File size: 13,239 Bytes
2cd207c
 
 
 
 
 
 
6963450
2cd207c
 
 
6febf41
6963450
 
2cd207c
 
 
 
 
 
 
367d6d8
2cd207c
 
 
 
 
 
 
 
 
6febf41
 
 
 
 
 
367d6d8
 
 
 
 
 
2cd207c
 
 
367d6d8
 
 
 
 
 
 
 
 
 
 
 
740a1b1
 
367d6d8
 
 
 
 
6bf5ba7
367d6d8
 
 
 
 
 
 
 
 
 
 
2cd207c
 
 
 
99a4efe
2cd207c
 
99a4efe
2cd207c
 
 
 
 
99a4efe
 
 
6febf41
 
 
2cd207c
6febf41
 
 
692bdb3
2cd207c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
99719fb
 
 
 
 
 
 
 
6febf41
5acd4d2
6963450
 
5acd4d2
 
6963450
 
 
6febf41
6963450
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5acd4d2
 
6963450
5acd4d2
 
 
 
 
 
367d6d8
5acd4d2
367d6d8
 
6963450
367d6d8
6963450
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
367d6d8
10b9e1a
367d6d8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6bf5ba7
 
 
 
367d6d8
 
 
 
 
 
 
2cd207c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
367d6d8
 
6bf5ba7
367d6d8
740a1b1
 
dbb7d2e
2cd207c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
import streamlit as st
import numpy as np
import random
import pandas as pd
import glob
import csv
from PIL import Image
import datasets
from datasets import load_dataset, Dataset, load_from_disk
from huggingface_hub import login
import os
import requests

SCORE_NAME_MAPPING = {'clip': 'clip_score', 'rank': 'avg_rank', 'pop': 'model_download_count'}


class GalleryApp:
    def __init__(self, promptBook):
        self.promptBook = promptBook
        st.set_page_config(layout="wide")

    def gallery_masonry(self, items, col_num, info):
        cols = st.columns(col_num)
        # # sort items by brisque score
        # items = items.sort_values(by=['brisque'], ascending=True).reset_index(drop=True)
        for idx in range(len(items)):
            with cols[idx % col_num]:
                image = st.session_state.images[items.iloc[idx]['row_idx'].item()]['image']
                st.image(image,
                         use_column_width=True,
                )
                # with st.expander('Similarity Info'):
                #     tab1, tab2 = st.tabs(['Most Similar', 'Least Similar'])
                #     with tab1:
                #         st.image(image, use_column_width=True)
                #     with tab2:
                #         st.image(image, use_column_width=True)

                # show checkbox
                self.promptBook.loc[items.iloc[idx]['row_idx'].item(), 'checked'] = st.checkbox(
                    'Select', value=self.promptBook.loc[items.iloc[idx]['row_idx'].item(), 'checked'],
                    key=f'select_{idx}')

                for key in info:
                    st.write(f"**{key}**: {items.iloc[idx][key]}")

    def gallery_standard(self, items, col_num, info):
        rows = len(items) // col_num + 1
        containers = [st.container() for _ in range(rows*2)]
        for idx in range(0, len(items), col_num):
            # assign one container for each row
            row_idx = (idx // col_num) * 2
            with containers[row_idx]:
                cols = st.columns(col_num)
                for j in range(col_num):
                    if idx + j < len(items):
                        with cols[j]:
                            # show image
                            image = st.session_state.images[items.iloc[idx+j]['row_idx'].item()]['image']
                            # image = list(st.session_state.images.skip(items.iloc[idx+j]['row_idx'].item()).take(1))[0]['image']
                            st.image(image,
                                     use_column_width=True,
                            )

                            # show checkbox
                            self.promptBook.loc[items.iloc[idx+j]['row_idx'].item(), 'checked'] = st.checkbox('Select', value=self.promptBook.loc[items.iloc[idx+j]['row_idx'].item(), 'checked'], key=f'select_{idx+j}')

                            # show selected info
                            for key in info:
                                st.write(f"**{key}**: {items.iloc[idx+j][key]}")

                            # st.write(row_idx/2, idx+j, rows)
                            # extra_info = st.checkbox('Extra Info', key=f'extra_info_{idx+j}')
                            # if extra_info:
                            #     with containers[row_idx+1]:
                            #         st.image(image, use_column_width=True)

    def app(self):
        st.title('Model Coffer Gallery')
        st.write('This is a gallery of images generated by the models in the Model Coffer')

        with st.sidebar:
            prompt_tags = self.promptBook['tag'].unique()
            # sort tags by alphabetical order
            prompt_tags = np.sort(prompt_tags)[::-1]

            tag = st.selectbox('Select a tag', prompt_tags)

            items = self.promptBook[self.promptBook['tag'] == tag].reset_index(drop=True)

            original_prompts = np.sort(items['prompt'].unique())[::-1]

            # remove the first four items in the prompt, which are mostly the same
            if tag != 'abstract':
                prompts = [', '.join(x.split(', ')[4:]) for x in original_prompts]
                prompt = st.selectbox('Select prompt', prompts)

                idx = prompts.index(prompt)
                prompt_full = ', '.join(original_prompts[idx].split(', ')[:4]) + ', ' + prompt
            else:
                prompt_full = st.selectbox('Select prompt', original_prompts)

            prompt_id = items[items['prompt'] == prompt_full]['prompt_id'].unique()[0]
            items = items[items['prompt_id'] == prompt_id].reset_index(drop=True)

            st.write('**Prompt ID**')
            st.caption(f"{prompt_id}")
            st.write('**Prompt**')
            st.caption(f"{items['prompt'][0]}")
            st.write('**Negative Prompt**')
            st.caption(f"{items['negativePrompt'][0]}")
            st.write('**Sampler**')
            st.caption(f"{items['sampler'][0]}")
            st.write('**cfgScale**')
            st.caption(f"{items['cfgScale'][0]}")
            st.write('**Size**')
            st.caption(f"width: {items['size'][0].split('x')[0]}, height: {items['size'][0].split('x')[1]}")
            st.write('**Seed**')
            st.caption(f"{items['seed'][0]}")

            # # for tag as civitai, add civitai reference
            # if tag == 'civitai':
            #     st.write('**Reference**')
            #
            #     res = requests.get(f'https://civitai.com/images', params={'post_id': prompt_id})
            #     st.write(res)
            #     image_url = res.json()['items'][0]['url']
            #     st.image(image_url, use_column_width=True)

        # with images:
        # selecters = st.columns([2, 1, 2, 0.5])
        selecters = st.columns([4, 1, 1])

        with selecters[0]:
            # # sort_by = st.selectbox('Sort by', items.columns[11: -1])
            # sort_by = st.selectbox('Sort by', ['model_download_count', 'clip_score', 'avg_rank', 'model_name', 'model_id',
            #                        'modelVersion_name', 'modelVersion_id'])
            print(items.columns)
            types = st.columns([1, 3])
            with types[0]:
                sort_type = st.selectbox('Sort by', ['IDs and Names', 'Scores'])
            with types[1]:
                if sort_type == 'IDs and Names':
                    sort_by = st.selectbox('Sort by', ['model_name', 'model_id', 'modelVersion_name', 'modelVersion_id'], label_visibility='hidden')
                elif sort_type == 'Scores':
                    sort_by = st.multiselect('Sort by', ['clip_score', 'avg_rank', 'popularity'], label_visibility='hidden', default=['clip_score', 'avg_rank', 'popularity'])
                    # process sort_by to map to the column name

                    if len(sort_by) == 3:
                        sort_by = 'clip+rank+pop'
                    elif len(sort_by) == 2:
                        if 'clip_score' in sort_by and 'avg_rank' in sort_by:
                            sort_by = 'clip+rank'
                        elif 'clip_score' in sort_by and 'popularity' in sort_by:
                            sort_by = 'clip+pop'
                        elif 'avg_rank' in sort_by and 'popularity' in sort_by:
                            sort_by = 'rank+pop'
                    elif len(sort_by) == 1:
                        if 'popularity' in sort_by:
                            sort_by = 'model_download_count'
                        else:
                            sort_by = sort_by[0]
                    print(sort_by)

        with selecters[1]:
            order = st.selectbox('Order', ['Ascending', 'Descending'], index=1 if sort_type == 'Scores' else 0)
            if order == 'Ascending':
                order = True
            else:
                order = False

        items = items.sort_values(by=[sort_by], ascending=order).reset_index(drop=True)

        with selecters[2]:
            filter = st.selectbox('Filter', ['All', 'Checked', 'Unchecked'])
            if filter == 'Checked':
                items = items[items['checked'] is True].reset_index(drop=True)
            elif filter == 'Unchecked':
                items = items[items['checked'] is False].reset_index(drop=True)

        info = st.multiselect('Show Info',
                              ['model_download_count', 'clip_score', 'avg_rank', 'model_name', 'model_id',
                               'modelVersion_name', 'modelVersion_id', 'clip+rank', 'clip+pop', 'rank+pop', 'clip+rank+pop'],
                              default=sort_by)

        print('info', info)
        # add one annotation
        mentioned_scores = []
        for i in info:
            if '+' in i:
                mentioned = i.split('+')
                for m in mentioned:
                    if SCORE_NAME_MAPPING[m] not in mentioned_scores:
                        mentioned_scores.append(SCORE_NAME_MAPPING[m])
        if len(mentioned_scores) > 0:
            st.write(f"**Note: ** The scores {mentioned_scores} are normalized to [0, 1] for each score type, and then added together. The higher the score, the better the model.")


        col_num = st.slider('Number of columns', min_value=1, max_value=9, value=4, step=1, key='col_num')

        with st.form(key=f'{prompt_id}', clear_on_submit=False):
            buttons = st.columns([1, 1, 1])
            with buttons[0]:
                submit = st.form_submit_button('Save selections', on_click=self.save_checked, use_container_width=True, type='primary')
            with buttons[1]:
                submit = st.form_submit_button('Reset current prompt', on_click=self.reset_current_prompt, kwargs={'prompt_id': prompt_id} , use_container_width=True)
            with buttons[2]:
                submit = st.form_submit_button('Reset all selections', on_click=self.reset_all, use_container_width=True)
            self.gallery_standard(items, col_num, info)

    def reset_current_prompt(self, prompt_id):
        # reset current prompt
        self.promptBook.loc[self.promptBook['prompt_id'] == prompt_id, 'checked'] = False
        self.save_checked()

    def reset_all(self):
        # reset all
        self.promptBook.loc[:, 'checked'] = False
        self.save_checked()

    def save_checked(self):
        # save checked images to huggingface dataset
        dataset = load_dataset('NYUSHPRP/ModelCofferMetadata', split='train')
        # get checked images
        checked_info = self.promptBook['checked']
        # print('checked_info: ', checked_info)
        # for d in checked_info:
        #     if d is True:
        #         print('checked')

        if 'checked' in dataset.column_names:
            dataset = dataset.remove_columns('checked')
        dataset = dataset.add_column('checked', checked_info)

        # print('metadata dataset: ', dataset)
        dataset.push_to_hub('NYUSHPRP/ModelCofferMetadata', split='train')


if __name__ == '__main__':
    login(token=os.environ.get("HF_TOKEN"))

    if 'roster' not in st.session_state:
        print('loading roster')
        # st.session_state.roster = pd.DataFrame(load_dataset('NYUSHPRP/ModelCofferRoster', split='train'))
        st.session_state.roster = pd.DataFrame(load_from_disk(os.path.join(os.getcwd(), 'data', 'roster')))
        st.session_state.roster = st.session_state.roster[['model_id', 'model_name', 'modelVersion_id', 'modelVersion_name',
                                          'model_download_count']].drop_duplicates().reset_index(drop=True)
    # add model download count from roster to promptbook dataframe
    if 'promptBook' not in st.session_state:
        print('loading promptBook')

        st.session_state.promptBook = pd.DataFrame(load_dataset('NYUSHPRP/ModelCofferMetadata', split='train'))
        # add 'checked' column to promptBook if not exist
        if 'checked' not in st.session_state.promptBook.columns:
            st.session_state.promptBook.loc[:, 'checked'] = False

        st.session_state.images = load_from_disk(os.path.join(os.getcwd(), 'data', 'promptbook'))
        # st.session_state.images = load_dataset('NYUSHPRP/ModelCofferPromptBook', split='train', streaming=True)
        print(st.session_state.images)
        print('images loaded')
        # st.session_state.promptBook = pd.DataFrame(load_dataset('NYUSHPRP/ModelCofferPromptBook', split='train'))
        st.session_state.promptBook = st.session_state.promptBook.merge(st.session_state.roster[['model_id', 'model_name', 'modelVersion_id', 'modelVersion_name', 'model_download_count']], on=['model_id', 'modelVersion_id'], how='left')

        # add column to record current row index
        st.session_state.promptBook['row_idx'] = st.session_state.promptBook.index
        print('promptBook loaded')
    # print(st.session_state.promptBook)

    check_roster_error = False
    if check_roster_error:
        # print all rows with the same model_id and modelVersion_id but different model_download_count in roster
        print(st.session_state.roster[st.session_state.roster.duplicated(subset=['model_id', 'modelVersion_id'], keep=False)].sort_values(by=['model_id', 'modelVersion_id']))

    app = GalleryApp(promptBook=st.session_state.promptBook)
    app.app()