upload files

.gitignore

@@ -0,0 +1,6 @@
+.DS_Store?
+ehthumbs.db
+Icon?
+Thumbs.db
+*.DS_Store
+secret.sh

app.py

@@ -0,0 +1,136 @@
+import streamlit as st
+import numpy as np
+import random
+import pandas as pd
+import glob
+import csv
+from PIL import Image
+from datasets import load_dataset, Dataset, load_from_disk
+from huggingface_hub import login
+import os
+
+
+class GalleryApp:
+    def __init__(self, promptBook):
+        self.promptBook = promptBook
+        st.set_page_config(layout="wide")
+
+
+    def gallery(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,
+                )
+                for key in info:
+                    st.write(f"**{key}**: {items.iloc[idx][key]}")
+
+    def app(self):
+        st.title('Model Coffer Gallery')
+        st.write('This is a gallery of images generated by the models in the Model Coffer')
+
+        metadata, images = st.columns([1, 3])
+        # with images:
+            # prompt_tags = self.promptBook['tag'].unique()
+            # # sort tags by alphabetical order
+            # prompt_tags = np.sort(prompt_tags)
+            #
+            # selecters = st.columns(3)
+            # with selecters[0]:
+            #     tag = st.selectbox('Select a tag', prompt_tags)
+
+        with metadata:
+            prompt_tags = self.promptBook['tag'].unique()
+            # sort tags by alphabetical order
+            prompt_tags = np.sort(prompt_tags)
+
+            tag = st.selectbox('Select a tag', prompt_tags)
+
+            items = self.promptBook[self.promptBook['tag'] == tag].reset_index(drop=True)
+
+            prompts = [', '.join(x.split(', ')[4:]) for x in items['prompt'].unique()]
+            prompt = st.selectbox('Select prompt', prompts)
+
+            idx = prompts.index(prompt)
+            prompt_full = ', '.join(items['prompt'].unique()[idx].split(', ')[:4]) + ', ' + prompt
+
+            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]}")
+
+        with images:
+            selecters = st.columns([1, 1, 2])
+            # with selecters[0]:
+            with selecters[0]:
+                sort_by = st.selectbox('Sort by', items.columns[11: -1])
+
+            with selecters[1]:
+                order = st.selectbox('Order', ['Ascending', 'Descending'], index=1 if sort_by == 'clip_score' or sort_by == 'model_download_count' 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]:
+                info = st.multiselect('Show Info',
+                                      ['brisque_score', 'clip_score', 'model_download_count', 'model_name', 'model_id',
+                                       'modelVersion_name', 'modelVersion_id'],
+                                      default=sort_by)
+            # if sort_by not in info:
+            #     info.append(sort_by)
+
+            col_num = st.slider('Number of columns', min_value=1, max_value=9, value=4, step=1, key='col_num')
+            self.gallery(items, col_num, info)
+        # st.write(items)
+
+
+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'))
+        st.session_state.images = load_from_disk(os.path.join(os.getcwd(), 'data', 'promptbook'))
+        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()

data/download_script.py

@@ -0,0 +1,26 @@
+from datasets import load_dataset, Dataset, load_from_disk
+
+
+def main():
+    promptbook = load_dataset('NYUSHPRP/ModelCofferPromptBook', split='train')
+    promptbook.save_to_disk('./promptbook')
+
+    roster = load_dataset('NYUSHPRP/ModelCofferRoster', split='train')
+    roster.save_to_disk('./roster')
+
+
+def load():
+    roster = load_from_disk('./roster')
+    print(roster)
+
+
+def test():
+    promptbook = load_from_disk('./promptbook')
+    print(promptbook[0]['image'])
+
+
+
+if __name__ == '__main__':
+    # main()
+    # load()
+    test()

data/promptbook/data-00000-of-00010.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7abd243755b826c29ab6fb46266f135533d93e809833e546f5904d2882d2cc03
+size 473104752

data/promptbook/data-00001-of-00010.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff212f5cca342b996acd01be6dcd58fd7cf9f38fb5911b0c1cb088295059640c
+size 465910968

data/promptbook/data-00002-of-00010.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:780ff259901f6b76eb24fa22d9a8d04c3ffba97337f8b0c6698042d7a1c65665
+size 467081872

data/promptbook/data-00003-of-00010.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:244f7c5fe9d22b3e0f1860d907769ecc5d5b47c7368ed1adcfe9286eee3acad2
+size 470412576

data/promptbook/data-00004-of-00010.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a8bb4117058db33d04aee01417edbfc31c3c4d5ab676513fdd8c1721524d6a
+size 471499320

data/promptbook/data-00005-of-00010.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a248986cee7eaa81f4f1655c695dd6529d55d010879c771b596ecb8c634c5c
+size 470668704

data/promptbook/data-00006-of-00010.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2625acda78f978666df44577de4114e858c9cc93013afcc044b51e368e8357d
+size 466806344

data/promptbook/data-00007-of-00010.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fee7c9b20d9deb0fea358772d72ca5b4554f901808b3685f90a0794b16a2e42c
+size 468241728

data/promptbook/data-00008-of-00010.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab49d30832f279ec60ffeece9fdf89e032c01a0c02378365a601a327699fb7ac
+size 469175856

data/promptbook/data-00009-of-00010.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f73b02a9dded0a39d705c3c6aec0ba10c0e969fd0f11280895bc702fbfb394da
+size 466882920

data/promptbook/dataset_info.json

@@ -0,0 +1,123 @@
+{
+  "citation": "",
+  "dataset_size": 4689764693,
+  "description": "",
+  "download_checksums": {
+    "https://huggingface.co/datasets/NYUSHPRP/ModelCofferPromptBook/resolve/2c8baf22882145215d258a580b75abf3a27107b1/data/train-00000-of-00010-d9a8d9d4a085684d.parquet": {
+      "num_bytes": 472890795,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/NYUSHPRP/ModelCofferPromptBook/resolve/2c8baf22882145215d258a580b75abf3a27107b1/data/train-00001-of-00010-ee4b84513a1ad2d4.parquet": {
+      "num_bytes": 465701779,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/NYUSHPRP/ModelCofferPromptBook/resolve/2c8baf22882145215d258a580b75abf3a27107b1/data/train-00002-of-00010-7f26e0d02d54bd02.parquet": {
+      "num_bytes": 466873748,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/NYUSHPRP/ModelCofferPromptBook/resolve/2c8baf22882145215d258a580b75abf3a27107b1/data/train-00003-of-00010-d4ca45236306d54b.parquet": {
+      "num_bytes": 470202126,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/NYUSHPRP/ModelCofferPromptBook/resolve/2c8baf22882145215d258a580b75abf3a27107b1/data/train-00004-of-00010-d1bad2a249d12a53.parquet": {
+      "num_bytes": 471290759,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/NYUSHPRP/ModelCofferPromptBook/resolve/2c8baf22882145215d258a580b75abf3a27107b1/data/train-00005-of-00010-eb750f68b3736e3e.parquet": {
+      "num_bytes": 470459382,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/NYUSHPRP/ModelCofferPromptBook/resolve/2c8baf22882145215d258a580b75abf3a27107b1/data/train-00006-of-00010-717c8b796b5738e7.parquet": {
+      "num_bytes": 466595911,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/NYUSHPRP/ModelCofferPromptBook/resolve/2c8baf22882145215d258a580b75abf3a27107b1/data/train-00007-of-00010-61d704caa01de276.parquet": {
+      "num_bytes": 468032296,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/NYUSHPRP/ModelCofferPromptBook/resolve/2c8baf22882145215d258a580b75abf3a27107b1/data/train-00008-of-00010-38eb6fe5f60d6139.parquet": {
+      "num_bytes": 468967088,
+      "checksum": null
+    },
+    "https://huggingface.co/datasets/NYUSHPRP/ModelCofferPromptBook/resolve/2c8baf22882145215d258a580b75abf3a27107b1/data/train-00009-of-00010-47ae97f4f60b336a.parquet": {
+      "num_bytes": 466675982,
+      "checksum": null
+    }
+  },
+  "download_size": 4687689866,
+  "features": {
+    "image": {
+      "_type": "Image"
+    },
+    "image_id": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "tag": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "model_id": {
+      "dtype": "int64",
+      "_type": "Value"
+    },
+    "modelVersion_id": {
+      "dtype": "int64",
+      "_type": "Value"
+    },
+    "prompt_id": {
+      "dtype": "int64",
+      "_type": "Value"
+    },
+    "size": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "seed": {
+      "dtype": "int64",
+      "_type": "Value"
+    },
+    "prompt": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "negativePrompt": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "cfgScale": {
+      "dtype": "int64",
+      "_type": "Value"
+    },
+    "sampler": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "brisque_score": {
+      "dtype": "float64",
+      "_type": "Value"
+    },
+    "clip_score": {
+      "dtype": "float64",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 9377454559,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 4689764693,
+      "num_examples": 7797,
+      "shard_lengths": [
+        1560,
+        1560,
+        1560,
+        1559,
+        1558
+      ],
+      "dataset_name": "parquet"
+    }
+  }
+}

data/promptbook/state.json

@@ -0,0 +1,40 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00010.arrow"
+    },
+    {
+      "filename": "data-00001-of-00010.arrow"
+    },
+    {
+      "filename": "data-00002-of-00010.arrow"
+    },
+    {
+      "filename": "data-00003-of-00010.arrow"
+    },
+    {
+      "filename": "data-00004-of-00010.arrow"
+    },
+    {
+      "filename": "data-00005-of-00010.arrow"
+    },
+    {
+      "filename": "data-00006-of-00010.arrow"
+    },
+    {
+      "filename": "data-00007-of-00010.arrow"
+    },
+    {
+      "filename": "data-00008-of-00010.arrow"
+    },
+    {
+      "filename": "data-00009-of-00010.arrow"
+    }
+  ],
+  "_fingerprint": "f0f128229ec661c4",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": "train"
+}

data/roster/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbaae46cb2963826d3b62bfc6e4877d9e3fee8dab09a0a0c4dde8469e0950b98
+size 94784

data/roster/dataset_info.json

@@ -0,0 +1,57 @@
+{
+  "citation": "",
+  "dataset_size": 93369,
+  "description": "",
+  "download_checksums": {
+    "https://huggingface.co/datasets/NYUSHPRP/ModelCofferRoster/resolve/5ebb9e1dde0260782309d6ebe6328a10d75ecadc/data/train-00000-of-00001-11e8fb473661b208.parquet": {
+      "num_bytes": 15443,
+      "checksum": null
+    }
+  },
+  "download_size": 15443,
+  "features": {
+    "tag": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "model_name": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "model_id": {
+      "dtype": "int64",
+      "_type": "Value"
+    },
+    "modelVersion_name": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "modelVersion_id": {
+      "dtype": "int64",
+      "_type": "Value"
+    },
+    "modelVersion_url": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "modelVersion_trainedWords": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "model_download_count": {
+      "dtype": "int64",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 108812,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 93369,
+      "num_examples": 722,
+      "dataset_name": "parquet"
+    }
+  }
+}

data/roster/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "a937ede09f446dbe",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": "train"
+}

requirements.txt

@@ -0,0 +1,4 @@
+huggingface_hub
+streamlit-elements==0.1.0
+streamlit-extras
+altair<5