Hugging Face's logo

Datasets:
hexuan21
/
VideoScore_legacy

License:
Dataset card Data Studio Files
xet
Community
hexuan21 commited on
Commit
561b516
·
verified ·
1 Parent(s): 8ff4d13

upload subset_20k/test_600 's json, videos and frames

Browse files
Files changed (1) hide show
  1. data/subset_20k/test_600/data_static.json +622 -0
data/subset_20k/test_600/data_static.json ADDED
@@ -0,0 +1,622 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "id": "d500946",
4
+ "images": [
5
+ "d500946_00.jpg",
6
+ "d500946_01.jpg",
7
+ "d500946_02.jpg",
8
+ "d500946_03.jpg",
9
+ "d500946_04.jpg",
10
+ "d500946_05.jpg",
11
+ "d500946_06.jpg",
12
+ "d500946_07.jpg",
13
+ "d500946_08.jpg",
14
+ "d500946_09.jpg",
15
+ "d500946_10.jpg",
16
+ "d500946_11.jpg",
17
+ "d500946_12.jpg",
18
+ "d500946_13.jpg",
19
+ "d500946_14.jpg",
20
+ "d500946_15.jpg"
21
+ ],
22
+ "conversations": [
23
+ {
24
+ "from": "human",
25
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is create video of children sad because of their sneakers ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
26
+ },
27
+ {
28
+ "from": "gpt",
29
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
30
+ }
31
+ ]
32
+ },
33
+ {
34
+ "id": "d500947",
35
+ "images": [
36
+ "d500947_00.jpg",
37
+ "d500947_01.jpg",
38
+ "d500947_02.jpg",
39
+ "d500947_03.jpg",
40
+ "d500947_04.jpg",
41
+ "d500947_05.jpg",
42
+ "d500947_06.jpg",
43
+ "d500947_07.jpg",
44
+ "d500947_08.jpg",
45
+ "d500947_09.jpg",
46
+ "d500947_10.jpg",
47
+ "d500947_11.jpg",
48
+ "d500947_12.jpg",
49
+ "d500947_13.jpg",
50
+ "d500947_14.jpg",
51
+ "d500947_15.jpg"
52
+ ],
53
+ "conversations": [
54
+ {
55
+ "from": "human",
56
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is 8k, man with fearful expression horror, exploring the dark corridors of the house ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
57
+ },
58
+ {
59
+ "from": "gpt",
60
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
61
+ }
62
+ ]
63
+ },
64
+ {
65
+ "id": "d500948",
66
+ "images": [
67
+ "d500948_00.jpg",
68
+ "d500948_01.jpg",
69
+ "d500948_02.jpg",
70
+ "d500948_03.jpg",
71
+ "d500948_04.jpg",
72
+ "d500948_05.jpg",
73
+ "d500948_06.jpg",
74
+ "d500948_07.jpg",
75
+ "d500948_08.jpg",
76
+ "d500948_09.jpg",
77
+ "d500948_10.jpg",
78
+ "d500948_11.jpg",
79
+ "d500948_12.jpg",
80
+ "d500948_13.jpg",
81
+ "d500948_14.jpg",
82
+ "d500948_15.jpg"
83
+ ],
84
+ "conversations": [
85
+ {
86
+ "from": "human",
87
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is tentacles growing from television screens 4k ar 16:9 ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
88
+ },
89
+ {
90
+ "from": "gpt",
91
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
92
+ }
93
+ ]
94
+ },
95
+ {
96
+ "id": "d500949",
97
+ "images": [
98
+ "d500949_00.jpg",
99
+ "d500949_01.jpg",
100
+ "d500949_02.jpg",
101
+ "d500949_03.jpg",
102
+ "d500949_04.jpg",
103
+ "d500949_05.jpg",
104
+ "d500949_06.jpg",
105
+ "d500949_07.jpg",
106
+ "d500949_08.jpg",
107
+ "d500949_09.jpg",
108
+ "d500949_10.jpg",
109
+ "d500949_11.jpg",
110
+ "d500949_12.jpg",
111
+ "d500949_13.jpg",
112
+ "d500949_14.jpg",
113
+ "d500949_15.jpg"
114
+ ],
115
+ "conversations": [
116
+ {
117
+ "from": "human",
118
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is cat, subtle movement of head, subtle movement of mouth, fur moving in the air, eyes blinking ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
119
+ },
120
+ {
121
+ "from": "gpt",
122
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
123
+ }
124
+ ]
125
+ },
126
+ {
127
+ "id": "d500950",
128
+ "images": [
129
+ "d500950_00.jpg",
130
+ "d500950_01.jpg",
131
+ "d500950_02.jpg",
132
+ "d500950_03.jpg",
133
+ "d500950_04.jpg",
134
+ "d500950_05.jpg",
135
+ "d500950_06.jpg",
136
+ "d500950_07.jpg",
137
+ "d500950_08.jpg",
138
+ "d500950_09.jpg",
139
+ "d500950_10.jpg",
140
+ "d500950_11.jpg",
141
+ "d500950_12.jpg",
142
+ "d500950_13.jpg",
143
+ "d500950_14.jpg",
144
+ "d500950_15.jpg"
145
+ ],
146
+ "conversations": [
147
+ {
148
+ "from": "human",
149
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is giant hurricanes sweeping through a village ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
150
+ },
151
+ {
152
+ "from": "gpt",
153
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
154
+ }
155
+ ]
156
+ },
157
+ {
158
+ "id": "d500951",
159
+ "images": [
160
+ "d500951_00.jpg",
161
+ "d500951_01.jpg",
162
+ "d500951_02.jpg",
163
+ "d500951_03.jpg",
164
+ "d500951_04.jpg",
165
+ "d500951_05.jpg",
166
+ "d500951_06.jpg",
167
+ "d500951_07.jpg",
168
+ "d500951_08.jpg",
169
+ "d500951_09.jpg",
170
+ "d500951_10.jpg",
171
+ "d500951_11.jpg",
172
+ "d500951_12.jpg",
173
+ "d500951_13.jpg",
174
+ "d500951_14.jpg",
175
+ "d500951_15.jpg"
176
+ ],
177
+ "conversations": [
178
+ {
179
+ "from": "human",
180
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is a tree with the form a woman, in enhanced highly detailed digital painting style ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
181
+ },
182
+ {
183
+ "from": "gpt",
184
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
185
+ }
186
+ ]
187
+ },
188
+ {
189
+ "id": "d500952",
190
+ "images": [
191
+ "d500952_00.jpg",
192
+ "d500952_01.jpg",
193
+ "d500952_02.jpg",
194
+ "d500952_03.jpg",
195
+ "d500952_04.jpg",
196
+ "d500952_05.jpg",
197
+ "d500952_06.jpg",
198
+ "d500952_07.jpg",
199
+ "d500952_08.jpg",
200
+ "d500952_09.jpg",
201
+ "d500952_10.jpg",
202
+ "d500952_11.jpg",
203
+ "d500952_12.jpg",
204
+ "d500952_13.jpg",
205
+ "d500952_14.jpg",
206
+ "d500952_15.jpg"
207
+ ],
208
+ "conversations": [
209
+ {
210
+ "from": "human",
211
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is i want a snow in the mountain sea ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
212
+ },
213
+ {
214
+ "from": "gpt",
215
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
216
+ }
217
+ ]
218
+ },
219
+ {
220
+ "id": "d500953",
221
+ "images": [
222
+ "d500953_00.jpg",
223
+ "d500953_01.jpg",
224
+ "d500953_02.jpg",
225
+ "d500953_03.jpg",
226
+ "d500953_04.jpg",
227
+ "d500953_05.jpg",
228
+ "d500953_06.jpg",
229
+ "d500953_07.jpg",
230
+ "d500953_08.jpg",
231
+ "d500953_09.jpg",
232
+ "d500953_10.jpg",
233
+ "d500953_11.jpg",
234
+ "d500953_12.jpg",
235
+ "d500953_13.jpg",
236
+ "d500953_14.jpg",
237
+ "d500953_15.jpg"
238
+ ],
239
+ "conversations": [
240
+ {
241
+ "from": "human",
242
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is Make me something that plays the guitar ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
243
+ },
244
+ {
245
+ "from": "gpt",
246
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
247
+ }
248
+ ]
249
+ },
250
+ {
251
+ "id": "d500954",
252
+ "images": [
253
+ "d500954_00.jpg",
254
+ "d500954_01.jpg",
255
+ "d500954_02.jpg",
256
+ "d500954_03.jpg",
257
+ "d500954_04.jpg",
258
+ "d500954_05.jpg",
259
+ "d500954_06.jpg",
260
+ "d500954_07.jpg",
261
+ "d500954_08.jpg",
262
+ "d500954_09.jpg",
263
+ "d500954_10.jpg",
264
+ "d500954_11.jpg",
265
+ "d500954_12.jpg",
266
+ "d500954_13.jpg",
267
+ "d500954_14.jpg",
268
+ "d500954_15.jpg"
269
+ ],
270
+ "conversations": [
271
+ {
272
+ "from": "human",
273
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is Illustrate a scene where an anime girl, her eyes blazing with determination, stands in a dynamic pose. She holds a pistol emitting fiery energy, while behind her, a surreal landscape unfolds ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
274
+ },
275
+ {
276
+ "from": "gpt",
277
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
278
+ }
279
+ ]
280
+ },
281
+ {
282
+ "id": "d500955",
283
+ "images": [
284
+ "d500955_00.jpg",
285
+ "d500955_01.jpg",
286
+ "d500955_02.jpg",
287
+ "d500955_03.jpg",
288
+ "d500955_04.jpg",
289
+ "d500955_05.jpg",
290
+ "d500955_06.jpg",
291
+ "d500955_07.jpg",
292
+ "d500955_08.jpg",
293
+ "d500955_09.jpg",
294
+ "d500955_10.jpg",
295
+ "d500955_11.jpg",
296
+ "d500955_12.jpg",
297
+ "d500955_13.jpg",
298
+ "d500955_14.jpg",
299
+ "d500955_15.jpg"
300
+ ],
301
+ "conversations": [
302
+ {
303
+ "from": "human",
304
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is Visuals of a mysterious, isolated village in the Himalayas, eerie sounds echoing ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
305
+ },
306
+ {
307
+ "from": "gpt",
308
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
309
+ }
310
+ ]
311
+ },
312
+ {
313
+ "id": "d500956",
314
+ "images": [
315
+ "d500956_00.jpg",
316
+ "d500956_01.jpg",
317
+ "d500956_02.jpg",
318
+ "d500956_03.jpg",
319
+ "d500956_04.jpg",
320
+ "d500956_05.jpg",
321
+ "d500956_06.jpg",
322
+ "d500956_07.jpg",
323
+ "d500956_08.jpg",
324
+ "d500956_09.jpg",
325
+ "d500956_10.jpg",
326
+ "d500956_11.jpg",
327
+ "d500956_12.jpg",
328
+ "d500956_13.jpg",
329
+ "d500956_14.jpg",
330
+ "d500956_15.jpg"
331
+ ],
332
+ "conversations": [
333
+ {
334
+ "from": "human",
335
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is A Creature Crashed Got Hit In The Car (DashCam ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
336
+ },
337
+ {
338
+ "from": "gpt",
339
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
340
+ }
341
+ ]
342
+ },
343
+ {
344
+ "id": "d500957",
345
+ "images": [
346
+ "d500957_00.jpg",
347
+ "d500957_01.jpg",
348
+ "d500957_02.jpg",
349
+ "d500957_03.jpg",
350
+ "d500957_04.jpg",
351
+ "d500957_05.jpg",
352
+ "d500957_06.jpg",
353
+ "d500957_07.jpg",
354
+ "d500957_08.jpg",
355
+ "d500957_09.jpg",
356
+ "d500957_10.jpg",
357
+ "d500957_11.jpg",
358
+ "d500957_12.jpg",
359
+ "d500957_13.jpg",
360
+ "d500957_14.jpg",
361
+ "d500957_15.jpg"
362
+ ],
363
+ "conversations": [
364
+ {
365
+ "from": "human",
366
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is Einstein waved to the camera with VR glasses on ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
367
+ },
368
+ {
369
+ "from": "gpt",
370
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
371
+ }
372
+ ]
373
+ },
374
+ {
375
+ "id": "d500958",
376
+ "images": [
377
+ "d500958_00.jpg",
378
+ "d500958_01.jpg",
379
+ "d500958_02.jpg",
380
+ "d500958_03.jpg",
381
+ "d500958_04.jpg",
382
+ "d500958_05.jpg",
383
+ "d500958_06.jpg",
384
+ "d500958_07.jpg",
385
+ "d500958_08.jpg",
386
+ "d500958_09.jpg",
387
+ "d500958_10.jpg",
388
+ "d500958_11.jpg",
389
+ "d500958_12.jpg",
390
+ "d500958_13.jpg",
391
+ "d500958_14.jpg",
392
+ "d500958_15.jpg"
393
+ ],
394
+ "conversations": [
395
+ {
396
+ "from": "human",
397
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is The Chinese King , QinShiHuang, is watching you in the morning sunshine. ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
398
+ },
399
+ {
400
+ "from": "gpt",
401
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
402
+ }
403
+ ]
404
+ },
405
+ {
406
+ "id": "d500960",
407
+ "images": [
408
+ "d500960_00.jpg",
409
+ "d500960_01.jpg",
410
+ "d500960_02.jpg",
411
+ "d500960_03.jpg",
412
+ "d500960_04.jpg",
413
+ "d500960_05.jpg",
414
+ "d500960_06.jpg",
415
+ "d500960_07.jpg",
416
+ "d500960_08.jpg",
417
+ "d500960_09.jpg",
418
+ "d500960_10.jpg",
419
+ "d500960_11.jpg",
420
+ "d500960_12.jpg",
421
+ "d500960_13.jpg",
422
+ "d500960_14.jpg",
423
+ "d500960_15.jpg"
424
+ ],
425
+ "conversations": [
426
+ {
427
+ "from": "human",
428
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is Templar Knight with goat head and tounge of a cobra surreal Hieronymus Bosch Alejandro Jodorowsky 1920s ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
429
+ },
430
+ {
431
+ "from": "gpt",
432
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
433
+ }
434
+ ]
435
+ },
436
+ {
437
+ "id": "d500961",
438
+ "images": [
439
+ "d500961_00.jpg",
440
+ "d500961_01.jpg",
441
+ "d500961_02.jpg",
442
+ "d500961_03.jpg",
443
+ "d500961_04.jpg",
444
+ "d500961_05.jpg",
445
+ "d500961_06.jpg",
446
+ "d500961_07.jpg",
447
+ "d500961_08.jpg",
448
+ "d500961_09.jpg",
449
+ "d500961_10.jpg",
450
+ "d500961_11.jpg",
451
+ "d500961_12.jpg",
452
+ "d500961_13.jpg",
453
+ "d500961_14.jpg",
454
+ "d500961_15.jpg"
455
+ ],
456
+ "conversations": [
457
+ {
458
+ "from": "human",
459
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is underwater statue of goddess Athena, overgrown by coral, mystical cinematic scene ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
460
+ },
461
+ {
462
+ "from": "gpt",
463
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
464
+ }
465
+ ]
466
+ },
467
+ {
468
+ "id": "d500962",
469
+ "images": [
470
+ "d500962_00.jpg",
471
+ "d500962_01.jpg",
472
+ "d500962_02.jpg",
473
+ "d500962_03.jpg",
474
+ "d500962_04.jpg",
475
+ "d500962_05.jpg",
476
+ "d500962_06.jpg",
477
+ "d500962_07.jpg",
478
+ "d500962_08.jpg",
479
+ "d500962_09.jpg",
480
+ "d500962_10.jpg",
481
+ "d500962_11.jpg",
482
+ "d500962_12.jpg",
483
+ "d500962_13.jpg",
484
+ "d500962_14.jpg",
485
+ "d500962_15.jpg"
486
+ ],
487
+ "conversations": [
488
+ {
489
+ "from": "human",
490
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is zoom in sunflower, closeup, sunraise, timelapse ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
491
+ },
492
+ {
493
+ "from": "gpt",
494
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
495
+ }
496
+ ]
497
+ },
498
+ {
499
+ "id": "d500963",
500
+ "images": [
501
+ "d500963_00.jpg",
502
+ "d500963_01.jpg",
503
+ "d500963_02.jpg",
504
+ "d500963_03.jpg",
505
+ "d500963_04.jpg",
506
+ "d500963_05.jpg",
507
+ "d500963_06.jpg",
508
+ "d500963_07.jpg",
509
+ "d500963_08.jpg",
510
+ "d500963_09.jpg",
511
+ "d500963_10.jpg",
512
+ "d500963_11.jpg",
513
+ "d500963_12.jpg",
514
+ "d500963_13.jpg",
515
+ "d500963_14.jpg",
516
+ "d500963_15.jpg"
517
+ ],
518
+ "conversations": [
519
+ {
520
+ "from": "human",
521
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is human head facing camera directly , and zoom into the skull of the head with details of Anatomy and split the bones anatomically , show only the head skull nothing else and split it like anatomy\n\nthe Skull should face directly at the camera ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
522
+ },
523
+ {
524
+ "from": "gpt",
525
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
526
+ }
527
+ ]
528
+ },
529
+ {
530
+ "id": "d500965",
531
+ "images": [
532
+ "d500965_00.jpg",
533
+ "d500965_01.jpg",
534
+ "d500965_02.jpg",
535
+ "d500965_03.jpg",
536
+ "d500965_04.jpg",
537
+ "d500965_05.jpg",
538
+ "d500965_06.jpg",
539
+ "d500965_07.jpg",
540
+ "d500965_08.jpg",
541
+ "d500965_09.jpg",
542
+ "d500965_10.jpg",
543
+ "d500965_11.jpg",
544
+ "d500965_12.jpg",
545
+ "d500965_13.jpg",
546
+ "d500965_14.jpg",
547
+ "d500965_15.jpg"
548
+ ],
549
+ "conversations": [
550
+ {
551
+ "from": "human",
552
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is Venus gains the crown and dreams begin in her Qasr ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
553
+ },
554
+ {
555
+ "from": "gpt",
556
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
557
+ }
558
+ ]
559
+ },
560
+ {
561
+ "id": "d500966",
562
+ "images": [
563
+ "d500966_00.jpg",
564
+ "d500966_01.jpg",
565
+ "d500966_02.jpg",
566
+ "d500966_03.jpg",
567
+ "d500966_04.jpg",
568
+ "d500966_05.jpg",
569
+ "d500966_06.jpg",
570
+ "d500966_07.jpg",
571
+ "d500966_08.jpg",
572
+ "d500966_09.jpg",
573
+ "d500966_10.jpg",
574
+ "d500966_11.jpg",
575
+ "d500966_12.jpg",
576
+ "d500966_13.jpg",
577
+ "d500966_14.jpg",
578
+ "d500966_15.jpg"
579
+ ],
580
+ "conversations": [
581
+ {
582
+ "from": "human",
583
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is a burning blue fabric with flowers ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
584
+ },
585
+ {
586
+ "from": "gpt",
587
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
588
+ }
589
+ ]
590
+ },
591
+ {
592
+ "id": "d500967",
593
+ "images": [
594
+ "d500967_00.jpg",
595
+ "d500967_01.jpg",
596
+ "d500967_02.jpg",
597
+ "d500967_03.jpg",
598
+ "d500967_04.jpg",
599
+ "d500967_05.jpg",
600
+ "d500967_06.jpg",
601
+ "d500967_07.jpg",
602
+ "d500967_08.jpg",
603
+ "d500967_09.jpg",
604
+ "d500967_10.jpg",
605
+ "d500967_11.jpg",
606
+ "d500967_12.jpg",
607
+ "d500967_13.jpg",
608
+ "d500967_14.jpg",
609
+ "d500967_15.jpg"
610
+ ],
611
+ "conversations": [
612
+ {
613
+ "from": "human",
614
+ "value": "\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, \nplease watch the following frames of a given video and see the text prompt for generating the video, \nthen give scores from 7 different dimensions:\n(1) visual quality, \n(2) object consistency,\n(3) dynamic degree,\n(4) motion smoothness,\n(5) text-to-video alignment,\n(6) factual consistency, \n(7) overall score\nfor each dimension, output a number from [1,2,3], in which '1' stands for 'Bad', '2' stands for 'Average', '3' stands for 'Good'.\nHere is an output example: \nvisual quality: 3\nobject consistency: 2 \ndynamic degree: 2\nmotion smoothness: 1\ntext-to-video alignment: 1\nfactual consistency: 2\noverall score: 1\n\nFor this item, the text prompt is An alien world with different creatures. There is a young couple holding hands standing in the foreground. ,\nall the frames of video are as follows: \n\n<image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> <image> \n"
615
+ },
616
+ {
617
+ "from": "gpt",
618
+ "value": "visual quality: 1\n object consistency: 3\n dynamic degree: 1\n motion smoothness: 1\n text-to-video alignment: 1\n factual consistency: 1\n overall score: 1\n"
619
+ }
620
+ ]
621
+ }
622
+ ]