\n",
174
+ "\n",
175
+ " .dataframe thead th {\n",
176
+ " text-align: right;\n",
177
+ " }\n",
178
+ "</style>\n",
179
+ "<table border=\"1\" class=\"dataframe\">\n",
180
+ " <thead>\n",
181
+ " <tr style=\"text-align: right;\">\n",
182
+ " <th></th>\n",
183
+ " <th>Unnamed: 0</th>\n",
184
+ " <th>url</th>\n",
185
+ " <th>prompt</th>\n",
186
+ " </tr>\n",
187
+ " </thead>\n",
188
+ " <tbody>\n",
189
+ " <tr>\n",
190
+ " <th>0</th>\n",
191
+ " <td>0</td>\n",
192
+ " <td>https://cdn.donmai.us/original/51/bb/51bb44d69...</td>\n",
193
+ " <td>genshin_impact boo_tao_(genshin_impact) hu_tao...</td>\n",
194
+ " </tr>\n",
195
+ " <tr>\n",
196
+ " <th>1</th>\n",
197
+ " <td>1</td>\n",
198
+ " <td>https://cdn.donmai.us/original/4f/8e/4f8e5eaba...</td>\n",
199
+ " <td>genshin_impact arlecchino_(genshin_impact) cap...</td>\n",
200
+ " </tr>\n",
201
+ " <tr>\n",
202
+ " <th>2</th>\n",
203
+ " <td>2</td>\n",
204
+ " <td>https://cdn.donmai.us/original/c8/54/c85428d89...</td>\n",
205
+ " <td>genshin_impact fischl_(ein_immernachtstraum)_(...</td>\n",
206
+ " </tr>\n",
207
+ " <tr>\n",
208
+ " <th>3</th>\n",
209
+ " <td>3</td>\n",
210
+ " <td>https://cdn.donmai.us/original/e9/fc/e9fcc788e...</td>\n",
211
+ " <td>genshin_impact eula_(genshin_impact) 1girl :o ...</td>\n",
212
+ " </tr>\n",
213
+ " <tr>\n",
214
+ " <th>4</th>\n",
215
+ " <td>4</td>\n",
216
+ " <td>https://cdn.donmai.us/original/8a/63/8a639d21b...</td>\n",
217
+ " <td>genshin_impact kuki_shinobu 1girl breasts brid...</td>\n",
218
+ " </tr>\n",
219
+ " </tbody>\n",
220
+ "</table>\n",
221
+ "</div>\n",
222
+ " <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b1359ba3-d298-4260-9864-de09e0a61fd0')\"\n",
223
+ " title=\"Convert this dataframe to an interactive table.\"\n",
224
+ " style=\"display:none;\">\n",
225
+ " \n",
226
+ " <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
227
+ " width=\"24px\">\n",
228
+ " <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
229
+ " <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
230
+ " </svg>\n",
231
+ " </button>\n",
232
+ " \n",
233
+ " <style>\n",
234
+ " .colab-df-container {\n",
235
+ " display:flex;\n",
236
+ " flex-wrap:wrap;\n",
237
+ " gap: 12px;\n",
238
+ " }\n",
239
+ "\n",
240
+ " .colab-df-convert {\n",
241
+ " background-color: #E8F0FE;\n",
242
+ " border: none;\n",
243
+ " border-radius: 50%;\n",
244
+ " cursor: pointer;\n",
245
+ " display: none;\n",
246
+ " fill: #1967D2;\n",
247
+ " height: 32px;\n",
248
+ " padding: 0 0 0 0;\n",
249
+ " width: 32px;\n",
250
+ " }\n",
251
+ "\n",
252
+ " .colab-df-convert:hover {\n",
253
+ " background-color: #E2EBFA;\n",
254
+ " box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
255
+ " fill: #174EA6;\n",
256
+ " }\n",
257
+ "\n",
258
+ " [theme=dark] .colab-df-convert {\n",
259
+ " background-color: #3B4455;\n",
260
+ " fill: #D2E3FC;\n",
261
+ " }\n",
262
+ "\n",
263
+ " [theme=dark] .colab-df-convert:hover {\n",
264
+ " background-color: #434B5C;\n",
265
+ " box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
266
+ " filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
267
+ " fill: #FFFFFF;\n",
268
+ " }\n",
269
+ " </style>\n",
270
+ "\n",
271
+ " <script>\n",
272
+ " const buttonEl =\n",
273
+ " document.querySelector('#df-b1359ba3-d298-4260-9864-de09e0a61fd0 button.colab-df-convert');\n",
274
+ " buttonEl.style.display =\n",
275
+ " google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
276
+ "\n",
277
+ " async function convertToInteractive(key) {\n",
278
+ " const element = document.querySelector('#df-b1359ba3-d298-4260-9864-de09e0a61fd0');\n",
279
+ " const dataTable =\n",
280
+ " await google.colab.kernel.invokeFunction('convertToInteractive',\n",
281
+ " [key], {});\n",
282
+ " if (!dataTable) return;\n",
283
+ "\n",
284
+ " const docLinkHtml = 'Like what you see? Visit the ' +\n",
285
+ " '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
286
+ " + ' to learn more about interactive tables.';\n",
287
+ " element.innerHTML = '';\n",
288
+ " dataTable['output_type'] = 'display_data';\n",
289
+ " await google.colab.output.renderOutput(dataTable, element);\n",
290
+ " const docLink = document.createElement('div');\n",
291
+ " docLink.innerHTML = docLinkHtml;\n",
292
+ " element.appendChild(docLink);\n",
293
+ " }\n",
294
+ " </script>\n",
295
+ " </div>\n",
296
+ " </div>\n",
297
+ " "
298
+ ]
299
+ },
300
+ "metadata": {},
301
+ "execution_count": 5
302
+ }
303
+ ],
304
+ "source": [
305
+ "# ultimately you just need >1000 prompt+url pairs in lists named prompts and urls, however you load it is fine\n",
306
+ "# this is how i scraped them so this is how i load them\n",
307
+ "# you can scrape danbooru/safebooru/others with pybooru with this script from waifu-diffusion https://github.com/harubaru/waifu-diffusion/blob/main/danbooru_data/scrape.py\n",
308
+ "df = pd.read_csv(\"/content/genshin.csv\")\n",
309
+ "prompts = df['prompt']#[:steps*bs]\n",
310
+ "urls = df['url']#[:steps*bs\n",
311
+ "df.head()"
312
+ ]
313
+ },
314
+ {
315
+ "cell_type": "code",
316
+ "source": [
317
+ "print(len(prompts))"
318
+ ],
319
+ "metadata": {
320
+ "colab": {
321
+ "base_uri": "https://localhost:8080/"
322
+ },
323
+ "id": "6lYQYqKEZKhv",
324
+ "outputId": "7d26b946-ce1e-41ed-abaf-a4efed5d02cc"
325
+ },
326
+ "id": "6lYQYqKEZKhv",
327
+ "execution_count": 6,
328
+ "outputs": [
329
+ {
330
+ "output_type": "stream",
331
+ "name": "stdout",
332
+ "text": [
333
+ "1200\n"
334
+ ]
335
+ }
336
+ ]
337
+ },
338
+ {
339
+ "cell_type": "code",
340
+ "execution_count": 7,
341
+ "id": "12fce080-73f3-430f-ba2c-99f265316b66",
342
+ "metadata": {
343
+ "id": "12fce080-73f3-430f-ba2c-99f265316b66"
344
+ },
345
+ "outputs": [],
346
+ "source": [
347
+ "clip_model.token_embedding.weight.requires_grad = True\n",
348
+ "# opt = optim.Adam([clip_model.token_embedding.weight], lr)\n",
349
+ "opt = bnb.optim.AdamW8bit([clip_model.token_embedding.weight], lr)"
350
+ ]
351
+ },
352
+ {
353
+ "cell_type": "code",
354
+ "execution_count": 8,
355
+ "id": "9a4b1696-a8d9-4eea-a8e0-ba372d450619",
356
+ "metadata": {
357
+ "id": "9a4b1696-a8d9-4eea-a8e0-ba372d450619"
358
+ },
359
+ "outputs": [],
360
+ "source": [
361
+ "# functions from another project of mine that's a bit messy\n",
362
+ "def fix_to_224(pil_image):\n",
363
+ " width, height = pil_image.size\n",
364
+ " if width < height:\n",
365
+ " new_width = 224\n",
366
+ " new_height = int(new_width * height / width)\n",
367
+ " else:\n",
368
+ " new_height = 224\n",
369
+ " new_width = int(new_height * width / height)\n",
370
+ " return pil_image.resize((new_width, new_height))\n",
371
+ "def to_tensor_and_center_crop(pil_image):\n",
372
+ " tensor = torchvision.transforms.functional.to_tensor(pil_image)\n",
373
+ " center_crop = torchvision.transforms.functional.center_crop(tensor, (224, 224))\n",
374
+ " return center_crop\n",
375
+ "def fix(img):\n",
376
+ " return to_tensor_and_center_crop(fix_to_224(img))\n",
377
+ "\n",
378
+ "iter_prompts = iter(prompts)\n",
379
+ "iter_urls = iter(urls)\n",
380
+ "def get_batch(size=8, step=1, steps_per_epoch=128, epoch=1, total_epochs=1):\n",
381
+ " to_tensor = transforms.ToTensor()\n",
382
+ " x = []\n",
383
+ " y = []\n",
384
+ " total_steps = total_epochs*steps_per_epoch\n",
385
+ " current_fraction = (epoch*steps_per_epoch-steps_per_epoch+step) / total_steps\n",
386
+ "\n",
387
+ " while len(x) < size:\n",
388
+ " # uncomment these and space the big block right one tab\n",
389
+ " # if you're using a set that might have dead urls\n",
390
+ " try:\n",
391
+ " url = next(iter_urls)\n",
392
+ " response = requests.get(url)\n",
393
+ " img = Image.open(BytesIO(response.content))\n",
394
+ " img = img.convert(\"RGB\")\n",
395
+ " img = fix(img)\n",
396
+ " x.append(img.unsqueeze(0))\n",
397
+ "\n",
398
+ " p = next(iter_prompts)\n",
399
+ "\n",
400
+ " # comment out these lines if you aren't using danbooru tags\n",
401
+ " p = p.split(\" \")\n",
402
+ " random.shuffle(p)\n",
403
+ " if current_fraction > 0.5: # halfway through training, start dropping half of the tags\n",
404
+ " p = p[:len(p)//2]\n",
405
+ " if current_fraction > 0.75: # halfway through training, start dropping half of the tags\n",
406
+ " p = p[:len(p)//2]\n",
407
+ " p = \" \".join(p)\n",
408
+ " y.append(p)\n",
409
+ " except KeyboardInterrupt:\n",
410
+ " print('Interrupted')\n",
411
+ " break\n",
412
+ " except:\n",
413
+ " pass\n",
414
+ " \n",
415
+ " x = torch.cat(x, 0)\n",
416
+ " x = clip_model.encode_image(x.cuda())\n",
417
+ " \n",
418
+ " y = clip.tokenize(y, truncate=True)\n",
419
+ " y = clip_model.encode_text(y.cuda())\n",
420
+ " return x, y"
421
+ ]
422
+ },
423
+ {
424
+ "cell_type": "code",
425
+ "execution_count": null,
426
+ "id": "203637dd-441e-4b43-944d-48ffa126e826",
427
+ "metadata": {
428
+ "colab": {
429
+ "base_uri": "https://localhost:8080/",
430
+ "height": 182,
431
+ "referenced_widgets": [
432
+ "cfab11c900c44070b2dc032034b9a65d",
433
+ "edf50d7b6e8b475abd9e1ebae7778aba",
434
+ "af697a5f975c405190c54d2a349b551c",
435
+ "1953f85f00e04cb4bb95acadbb589b12",
436
+ "d28248f12d834263a1605afed777077a",
437
+ "1b255d9b51cb4dee82e1d14a506bf85e",
438
+ "effd6703ac904650a7c02fbac19d1ce9",
439
+ "f62a8b3dfedd4500b795e8a9e57ee4e1",
440
+ "c2669c5874354798b33d7da9a5d8084d",
441
+ "6b085d5276bf42c8b8e6a050de4730c9",
442
+ "47347341d5a14564a25e52179187b218",
443
+ "39487ee2262647a79ed05bd89413ec25",
444
+ "37fd57a2be584e37aade4f200aca564e",
445
+ "2daa2d8768f94963b4be13ee5108ec16",
446
+ "41d52c3d2db543ac8654f2d79ea72f51",
447
+ "cee7cfd5a46a4a86a048e84c9aa6df56",
448
+ "365846f3939d49188dd2698ccb4a0c6d",
449
+ "fa8cd1c1559248aeb8a920d6a1f7b8ca",
450
+ "8d6f469af323498aae3b8c2fd2e4f7de",
451
+ "a58aa5c526234c25bd330564a8631310",
452
+ "355e7a4bac0f41d1a0a7aba831c1916b",
453
+ "d8d127599a964af2b22957e7cadc3949",
454
+ "94c994a72e6e47a581ef47eafc4f8621",
455
+ "e2409e281b874665bbe830fc5843e4fe",
456
+ "c980cbb0b5ba43378c84ea122829e70e",
457
+ "08ab7aae4ac341909798caf190c84ada",
458
+ "9decfef2a41f42f0a3b77dfaa3a02bac",
459
+ "a0f24920a480438381da74562a7f7df1",
460
+ "bc4723c3d801406b891f808c84e9e83b",
461
+ "c464d7549104481a90f75f3e5b219189",
462
+ "d9792cd6d5034352a3a9f2122bb5d9c0",
463
+ "8a9c974907c74fe29b6a323df7df0d4d",
464
+ "40ae1be859d74847b4f0944c4027e1cf"
465
+ ]
466
+ },
467
+ "id": "203637dd-441e-4b43-944d-48ffa126e826",
468
+ "outputId": "4ea5f3da-86fa-4910-d919-fc1ef0d8f007"
469
+ },
470
+ "outputs": [
471
+ {
472
+ "output_type": "display_data",
473
+ "data": {
474
+ "text/plain": [
475
+ " 0%| | 0/4 [00:00<?, ?it/s]"
476
+ ],
477
+ "application/vnd.jupyter.widget-view+json": {
478
+ "version_major": 2,
479
+ "version_minor": 0,
480
+ "model_id": "cfab11c900c44070b2dc032034b9a65d"
481
+ }
482
+ },
483
+ "metadata": {}
484
+ },
485
+ {
486
+ "output_type": "display_data",
487
+ "data": {
488
+ "text/plain": [
489
+ " 0%| | 0/64 [00:00<?, ?it/s]"
490
+ ],
491
+ "application/vnd.jupyter.widget-view+json": {
492
+ "version_major": 2,
493
+ "version_minor": 0,
494
+ "model_id": "39487ee2262647a79ed05bd89413ec25"
495
+ }
496
+ },
497
+ "metadata": {}
498
+ },
499
+ {
500
+ "output_type": "stream",
501
+ "name": "stderr",
502
+ "text": [
503
+ "/usr/local/lib/python3.7/dist-packages/PIL/Image.py:960: UserWarning: Palette images with Transparency expressed in bytes should be converted to RGBA images\n",
504
+ " \"Palette images with Transparency expressed in bytes should be \"\n",
505
+ "/usr/local/lib/python3.7/dist-packages/PIL/TiffImagePlugin.py:788: UserWarning: Corrupt EXIF data. Expecting to read 4 bytes but only got 0. \n",
506
+ " warnings.warn(str(msg))\n"
507
+ ]
508
+ },
509
+ {
510
+ "output_type": "display_data",
511
+ "data": {
512
+ "text/plain": [
513
+ " 0%| | 0/64 [00:00<?, ?it/s]"
514
+ ],
515
+ "application/vnd.jupyter.widget-view+json": {
516
+ "version_major": 2,
517
+ "version_minor": 0,
518
+ "model_id": "94c994a72e6e47a581ef47eafc4f8621"
519
+ }
520
+ },
521
+ "metadata": {}
522
+ }
523
+ ],
524
+ "source": [
525
+ "losses = []\n",
526
+ "\n",
527
+ "for epoch in trange(epochs):\n",
528
+ " pbar = trange(steps)\n",
529
+ " iter_prompts = iter(prompts)\n",
530
+ " iter_urls = iter(urls)\n",
531
+ "\n",
532
+ " for i in pbar:\n",
533
+ " x, y = get_batch(bs, i, steps, epoch, epochs)\n",
534
+ " loss = (x-y).pow(2).mean()\n",
535
+ " # loss = spherical_distance_loss(x,y).mean() # TODO: try whatever loss they use in the CLIP paper instead\n",
536
+ " loss.backward()\n",
537
+ " opt.step()\n",
538
+ " opt.zero_grad()\n",
539
+ "\n",
540
+ " pbar.set_description(str(loss.item()))\n",
541
+ " losses.append(loss.item())"
542
+ ]
543
+ },
544
+ {
545
+ "cell_type": "code",
546
+ "source": [
547
+ "import matplotlib.pyplot as plt\n",
548
+ "\n",
549
+ "# hacky ema plot\n",
550
+ "losses_df = pd.DataFrame(losses, columns=['loss'])\n",
551
+ "losses_plot = losses_df.ewm(alpha=0.05).mean()['loss']\n",
552
+ "plt.plot(losses_plot)\n",
553
+ "plt.plot(losses)"
554
+ ],
555
+ "metadata": {
556
+ "id": "J5QkXxh5PI04"
557
+ },
558
+ "id": "J5QkXxh5PI04",
559
+ "execution_count": null,
560
+ "outputs": []
561
+ },
562
+ {
563
+ "cell_type": "code",
564
+ "source": [
565
+ "torch.save(clip_model.token_embedding.weight, \"token_embeddings.pt\")"
566
+ ],
567
+ "metadata": {
568
+ "id": "MdEjBt3hRIRB"
569
+ },
570
+ "id": "MdEjBt3hRIRB",
571
+ "execution_count": null,
572
+ "outputs": []
573
+ },
574
+ {
575
+ "cell_type": "code",
576
+ "source": [
577
+ "#@markdown 🔔\n",
578
+ "from google.colab import output\n",
579
+ "output.eval_js('new Audio(\"https://freesound.org/data/previews/80/80921_1022651-lq.ogg\").play()')"
580
+ ],
581
+ "metadata": {
582
+ "cellView": "form",
583
+ "id": "IU0mqpyVTQzt"
584
+ },
585
+ "id": "IU0mqpyVTQzt",
586
+ "execution_count": null,
587
+ "outputs": []
588
+ },
589
+ {
590
+ "cell_type": "markdown",
591
+ "source": [
592
+ "### Upload to 🤗"
593
+ ],
594
+ "metadata": {
595
+ "id": "E5TP5qjAkTjL"
596
+ },
597
+ "id": "E5TP5qjAkTjL"
598
+ },
599
+ {
600
+ "cell_type": "code",
601
+ "source": [
602
+ "#@markdown Log in\n",
603
+ "!pip install huggingface-hub -q\n",
604
+ "from huggingface_hub import notebook_login\n",
605
+ "notebook_login()"
606
+ ],
607
+ "metadata": {
608
+ "id": "bUdMc0o4kBYx",
609
+ "cellView": "form"
610
+ },
611
+ "id": "bUdMc0o4kBYx",
612
+ "execution_count": null,
613
+ "outputs": []
614
+ },
615
+ {
616
+ "cell_type": "code",
617
+ "source": [
618
+ "from huggingface_hub import HfApi\n",
619
+ "api = HfApi()\n",
620
+ "\n",
621
+ "#@markdown go ahead and create the repository on 🤗 before running this\n",
622
+ "my_repo = \"user/my-stable-inversion\" #@param {type:\"string\"}\n",
623
+ "\n",
624
+ "api.upload_file(\n",
625
+ " path_or_fileobj=\"token_embeddings.pt\",\n",
626
+ " path_in_repo=\"token_embeddings.pt\",\n",
627
+ " repo_id=my_repo,\n",
628
+ " repo_type=\"model\",\n",
629
+ ")"
630
+ ],
631
+ "metadata": {
632
+ "id": "WJ30dShA7koO"
633
+ },
634
+ "id": "WJ30dShA7koO",
635
+ "execution_count": null,
636
+ "outputs": []
637
+ },
638
+ {
639
+ "cell_type": "markdown",
640
+ "source": [
641
+ "how you can load the stable inversions into a diffusers-based notebook like [Doohickey](https://github.com/aicrumb/doohickey) might look something like this\n",
642
+ "\n",
643
+ "```\n",
644
+ "from huggingface_hub import hf_hub_download\n",
645
+ "\n",
646
+ "stable_inversion = \"user/my-stable-inversion\" #@param {type:\"string\"}\n",
647
+ "if len(stable_inversion)>1:\n",
648
+ " g = hf_hub_download(repo_id=stable_inversion, filename=\"token_embeddings.pt\")\n",
649
+ " text_encoder.text_model.embeddings.token_embedding.weight = torch.load(g)\n",
650
+ "```"
651
+ ],
652
+ "metadata": {
653
+ "id": "tIKiCVkHkFET"
654
+ },
655
+ "id": "tIKiCVkHkFET"
656
+ }
657
+ ],
658
+ "metadata": {
659
+ "kernelspec": {
660
+ "display_name": "Python 3 (ipykernel)",
661
+ "language": "python",
662
+ "name": "python3"
663
+ },
664
+ "language_info": {
665
+ "codemirror_mode": {
666
+ "name": "ipython",
667
+ "version": 3
668
+ },
669
+ "file_extension": ".py",
670
+ "mimetype": "text/x-python",
671
+ "name": "python",
672
+ "nbconvert_exporter": "python",
673
+ "pygments_lexer": "ipython3",
674
+ "version": "3.10.4"
675
+ },
676
+ "colab": {
677
+ "provenance": [],
678
+ "collapsed_sections": []
679
+ },
680
+ "accelerator": "GPU",
681
+ "widgets": {
682
+ "application/vnd.jupyter.widget-state+json": {
683
+ "cfab11c900c44070b2dc032034b9a65d": {
684
+ "model_module": "@jupyter-widgets/controls",
685
+ "model_name": "HBoxModel",
686
+ "model_module_version": "1.5.0",
687
+ "state": {
688
+ "_dom_classes": [],
689
+ "_model_module": "@jupyter-widgets/controls",
690
+ "_model_module_version": "1.5.0",
691
+ "_model_name": "HBoxModel",
692
+ "_view_count": null,
693
+ "_view_module": "@jupyter-widgets/controls",
694
+ "_view_module_version": "1.5.0",
695
+ "_view_name": "HBoxView",
696
+ "box_style": "",
697
+ "children": [
698
+ "IPY_MODEL_edf50d7b6e8b475abd9e1ebae7778aba",
699
+ "IPY_MODEL_af697a5f975c405190c54d2a349b551c",
700
+ "IPY_MODEL_1953f85f00e04cb4bb95acadbb589b12"
701
+ ],
702
+ "layout": "IPY_MODEL_d28248f12d834263a1605afed777077a"
703
+ }
704
+ },
705
+ "edf50d7b6e8b475abd9e1ebae7778aba": {
706
+ "model_module": "@jupyter-widgets/controls",
707
+ "model_name": "HTMLModel",
708
+ "model_module_version": "1.5.0",
709
+ "state": {
710
+ "_dom_classes": [],
711
+ "_model_module": "@jupyter-widgets/controls",
712
+ "_model_module_version": "1.5.0",
713
+ "_model_name": "HTMLModel",
714
+ "_view_count": null,
715
+ "_view_module": "@jupyter-widgets/controls",
716
+ "_view_module_version": "1.5.0",
717
+ "_view_name": "HTMLView",
718
+ "description": "",
719
+ "description_tooltip": null,
720
+ "layout": "IPY_MODEL_1b255d9b51cb4dee82e1d14a506bf85e",
721
+ "placeholder": "​",
722
+ "style": "IPY_MODEL_effd6703ac904650a7c02fbac19d1ce9",
723
+ "value": " 25%"
724
+ }
725
+ },
726
+ "af697a5f975c405190c54d2a349b551c": {
727
+ "model_module": "@jupyter-widgets/controls",
728
+ "model_name": "FloatProgressModel",
729
+ "model_module_version": "1.5.0",
730
+ "state": {
731
+ "_dom_classes": [],
732
+ "_model_module": "@jupyter-widgets/controls",
733
+ "_model_module_version": "1.5.0",
734
+ "_model_name": "FloatProgressModel",
735
+ "_view_count": null,
736
+ "_view_module": "@jupyter-widgets/controls",
737
+ "_view_module_version": "1.5.0",
738
+ "_view_name": "ProgressView",
739
+ "bar_style": "",
740
+ "description": "",
741
+ "description_tooltip": null,
742
+ "layout": "IPY_MODEL_f62a8b3dfedd4500b795e8a9e57ee4e1",
743
+ "max": 4,
744
+ "min": 0,
745
+ "orientation": "horizontal",
746
+ "style": "IPY_MODEL_c2669c5874354798b33d7da9a5d8084d",
747
+ "value": 1
748
+ }
749
+ },
750
+ "1953f85f00e04cb4bb95acadbb589b12": {
751
+ "model_module": "@jupyter-widgets/controls",
752
+ "model_name": "HTMLModel",
753
+ "model_module_version": "1.5.0",
754
+ "state": {
755
+ "_dom_classes": [],
756
+ "_model_module": "@jupyter-widgets/controls",
757
+ "_model_module_version": "1.5.0",
758
+ "_model_name": "HTMLModel",
759
+ "_view_count": null,
760
+ "_view_module": "@jupyter-widgets/controls",
761
+ "_view_module_version": "1.5.0",
762
+ "_view_name": "HTMLView",
763
+ "description": "",
764
+ "description_tooltip": null,
765
+ "layout": "IPY_MODEL_6b085d5276bf42c8b8e6a050de4730c9",
766
+ "placeholder": "​",
767
+ "style": "IPY_MODEL_47347341d5a14564a25e52179187b218",
768
+ "value": " 1/4 [10:02&lt;30:08, 602.73s/it]"
769
+ }
770
+ },
771
+ "d28248f12d834263a1605afed777077a": {
772
+ "model_module": "@jupyter-widgets/base",
773
+ "model_name": "LayoutModel",
774
+ "model_module_version": "1.2.0",
775
+ "state": {
776
+ "_model_module": "@jupyter-widgets/base",
777
+ "_model_module_version": "1.2.0",
778
+ "_model_name": "LayoutModel",
779
+ "_view_count": null,
780
+ "_view_module": "@jupyter-widgets/base",
781
+ "_view_module_version": "1.2.0",
782
+ "_view_name": "LayoutView",
783
+ "align_content": null,
784
+ "align_items": null,
785
+ "align_self": null,
786
+ "border": null,
787
+ "bottom": null,
788
+ "display": null,
789
+ "flex": null,
790
+ "flex_flow": null,
791
+ "grid_area": null,
792
+ "grid_auto_columns": null,
793
+ "grid_auto_flow": null,
794
+ "grid_auto_rows": null,
795
+ "grid_column": null,
796
+ "grid_gap": null,
797
+ "grid_row": null,
798
+ "grid_template_areas": null,
799
+ "grid_template_columns": null,
800
+ "grid_template_rows": null,
801
+ "height": null,
802
+ "justify_content": null,
803
+ "justify_items": null,
804
+ "left": null,
805
+ "margin": null,
806
+ "max_height": null,
807
+ "max_width": null,
808
+ "min_height": null,
809
+ "min_width": null,
810
+ "object_fit": null,
811
+ "object_position": null,
812
+ "order": null,
813
+ "overflow": null,
814
+ "overflow_x": null,
815
+ "overflow_y": null,
816
+ "padding": null,
817
+ "right": null,
818
+ "top": null,
819
+ "visibility": null,
820
+ "width": null
821
+ }
822
+ },
823
+ "1b255d9b51cb4dee82e1d14a506bf85e": {
824
+ "model_module": "@jupyter-widgets/base",
825
+ "model_name": "LayoutModel",
826
+ "model_module_version": "1.2.0",
827
+ "state": {
828
+ "_model_module": "@jupyter-widgets/base",
829
+ "_model_module_version": "1.2.0",
830
+ "_model_name": "LayoutModel",
831
+ "_view_count": null,
832
+ "_view_module": "@jupyter-widgets/base",
833
+ "_view_module_version": "1.2.0",
834
+ "_view_name": "LayoutView",
835
+ "align_content": null,
836
+ "align_items": null,
837
+ "align_self": null,
838
+ "border": null,
839
+ "bottom": null,
840
+ "display": null,
841
+ "flex": null,
842
+ "flex_flow": null,
843
+ "grid_area": null,
844
+ "grid_auto_columns": null,
845
+ "grid_auto_flow": null,
846
+ "grid_auto_rows": null,
847
+ "grid_column": null,
848
+ "grid_gap": null,
849
+ "grid_row": null,
850
+ "grid_template_areas": null,
851
+ "grid_template_columns": null,
852
+ "grid_template_rows": null,
853
+ "height": null,
854
+ "justify_content": null,
855
+ "justify_items": null,
856
+ "left": null,
857
+ "margin": null,
858
+ "max_height": null,
859
+ "max_width": null,
860
+ "min_height": null,
861
+ "min_width": null,
862
+ "object_fit": null,
863
+ "object_position": null,
864
+ "order": null,
865
+ "overflow": null,
866
+ "overflow_x": null,
867
+ "overflow_y": null,
868
+ "padding": null,
869
+ "right": null,
870
+ "top": null,
871
+ "visibility": null,
872
+ "width": null
873
+ }
874
+ },
875
+ "effd6703ac904650a7c02fbac19d1ce9": {
876
+ "model_module": "@jupyter-widgets/controls",
877
+ "model_name": "DescriptionStyleModel",
878
+ "model_module_version": "1.5.0",
879
+ "state": {
880
+ "_model_module": "@jupyter-widgets/controls",
881
+ "_model_module_version": "1.5.0",
882
+ "_model_name": "DescriptionStyleModel",
883
+ "_view_count": null,
884
+ "_view_module": "@jupyter-widgets/base",
885
+ "_view_module_version": "1.2.0",
886
+ "_view_name": "StyleView",
887
+ "description_width": ""
888
+ }
889
+ },
890
+ "f62a8b3dfedd4500b795e8a9e57ee4e1": {
891
+ "model_module": "@jupyter-widgets/base",
892
+ "model_name": "LayoutModel",
893
+ "model_module_version": "1.2.0",
894
+ "state": {
895
+ "_model_module": "@jupyter-widgets/base",
896
+ "_model_module_version": "1.2.0",
897
+ "_model_name": "LayoutModel",
898
+ "_view_count": null,
899
+ "_view_module": "@jupyter-widgets/base",
900
+ "_view_module_version": "1.2.0",
901
+ "_view_name": "LayoutView",
902
+ "align_content": null,
903
+ "align_items": null,
904
+ "align_self": null,
905
+ "border": null,
906
+ "bottom": null,
907
+ "display": null,
908
+ "flex": null,
909
+ "flex_flow": null,
910
+ "grid_area": null,
911
+ "grid_auto_columns": null,
912
+ "grid_auto_flow": null,
913
+ "grid_auto_rows": null,
914
+ "grid_column": null,
915
+ "grid_gap": null,
916
+ "grid_row": null,
917
+ "grid_template_areas": null,
918
+ "grid_template_columns": null,
919
+ "grid_template_rows": null,
920
+ "height": null,
921
+ "justify_content": null,
922
+ "justify_items": null,
923
+ "left": null,
924
+ "margin": null,
925
+ "max_height": null,
926
+ "max_width": null,
927
+ "min_height": null,
928
+ "min_width": null,
929
+ "object_fit": null,
930
+ "object_position": null,
931
+ "order": null,
932
+ "overflow": null,
933
+ "overflow_x": null,
934
+ "overflow_y": null,
935
+ "padding": null,
936
+ "right": null,
937
+ "top": null,
938
+ "visibility": null,
939
+ "width": null
940
+ }
941
+ },
942
+ "c2669c5874354798b33d7da9a5d8084d": {
943
+ "model_module": "@jupyter-widgets/controls",
944
+ "model_name": "ProgressStyleModel",
945
+ "model_module_version": "1.5.0",
946
+ "state": {
947
+ "_model_module": "@jupyter-widgets/controls",
948
+ "_model_module_version": "1.5.0",
949
+ "_model_name": "ProgressStyleModel",
950
+ "_view_count": null,
951
+ "_view_module": "@jupyter-widgets/base",
952
+ "_view_module_version": "1.2.0",
953
+ "_view_name": "StyleView",
954
+ "bar_color": null,
955
+ "description_width": ""
956
+ }
957
+ },
958
+ "6b085d5276bf42c8b8e6a050de4730c9": {
959
+ "model_module": "@jupyter-widgets/base",
960
+ "model_name": "LayoutModel",
961
+ "model_module_version": "1.2.0",
962
+ "state": {
963
+ "_model_module": "@jupyter-widgets/base",
964
+ "_model_module_version": "1.2.0",
965
+ "_model_name": "LayoutModel",
966
+ "_view_count": null,
967
+ "_view_module": "@jupyter-widgets/base",
968
+ "_view_module_version": "1.2.0",
969
+ "_view_name": "LayoutView",
970
+ "align_content": null,
971
+ "align_items": null,
972
+ "align_self": null,
973
+ "border": null,
974
+ "bottom": null,
975
+ "display": null,
976
+ "flex": null,
977
+ "flex_flow": null,
978
+ "grid_area": null,
979
+ "grid_auto_columns": null,
980
+ "grid_auto_flow": null,
981
+ "grid_auto_rows": null,
982
+ "grid_column": null,
983
+ "grid_gap": null,
984
+ "grid_row": null,
985
+ "grid_template_areas": null,
986
+ "grid_template_columns": null,
987
+ "grid_template_rows": null,
988
+ "height": null,
989
+ "justify_content": null,
990
+ "justify_items": null,
991
+ "left": null,
992
+ "margin": null,
993
+ "max_height": null,
994
+ "max_width": null,
995
+ "min_height": null,
996
+ "min_width": null,
997
+ "object_fit": null,
998
+ "object_position": null,
999
+ "order": null,
1000
+ "overflow": null,
1001
+ "overflow_x": null,
1002
+ "overflow_y": null,
1003
+ "padding": null,
1004
+ "right": null,
1005
+ "top": null,
1006
+ "visibility": null,
1007
+ "width": null
1008
+ }
1009
+ },
1010
+ "47347341d5a14564a25e52179187b218": {
1011
+ "model_module": "@jupyter-widgets/controls",
1012
+ "model_name": "DescriptionStyleModel",
1013
+ "model_module_version": "1.5.0",
1014
+ "state": {
1015
+ "_model_module": "@jupyter-widgets/controls",
1016
+ "_model_module_version": "1.5.0",
1017
+ "_model_name": "DescriptionStyleModel",
1018
+ "_view_count": null,
1019
+ "_view_module": "@jupyter-widgets/base",
1020
+ "_view_module_version": "1.2.0",
1021
+ "_view_name": "StyleView",
1022
+ "description_width": ""
1023
+ }
1024
+ },
1025
+ "39487ee2262647a79ed05bd89413ec25": {
1026
+ "model_module": "@jupyter-widgets/controls",
1027
+ "model_name": "HBoxModel",
1028
+ "model_module_version": "1.5.0",
1029
+ "state": {
1030
+ "_dom_classes": [],
1031
+ "_model_module": "@jupyter-widgets/controls",
1032
+ "_model_module_version": "1.5.0",
1033
+ "_model_name": "HBoxModel",
1034
+ "_view_count": null,
1035
+ "_view_module": "@jupyter-widgets/controls",
1036
+ "_view_module_version": "1.5.0",
1037
+ "_view_name": "HBoxView",
1038
+ "box_style": "",
1039
+ "children": [
1040
+ "IPY_MODEL_37fd57a2be584e37aade4f200aca564e",
1041
+ "IPY_MODEL_2daa2d8768f94963b4be13ee5108ec16",
1042
+ "IPY_MODEL_41d52c3d2db543ac8654f2d79ea72f51"
1043
+ ],
1044
+ "layout": "IPY_MODEL_cee7cfd5a46a4a86a048e84c9aa6df56"
1045
+ }
1046
+ },
1047
+ "37fd57a2be584e37aade4f200aca564e": {
1048
+ "model_module": "@jupyter-widgets/controls",
1049
+ "model_name": "HTMLModel",
1050
+ "model_module_version": "1.5.0",
1051
+ "state": {
1052
+ "_dom_classes": [],
1053
+ "_model_module": "@jupyter-widgets/controls",
1054
+ "_model_module_version": "1.5.0",
1055
+ "_model_name": "HTMLModel",
1056
+ "_view_count": null,
1057
+ "_view_module": "@jupyter-widgets/controls",
1058
+ "_view_module_version": "1.5.0",
1059
+ "_view_name": "HTMLView",
1060
+ "description": "",
1061
+ "description_tooltip": null,
1062
+ "layout": "IPY_MODEL_365846f3939d49188dd2698ccb4a0c6d",
1063
+ "placeholder": "​",
1064
+ "style": "IPY_MODEL_fa8cd1c1559248aeb8a920d6a1f7b8ca",
1065
+ "value": "0.277587890625: 100%"
1066
+ }
1067
+ },
1068
+ "2daa2d8768f94963b4be13ee5108ec16": {
1069
+ "model_module": "@jupyter-widgets/controls",
1070
+ "model_name": "FloatProgressModel",
1071
+ "model_module_version": "1.5.0",
1072
+ "state": {
1073
+ "_dom_classes": [],
1074
+ "_model_module": "@jupyter-widgets/controls",
1075
+ "_model_module_version": "1.5.0",
1076
+ "_model_name": "FloatProgressModel",
1077
+ "_view_count": null,
1078
+ "_view_module": "@jupyter-widgets/controls",
1079
+ "_view_module_version": "1.5.0",
1080
+ "_view_name": "ProgressView",
1081
+ "bar_style": "success",
1082
+ "description": "",
1083
+ "description_tooltip": null,
1084
+ "layout": "IPY_MODEL_8d6f469af323498aae3b8c2fd2e4f7de",
1085
+ "max": 64,
1086
+ "min": 0,
1087
+ "orientation": "horizontal",
1088
+ "style": "IPY_MODEL_a58aa5c526234c25bd330564a8631310",
1089
+ "value": 64
1090
+ }
1091
+ },
1092
+ "41d52c3d2db543ac8654f2d79ea72f51": {
1093
+ "model_module": "@jupyter-widgets/controls",
1094
+ "model_name": "HTMLModel",
1095
+ "model_module_version": "1.5.0",
1096
+ "state": {
1097
+ "_dom_classes": [],
1098
+ "_model_module": "@jupyter-widgets/controls",
1099
+ "_model_module_version": "1.5.0",
1100
+ "_model_name": "HTMLModel",
1101
+ "_view_count": null,
1102
+ "_view_module": "@jupyter-widgets/controls",
1103
+ "_view_module_version": "1.5.0",
1104
+ "_view_name": "HTMLView",
1105
+ "description": "",
1106
+ "description_tooltip": null,
1107
+ "layout": "IPY_MODEL_355e7a4bac0f41d1a0a7aba831c1916b",
1108
+ "placeholder": "​",
1109
+ "style": "IPY_MODEL_d8d127599a964af2b22957e7cadc3949",
1110
+ "value": " 64/64 [10:02&lt;00:00, 9.10s/it]"
1111
+ }
1112
+ },
1113
+ "cee7cfd5a46a4a86a048e84c9aa6df56": {
1114
+ "model_module": "@jupyter-widgets/base",
1115
+ "model_name": "LayoutModel",
1116
+ "model_module_version": "1.2.0",
1117
+ "state": {
1118
+ "_model_module": "@jupyter-widgets/base",
1119
+ "_model_module_version": "1.2.0",
1120
+ "_model_name": "LayoutModel",
1121
+ "_view_count": null,
1122
+ "_view_module": "@jupyter-widgets/base",
1123
+ "_view_module_version": "1.2.0",
1124
+ "_view_name": "LayoutView",
1125
+ "align_content": null,
1126
+ "align_items": null,
1127
+ "align_self": null,
1128
+ "border": null,
1129
+ "bottom": null,
1130
+ "display": null,
1131
+ "flex": null,
1132
+ "flex_flow": null,
1133
+ "grid_area": null,
1134
+ "grid_auto_columns": null,
1135
+ "grid_auto_flow": null,
1136
+ "grid_auto_rows": null,
1137
+ "grid_column": null,
1138
+ "grid_gap": null,
1139
+ "grid_row": null,
1140
+ "grid_template_areas": null,
1141
+ "grid_template_columns": null,
1142
+ "grid_template_rows": null,
1143
+ "height": null,
1144
+ "justify_content": null,
1145
+ "justify_items": null,
1146
+ "left": null,
1147
+ "margin": null,
1148
+ "max_height": null,
1149
+ "max_width": null,
1150
+ "min_height": null,
1151
+ "min_width": null,
1152
+ "object_fit": null,
1153
+ "object_position": null,
1154
+ "order": null,
1155
+ "overflow": null,
1156
+ "overflow_x": null,
1157
+ "overflow_y": null,
1158
+ "padding": null,
1159
+ "right": null,
1160
+ "top": null,
1161
+ "visibility": null,
1162
+ "width": null
1163
+ }
1164
+ },
1165
+ "365846f3939d49188dd2698ccb4a0c6d": {
1166
+ "model_module": "@jupyter-widgets/base",
1167
+ "model_name": "LayoutModel",
1168
+ "model_module_version": "1.2.0",
1169
+ "state": {
1170
+ "_model_module": "@jupyter-widgets/base",
1171
+ "_model_module_version": "1.2.0",
1172
+ "_model_name": "LayoutModel",
1173
+ "_view_count": null,
1174
+ "_view_module": "@jupyter-widgets/base",
1175
+ "_view_module_version": "1.2.0",
1176
+ "_view_name": "LayoutView",
1177
+ "align_content": null,
1178
+ "align_items": null,
1179
+ "align_self": null,
1180
+ "border": null,
1181
+ "bottom": null,
1182
+ "display": null,
1183
+ "flex": null,
1184
+ "flex_flow": null,
1185
+ "grid_area": null,
1186
+ "grid_auto_columns": null,
1187
+ "grid_auto_flow": null,
1188
+ "grid_auto_rows": null,
1189
+ "grid_column": null,
1190
+ "grid_gap": null,
1191
+ "grid_row": null,
1192
+ "grid_template_areas": null,
1193
+ "grid_template_columns": null,
1194
+ "grid_template_rows": null,
1195
+ "height": null,
1196
+ "justify_content": null,
1197
+ "justify_items": null,
1198
+ "left": null,
1199
+ "margin": null,
1200
+ "max_height": null,
1201
+ "max_width": null,
1202
+ "min_height": null,
1203
+ "min_width": null,
1204
+ "object_fit": null,
1205
+ "object_position": null,
1206
+ "order": null,
1207
+ "overflow": null,
1208
+ "overflow_x": null,
1209
+ "overflow_y": null,
1210
+ "padding": null,
1211
+ "right": null,
1212
+ "top": null,
1213
+ "visibility": null,
1214
+ "width": null
1215
+ }
1216
+ },
1217
+ "fa8cd1c1559248aeb8a920d6a1f7b8ca": {
1218
+ "model_module": "@jupyter-widgets/controls",
1219
+ "model_name": "DescriptionStyleModel",
1220
+ "model_module_version": "1.5.0",
1221
+ "state": {
1222
+ "_model_module": "@jupyter-widgets/controls",
1223
+ "_model_module_version": "1.5.0",
1224
+ "_model_name": "DescriptionStyleModel",
1225
+ "_view_count": null,
1226
+ "_view_module": "@jupyter-widgets/base",
1227
+ "_view_module_version": "1.2.0",
1228
+ "_view_name": "StyleView",
1229
+ "description_width": ""
1230
+ }
1231
+ },
1232
+ "8d6f469af323498aae3b8c2fd2e4f7de": {
1233
+ "model_module": "@jupyter-widgets/base",
1234
+ "model_name": "LayoutModel",
1235
+ "model_module_version": "1.2.0",
1236
+ "state": {
1237
+ "_model_module": "@jupyter-widgets/base",
1238
+ "_model_module_version": "1.2.0",
1239
+ "_model_name": "LayoutModel",
1240
+ "_view_count": null,
1241
+ "_view_module": "@jupyter-widgets/base",
1242
+ "_view_module_version": "1.2.0",
1243
+ "_view_name": "LayoutView",
1244
+ "align_content": null,
1245
+ "align_items": null,
1246
+ "align_self": null,
1247
+ "border": null,
1248
+ "bottom": null,
1249
+ "display": null,
1250
+ "flex": null,
1251
+ "flex_flow": null,
1252
+ "grid_area": null,
1253
+ "grid_auto_columns": null,
1254
+ "grid_auto_flow": null,
1255
+ "grid_auto_rows": null,
1256
+ "grid_column": null,
1257
+ "grid_gap": null,
1258
+ "grid_row": null,
1259
+ "grid_template_areas": null,
1260
+ "grid_template_columns": null,
1261
+ "grid_template_rows": null,
1262
+ "height": null,
1263
+ "justify_content": null,
1264
+ "justify_items": null,
1265
+ "left": null,
1266
+ "margin": null,
1267
+ "max_height": null,
1268
+ "max_width": null,
1269
+ "min_height": null,
1270
+ "min_width": null,
1271
+ "object_fit": null,
1272
+ "object_position": null,
1273
+ "order": null,
1274
+ "overflow": null,
1275
+ "overflow_x": null,
1276
+ "overflow_y": null,
1277
+ "padding": null,
1278
+ "right": null,
1279
+ "top": null,
1280
+ "visibility": null,
1281
+ "width": null
1282
+ }
1283
+ },
1284
+ "a58aa5c526234c25bd330564a8631310": {
1285
+ "model_module": "@jupyter-widgets/controls",
1286
+ "model_name": "ProgressStyleModel",
1287
+ "model_module_version": "1.5.0",
1288
+ "state": {
1289
+ "_model_module": "@jupyter-widgets/controls",
1290
+ "_model_module_version": "1.5.0",
1291
+ "_model_name": "ProgressStyleModel",
1292
+ "_view_count": null,
1293
+ "_view_module": "@jupyter-widgets/base",
1294
+ "_view_module_version": "1.2.0",
1295
+ "_view_name": "StyleView",
1296
+ "bar_color": null,
1297
+ "description_width": ""
1298
+ }
1299
+ },
1300
+ "355e7a4bac0f41d1a0a7aba831c1916b": {
1301
+ "model_module": "@jupyter-widgets/base",
1302
+ "model_name": "LayoutModel",
1303
+ "model_module_version": "1.2.0",
1304
+ "state": {
1305
+ "_model_module": "@jupyter-widgets/base",
1306
+ "_model_module_version": "1.2.0",
1307
+ "_model_name": "LayoutModel",
1308
+ "_view_count": null,
1309
+ "_view_module": "@jupyter-widgets/base",
1310
+ "_view_module_version": "1.2.0",
1311
+ "_view_name": "LayoutView",
1312
+ "align_content": null,
1313
+ "align_items": null,
1314
+ "align_self": null,
1315
+ "border": null,
1316
+ "bottom": null,
1317
+ "display": null,
1318
+ "flex": null,
1319
+ "flex_flow": null,
1320
+ "grid_area": null,
1321
+ "grid_auto_columns": null,
1322
+ "grid_auto_flow": null,
1323
+ "grid_auto_rows": null,
1324
+ "grid_column": null,
1325
+ "grid_gap": null,
1326
+ "grid_row": null,
1327
+ "grid_template_areas": null,
1328
+ "grid_template_columns": null,
1329
+ "grid_template_rows": null,
1330
+ "height": null,
1331
+ "justify_content": null,
1332
+ "justify_items": null,
1333
+ "left": null,
1334
+ "margin": null,
1335
+ "max_height": null,
1336
+ "max_width": null,
1337
+ "min_height": null,
1338
+ "min_width": null,
1339
+ "object_fit": null,
1340
+ "object_position": null,
1341
+ "order": null,
1342
+ "overflow": null,
1343
+ "overflow_x": null,
1344
+ "overflow_y": null,
1345
+ "padding": null,
1346
+ "right": null,
1347
+ "top": null,
1348
+ "visibility": null,
1349
+ "width": null
1350
+ }
1351
+ },
1352
+ "d8d127599a964af2b22957e7cadc3949": {
1353
+ "model_module": "@jupyter-widgets/controls",
1354
+ "model_name": "DescriptionStyleModel",
1355
+ "model_module_version": "1.5.0",
1356
+ "state": {
1357
+ "_model_module": "@jupyter-widgets/controls",
1358
+ "_model_module_version": "1.5.0",
1359
+ "_model_name": "DescriptionStyleModel",
1360
+ "_view_count": null,
1361
+ "_view_module": "@jupyter-widgets/base",
1362
+ "_view_module_version": "1.2.0",
1363
+ "_view_name": "StyleView",
1364
+ "description_width": ""
1365
+ }
1366
+ },
1367
+ "94c994a72e6e47a581ef47eafc4f8621": {
1368
+ "model_module": "@jupyter-widgets/controls",
1369
+ "model_name": "HBoxModel",
1370
+ "model_module_version": "1.5.0",
1371
+ "state": {
1372
+ "_dom_classes": [],
1373
+ "_model_module": "@jupyter-widgets/controls",
1374
+ "_model_module_version": "1.5.0",
1375
+ "_model_name": "HBoxModel",
1376
+ "_view_count": null,
1377
+ "_view_module": "@jupyter-widgets/controls",
1378
+ "_view_module_version": "1.5.0",
1379
+ "_view_name": "HBoxView",
1380
+ "box_style": "",
1381
+ "children": [
1382
+ "IPY_MODEL_e2409e281b874665bbe830fc5843e4fe",
1383
+ "IPY_MODEL_c980cbb0b5ba43378c84ea122829e70e",
1384
+ "IPY_MODEL_08ab7aae4ac341909798caf190c84ada"
1385
+ ],
1386
+ "layout": "IPY_MODEL_9decfef2a41f42f0a3b77dfaa3a02bac"
1387
+ }
1388
+ },
1389
+ "e2409e281b874665bbe830fc5843e4fe": {
1390
+ "model_module": "@jupyter-widgets/controls",
1391
+ "model_name": "HTMLModel",
1392
+ "model_module_version": "1.5.0",
1393
+ "state": {
1394
+ "_dom_classes": [],
1395
+ "_model_module": "@jupyter-widgets/controls",
1396
+ "_model_module_version": "1.5.0",
1397
+ "_model_name": "HTMLModel",
1398
+ "_view_count": null,
1399
+ "_view_module": "@jupyter-widgets/controls",
1400
+ "_view_module_version": "1.5.0",
1401
+ "_view_name": "HTMLView",
1402
+ "description": "",
1403
+ "description_tooltip": null,
1404
+ "layout": "IPY_MODEL_a0f24920a480438381da74562a7f7df1",
1405
+ "placeholder": "​",
1406
+ "style": "IPY_MODEL_bc4723c3d801406b891f808c84e9e83b",
1407
+ "value": "0.2724609375: 84%"
1408
+ }
1409
+ },
1410
+ "c980cbb0b5ba43378c84ea122829e70e": {
1411
+ "model_module": "@jupyter-widgets/controls",
1412
+ "model_name": "FloatProgressModel",
1413
+ "model_module_version": "1.5.0",
1414
+ "state": {
1415
+ "_dom_classes": [],
1416
+ "_model_module": "@jupyter-widgets/controls",
1417
+ "_model_module_version": "1.5.0",
1418
+ "_model_name": "FloatProgressModel",
1419
+ "_view_count": null,
1420
+ "_view_module": "@jupyter-widgets/controls",
1421
+ "_view_module_version": "1.5.0",
1422
+ "_view_name": "ProgressView",
1423
+ "bar_style": "",
1424
+ "description": "",
1425
+ "description_tooltip": null,
1426
+ "layout": "IPY_MODEL_c464d7549104481a90f75f3e5b219189",
1427
+ "max": 64,
1428
+ "min": 0,
1429
+ "orientation": "horizontal",
1430
+ "style": "IPY_MODEL_d9792cd6d5034352a3a9f2122bb5d9c0",
1431
+ "value": 54
1432
+ }
1433
+ },
1434
+ "08ab7aae4ac341909798caf190c84ada": {
1435
+ "model_module": "@jupyter-widgets/controls",
1436
+ "model_name": "HTMLModel",
1437
+ "model_module_version": "1.5.0",
1438
+ "state": {
1439
+ "_dom_classes": [],
1440
+ "_model_module": "@jupyter-widgets/controls",
1441
+ "_model_module_version": "1.5.0",
1442
+ "_model_name": "HTMLModel",
1443
+ "_view_count": null,
1444
+ "_view_module": "@jupyter-widgets/controls",
1445
+ "_view_module_version": "1.5.0",
1446
+ "_view_name": "HTMLView",
1447
+ "description": "",
1448
+ "description_tooltip": null,
1449
+ "layout": "IPY_MODEL_8a9c974907c74fe29b6a323df7df0d4d",
1450
+ "placeholder": "​",
1451
+ "style": "IPY_MODEL_40ae1be859d74847b4f0944c4027e1cf",
1452
+ "value": " 54/64 [07:50&lt;01:35, 9.52s/it]"
1453
+ }
1454
+ },
1455
+ "9decfef2a41f42f0a3b77dfaa3a02bac": {
1456
+ "model_module": "@jupyter-widgets/base",
1457
+ "model_name": "LayoutModel",
1458
+ "model_module_version": "1.2.0",
1459
+ "state": {
1460
+ "_model_module": "@jupyter-widgets/base",
1461
+ "_model_module_version": "1.2.0",
1462
+ "_model_name": "LayoutModel",
1463
+ "_view_count": null,
1464
+ "_view_module": "@jupyter-widgets/base",
1465
+ "_view_module_version": "1.2.0",
1466
+ "_view_name": "LayoutView",
1467
+ "align_content": null,
1468
+ "align_items": null,
1469
+ "align_self": null,
1470
+ "border": null,
1471
+ "bottom": null,
1472
+ "display": null,
1473
+ "flex": null,
1474
+ "flex_flow": null,
1475
+ "grid_area": null,
1476
+ "grid_auto_columns": null,
1477
+ "grid_auto_flow": null,
1478
+ "grid_auto_rows": null,
1479
+ "grid_column": null,
1480
+ "grid_gap": null,
1481
+ "grid_row": null,
1482
+ "grid_template_areas": null,
1483
+ "grid_template_columns": null,
1484
+ "grid_template_rows": null,
1485
+ "height": null,
1486
+ "justify_content": null,
1487
+ "justify_items": null,
1488
+ "left": null,
1489
+ "margin": null,
1490
+ "max_height": null,
1491
+ "max_width": null,
1492
+ "min_height": null,
1493
+ "min_width": null,
1494
+ "object_fit": null,
1495
+ "object_position": null,
1496
+ "order": null,
1497
+ "overflow": null,
1498
+ "overflow_x": null,
1499
+ "overflow_y": null,
1500
+ "padding": null,
1501
+ "right": null,
1502
+ "top": null,
1503
+ "visibility": null,
1504
+ "width": null
1505
+ }
1506
+ },
1507
+ "a0f24920a480438381da74562a7f7df1": {
1508
+ "model_module": "@jupyter-widgets/base",
1509
+ "model_name": "LayoutModel",
1510
+ "model_module_version": "1.2.0",
1511
+ "state": {
1512
+ "_model_module": "@jupyter-widgets/base",
1513
+ "_model_module_version": "1.2.0",
1514
+ "_model_name": "LayoutModel",
1515
+ "_view_count": null,
1516
+ "_view_module": "@jupyter-widgets/base",
1517
+ "_view_module_version": "1.2.0",
1518
+ "_view_name": "LayoutView",
1519
+ "align_content": null,
1520
+ "align_items": null,
1521
+ "align_self": null,
1522
+ "border": null,
1523
+ "bottom": null,
1524
+ "display": null,
1525
+ "flex": null,
1526
+ "flex_flow": null,
1527
+ "grid_area": null,
1528
+ "grid_auto_columns": null,
1529
+ "grid_auto_flow": null,
1530
+ "grid_auto_rows": null,
1531
+ "grid_column": null,
1532
+ "grid_gap": null,
1533
+ "grid_row": null,
1534
+ "grid_template_areas": null,
1535
+ "grid_template_columns": null,
1536
+ "grid_template_rows": null,
1537
+ "height": null,
1538
+ "justify_content": null,
1539
+ "justify_items": null,
1540
+ "left": null,
1541
+ "margin": null,
1542
+ "max_height": null,
1543
+ "max_width": null,
1544
+ "min_height": null,
1545
+ "min_width": null,
1546
+ "object_fit": null,
1547
+ "object_position": null,
1548
+ "order": null,
1549
+ "overflow": null,
1550
+ "overflow_x": null,
1551
+ "overflow_y": null,
1552
+ "padding": null,
1553
+ "right": null,
1554
+ "top": null,
1555
+ "visibility": null,
1556
+ "width": null
1557
+ }
1558
+ },
1559
+ "bc4723c3d801406b891f808c84e9e83b": {
1560
+ "model_module": "@jupyter-widgets/controls",
1561
+ "model_name": "DescriptionStyleModel",
1562
+ "model_module_version": "1.5.0",
1563
+ "state": {
1564
+ "_model_module": "@jupyter-widgets/controls",
1565
+ "_model_module_version": "1.5.0",
1566
+ "_model_name": "DescriptionStyleModel",
1567
+ "_view_count": null,
1568
+ "_view_module": "@jupyter-widgets/base",
1569
+ "_view_module_version": "1.2.0",
1570
+ "_view_name": "StyleView",
1571
+ "description_width": ""
1572
+ }
1573
+ },
1574
+ "c464d7549104481a90f75f3e5b219189": {
1575
+ "model_module": "@jupyter-widgets/base",
1576
+ "model_name": "LayoutModel",
1577
+ "model_module_version": "1.2.0",
1578
+ "state": {
1579
+ "_model_module": "@jupyter-widgets/base",
1580
+ "_model_module_version": "1.2.0",
1581
+ "_model_name": "LayoutModel",
1582
+ "_view_count": null,
1583
+ "_view_module": "@jupyter-widgets/base",
1584
+ "_view_module_version": "1.2.0",
1585
+ "_view_name": "LayoutView",
1586
+ "align_content": null,
1587
+ "align_items": null,
1588
+ "align_self": null,
1589
+ "border": null,
1590
+ "bottom": null,
1591
+ "display": null,
1592
+ "flex": null,
1593
+ "flex_flow": null,
1594
+ "grid_area": null,
1595
+ "grid_auto_columns": null,
1596
+ "grid_auto_flow": null,
1597
+ "grid_auto_rows": null,
1598
+ "grid_column": null,
1599
+ "grid_gap": null,
1600
+ "grid_row": null,
1601
+ "grid_template_areas": null,
1602
+ "grid_template_columns": null,
1603
+ "grid_template_rows": null,
1604
+ "height": null,
1605
+ "justify_content": null,
1606
+ "justify_items": null,
1607
+ "left": null,
1608
+ "margin": null,
1609
+ "max_height": null,
1610
+ "max_width": null,
1611
+ "min_height": null,
1612
+ "min_width": null,
1613
+ "object_fit": null,
1614
+ "object_position": null,
1615
+ "order": null,
1616
+ "overflow": null,
1617
+ "overflow_x": null,
1618
+ "overflow_y": null,
1619
+ "padding": null,
1620
+ "right": null,
1621
+ "top": null,
1622
+ "visibility": null,
1623
+ "width": null
1624
+ }
1625
+ },
1626
+ "d9792cd6d5034352a3a9f2122bb5d9c0": {
1627
+ "model_module": "@jupyter-widgets/controls",
1628
+ "model_name": "ProgressStyleModel",
1629
+ "model_module_version": "1.5.0",
1630
+ "state": {
1631
+ "_model_module": "@jupyter-widgets/controls",
1632
+ "_model_module_version": "1.5.0",
1633
+ "_model_name": "ProgressStyleModel",
1634
+ "_view_count": null,
1635
+ "_view_module": "@jupyter-widgets/base",
1636
+ "_view_module_version": "1.2.0",
1637
+ "_view_name": "StyleView",
1638
+ "bar_color": null,
1639
+ "description_width": ""
1640
+ }
1641
+ },
1642
+ "8a9c974907c74fe29b6a323df7df0d4d": {
1643
+ "model_module": "@jupyter-widgets/base",
1644
+ "model_name": "LayoutModel",
1645
+ "model_module_version": "1.2.0",
1646
+ "state": {
1647
+ "_model_module": "@jupyter-widgets/base",
1648
+ "_model_module_version": "1.2.0",
1649
+ "_model_name": "LayoutModel",
1650
+ "_view_count": null,
1651
+ "_view_module": "@jupyter-widgets/base",
1652
+ "_view_module_version": "1.2.0",
1653
+ "_view_name": "LayoutView",
1654
+ "align_content": null,
1655
+ "align_items": null,
1656
+ "align_self": null,
1657
+ "border": null,
1658
+ "bottom": null,
1659
+ "display": null,
1660
+ "flex": null,
1661
+ "flex_flow": null,
1662
+ "grid_area": null,
1663
+ "grid_auto_columns": null,
1664
+ "grid_auto_flow": null,
1665
+ "grid_auto_rows": null,
1666
+ "grid_column": null,
1667
+ "grid_gap": null,
1668
+ "grid_row": null,
1669
+ "grid_template_areas": null,
1670
+ "grid_template_columns": null,
1671
+ "grid_template_rows": null,
1672
+ "height": null,
1673
+ "justify_content": null,
1674
+ "justify_items": null,
1675
+ "left": null,
1676
+ "margin": null,
1677
+ "max_height": null,
1678
+ "max_width": null,
1679
+ "min_height": null,
1680
+ "min_width": null,
1681
+ "object_fit": null,
1682
+ "object_position": null,
1683
+ "order": null,
1684
+ "overflow": null,
1685
+ "overflow_x": null,
1686
+ "overflow_y": null,
1687
+ "padding": null,
1688
+ "right": null,
1689
+ "top": null,
1690
+ "visibility": null,
1691
+ "width": null
1692
+ }
1693
+ },
1694
+ "40ae1be859d74847b4f0944c4027e1cf": {
1695
+ "model_module": "@jupyter-widgets/controls",
1696
+ "model_name": "DescriptionStyleModel",
1697
+ "model_module_version": "1.5.0",
1698
+ "state": {
1699
+ "_model_module": "@jupyter-widgets/controls",
1700
+ "_model_module_version": "1.5.0",
1701
+ "_model_name": "DescriptionStyleModel",
1702
+ "_view_count": null,
1703
+ "_view_module": "@jupyter-widgets/base",
1704
+ "_view_module_version": "1.2.0",
1705
+ "_view_name": "StyleView",
1706
+ "description_width": ""
1707
+ }
1708
+ }
1709
+ }
1710
+ }
1711
+ },
1712
+ "nbformat": 4,
1713
+ "nbformat_minor": 5
1714
+ }