messages
listlengths 3
3
| images
images listlengths 1
1
| bbox
stringlengths 9
24
| easyr1_prompt
stringlengths 269
883
|
|---|---|---|---|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on Celebrate our birthday!",
"role": "user"
},
{
"content": "(456,513)",
"role": "assistant"
}
] |
[349, 450, 563, 576]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on Celebrate our birthday!
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick the YouTube link",
"role": "user"
},
{
"content": "(235,534)",
"role": "assistant"
}
] |
[207, 508, 263, 560]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click the YouTube link
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on and",
"role": "user"
},
{
"content": "(1064,632)",
"role": "assistant"
}
] |
[860, 556, 1269, 709]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on and
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nPlease identify the coordinates of the webpage element I describe based on the provided screenshot (with point). This element serves as a mobile navigation trigger, enabling users to access various links within the webpage when clicked or tapped.",
"role": "user"
},
{
"content": "(201,14)",
"role": "assistant"
}
] |
[192, 6, 211, 22]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Please identify the coordinates of the webpage element I describe based on the provided screenshot (with point). This element serves as a mobile navigation trigger, enabling users to access various links within the webpage when clicked or tapped.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on UV DTF Sticker Customized For The 16oz Libbey Glasses Wraps Cup Can DIY Waterproof Easy To Use Custom Decals 1 Sheets",
"role": "user"
},
{
"content": "(266,105)",
"role": "assistant"
}
] |
[200, 98, 333, 113]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on UV DTF Sticker Customized For The 16oz Libbey Glasses Wraps Cup Can DIY Waterproof Easy To Use Custom Decals 1 Sheets
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nFrom the given webpage screenshot, I need you to identify the locations of the described element (with point). This element provides access to user account features and personalized content.",
"role": "user"
},
{
"content": "(616,13)",
"role": "assistant"
}
] |
[597, 3, 635, 24]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
From the given webpage screenshot, I need you to identify the locations of the described element (with point). This element provides access to user account features and personalized content.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick fill handle of R24",
"role": "user"
},
{
"content": "(1498,689)",
"role": "assistant"
}
] |
[1493, 684, 1503, 694]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click fill handle of R24
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nPoint to Choose a language and currency",
"role": "user"
},
{
"content": "(2056,130)",
"role": "assistant"
}
] |
[2036, 103, 2077, 158]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Point to Choose a language and currency
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nOn this webpage screenshot, I will point out an element; please predict their exact coordinates (with point). This element triggers a search popup, allowing users to initiate a search within the webpage.",
"role": "user"
},
{
"content": "(175,14)",
"role": "assistant"
}
] |
[167, 6, 184, 23]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
On this webpage screenshot, I will point out an element; please predict their exact coordinates (with point). This element triggers a search popup, allowing users to initiate a search within the webpage.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nNavigate to the user\"s guide.",
"role": "user"
},
{
"content": "(1652,1058)",
"role": "assistant"
}
] |
[1630, 1029, 1675, 1088]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Navigate to the user"s guide.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSelect Assassin",
"role": "user"
},
{
"content": "(1377,943)",
"role": "assistant"
}
] |
[1329, 925, 1426, 961]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Select Assassin
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI'll describe certain an element on this webpage image; your task is to find their locations (with point). This element collects the user's phone number as part of the application process.",
"role": "user"
},
{
"content": "(163,223)",
"role": "assistant"
}
] |
[43, 210, 283, 236]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I'll describe certain an element on this webpage image; your task is to find their locations (with point). This element collects the user's phone number as part of the application process.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nNavigate to What hosts like you say",
"role": "user"
},
{
"content": "(955,88)",
"role": "assistant"
}
] |
[890, 80, 1021, 97]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Navigate to What hosts like you say
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nUsing the image of this webpage, can you determine the coordinates of the element I describe (with point)? This element redirects the user to a setup guide for profiling in a Flutter app, providing a more focused resource for configuring performance monitoring and profiling in Sentry.",
"role": "user"
},
{
"content": "(414,80)",
"role": "assistant"
}
] |
[376, 73, 452, 88]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Using the image of this webpage, can you determine the coordinates of the element I describe (with point)? This element redirects the user to a setup guide for profiling in a Flutter app, providing a more focused resource for configuring performance monitoring and profiling in Sentry.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nChoose LS M47K-H2K1-1-Z, on the bottom right of the image",
"role": "user"
},
{
"content": "(696,1324)",
"role": "assistant"
}
] |
[616, 1309, 777, 1339]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Choose LS M47K-H2K1-1-Z, on the bottom right of the image
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSelect the handle located at the top of the text box containing the text \"Introduction Building confiden....\"",
"role": "user"
},
{
"content": "(839,222)",
"role": "assistant"
}
] |
[834, 217, 844, 227]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Select the handle located at the top of the text box containing the text "Introduction Building confiden...."
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nFrom this webpage image, I will describe a specific element. Please predict their exact locations (with point). This element toggles the UI to display the storage roots and facilitates navigation to different storage sections.",
"role": "user"
},
{
"content": "(25,41)",
"role": "assistant"
}
] |
[11, 26, 39, 57]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
From this webpage image, I will describe a specific element. Please predict their exact locations (with point). This element toggles the UI to display the storage roots and facilitates navigation to different storage sections.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nIn the provided web page image, I'll describe a specific element. Identify their locations, please (with point). This element provides access to a specific section of the Terms of Service document, allowing users to review and understand the rules and guidelines for using GitHub accounts.",
"role": "user"
},
{
"content": "(65,414)",
"role": "assistant"
}
] |
[25, 407, 106, 422]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
In the provided web page image, I'll describe a specific element. Identify their locations, please (with point). This element provides access to a specific section of the Terms of Service document, allowing users to review and understand the rules and guidelines for using GitHub accounts.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nThis region contains the main menu options for the application, including file, edit, view, and help.",
"role": "user"
},
{
"content": "(322,15)",
"role": "assistant"
}
] |
[37, 0, 607, 30]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
This region contains the main menu options for the application, including file, edit, view, and help.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nLower right corner of cell F59",
"role": "user"
},
{
"content": "(532,1042)",
"role": "assistant"
}
] |
[527, 1037, 537, 1047]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Lower right corner of cell F59
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nPlease use the provided webpage screenshot to locate the element I describe (with point). This element provides access to user-related content or functionality within the wiki.",
"role": "user"
},
{
"content": "(58,305)",
"role": "assistant"
}
] |
[13, 300, 103, 311]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Please use the provided webpage screenshot to locate the element I describe (with point). This element provides access to user-related content or functionality within the wiki.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nFind and click Arts",
"role": "user"
},
{
"content": "(887,125)",
"role": "assistant"
}
] |
[871, 114, 904, 137]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Find and click Arts
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nPlease determine the location of the element I describe in this webpage screenshot (with point). This element serves as a navigation link, directing users to the 'INTERIOR LIGHTING' section of the website, which is a part of a broader category of products. By clicking on this link, users can access and browse all interior lighting products available on the website.",
"role": "user"
},
{
"content": "(108,61)",
"role": "assistant"
}
] |
[3, 42, 214, 80]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Please determine the location of the element I describe in this webpage screenshot (with point). This element serves as a navigation link, directing users to the 'INTERIOR LIGHTING' section of the website, which is a part of a broader category of products. By clicking on this link, users can access and browse all interior lighting products available on the website.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nLocate Circular magnifying glass icon with 'in' text in light brown, centered and contrasting with the background",
"role": "user"
},
{
"content": "(121,771)",
"role": "assistant"
}
] |
[108, 758, 134, 785]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Locate Circular magnifying glass icon with 'in' text in light brown, centered and contrasting with the background
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on target through scope",
"role": "user"
},
{
"content": "(856,302)",
"role": "assistant"
}
] |
[775, 222, 938, 383]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on target through scope
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick to navigate to the video and audio section of the website",
"role": "user"
},
{
"content": "(394,374)",
"role": "assistant"
}
] |
[370, 359, 419, 389]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click to navigate to the video and audio section of the website
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nFrom this webpage image, I will describe a specific element. Please predict their exact locations (with point). This element triggers the download of a browser application.",
"role": "user"
},
{
"content": "(588,15)",
"role": "assistant"
}
] |
[535, 4, 641, 26]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
From this webpage image, I will describe a specific element. Please predict their exact locations (with point). This element triggers the download of a browser application.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nLocate Click text input field",
"role": "user"
},
{
"content": "(542,772)",
"role": "assistant"
}
] |
[312, 755, 772, 789]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Locate Click text input field
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nChoose Recycling",
"role": "user"
},
{
"content": "(601,517)",
"role": "assistant"
}
] |
[584, 511, 619, 524]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Choose Recycling
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nGiven the following text: \" everything that is said in class, but you are still responsible for this content.\" , find the text in the document and click the space between the continuous character \"l\" and \"l\" in the text.",
"role": "user"
},
{
"content": "(740,131)",
"role": "assistant"
}
] |
[737, 128, 744, 135]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Given the following text: " everything that is said in class, but you are still responsible for this content." , find the text in the document and click the space between the continuous character "l" and "l" in the text.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on sleeve",
"role": "user"
},
{
"content": "(340,331)",
"role": "assistant"
}
] |
[78, 230, 603, 433]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on sleeve
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nChoose A rectangular card with black background and red header, labeled 'New event'.",
"role": "user"
},
{
"content": "(111,87)",
"role": "assistant"
}
] |
[0, 67, 223, 108]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Choose A rectangular card with black background and red header, labeled 'New event'.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nGiven the following text: \" is designed to engage and inspire the next generation of Australian scientists on issues related to water and conservation. \" , find the text in the document and click the 2th character \"s\" in the text.",
"role": "user"
},
{
"content": "(690,466)",
"role": "assistant"
}
] |
[685, 461, 695, 471]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Given the following text: " is designed to engage and inspire the next generation of Australian scientists on issues related to water and conservation. " , find the text in the document and click the 2th character "s" in the text.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nchoose from list",
"role": "user"
},
{
"content": "(1301,154)",
"role": "assistant"
}
] |
[1243, 143, 1359, 166]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
choose from list
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSelect the handle located at the bottom of the text box containing the text \"We have identified important k....\" to adjust its size.",
"role": "user"
},
{
"content": "(901,567)",
"role": "assistant"
}
] |
[897, 562, 906, 572]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Select the handle located at the bottom of the text box containing the text "We have identified important k...." to adjust its size.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nGiven the following text: \" to glance back through the \" , find the text in the document and click the 1th character \"u\" in the text.",
"role": "user"
},
{
"content": "(821,630)",
"role": "assistant"
}
] |
[816, 625, 826, 635]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Given the following text: " to glance back through the " , find the text in the document and click the 1th character "u" in the text.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nGiven the following text: \" a significant digital divide (European Commission, 2019). This divide is particularly pronounced between urban and rural areas, with many rural communities lacking access to high-speed internet (Datta, 2020) This \" , find the text in the document and click the space between the continuous character \"a\" and \"s\" in the text.",
"role": "user"
},
{
"content": "(930,1039)",
"role": "assistant"
}
] |
[925, 1034, 935, 1044]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Given the following text: " a significant digital divide (European Commission, 2019). This divide is particularly pronounced between urban and rural areas, with many rural communities lacking access to high-speed internet (Datta, 2020) This " , find the text in the document and click the space between the continuous character "a" and "s" in the text.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nTap on North America",
"role": "user"
},
{
"content": "(364,492)",
"role": "assistant"
}
] |
[334, 486, 394, 499]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Tap on North America
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nEnable snapping to intersection points in the drawing.",
"role": "user"
},
{
"content": "(222,197)",
"role": "assistant"
}
] |
[206, 183, 239, 211]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Enable snapping to intersection points in the drawing.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI'll give descriptions of a certain webpage element; please identify where they are in this screenshot (with point). This element provides a direct path to download the Neighbors App from the App Store.",
"role": "user"
},
{
"content": "(57,290)",
"role": "assistant"
}
] |
[17, 276, 97, 304]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I'll give descriptions of a certain webpage element; please identify where they are in this screenshot (with point). This element provides a direct path to download the Neighbors App from the App Store.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nOpen video transitions for seamless scene changes",
"role": "user"
},
{
"content": "(2389,340)",
"role": "assistant"
}
] |
[2277, 320, 2502, 360]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Open video transitions for seamless scene changes
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSelect the rotate handle of the text box containing the text \"Market overview.\"",
"role": "user"
},
{
"content": "(1420,472)",
"role": "assistant"
}
] |
[1413, 465, 1427, 479]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Select the rotate handle of the text box containing the text "Market overview."
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSelect the Automobile Multipanel template for menu display",
"role": "user"
},
{
"content": "(1404,271)",
"role": "assistant"
}
] |
[1394, 258, 1415, 284]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Select the Automobile Multipanel template for menu display
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSelect the handle located at the bottom of the text box containing the text \"Product enhancement.\"",
"role": "user"
},
{
"content": "(1353,880)",
"role": "assistant"
}
] |
[1348, 875, 1358, 885]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Select the handle located at the bottom of the text box containing the text "Product enhancement."
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nGiven the following text: \"(Dubber & \" , find the text in the document and click the 1th character \"(\" in the text.",
"role": "user"
},
{
"content": "(540,565)",
"role": "assistant"
}
] |
[535, 560, 545, 570]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Given the following text: "(Dubber & " , find the text in the document and click the 1th character "(" in the text.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nLeft border of cell G-12",
"role": "user"
},
{
"content": "(532,411)",
"role": "assistant"
}
] |
[527, 406, 537, 416]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Left border of cell G-12
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI'll provide textual descriptions of the element in this webpage screenshot. Can you find their coordinates (with point)? This element provides access to a section related to the platform's virtual currency.",
"role": "user"
},
{
"content": "(195,9)",
"role": "assistant"
}
] |
[178, 3, 212, 15]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I'll provide textual descriptions of the element in this webpage screenshot. Can you find their coordinates (with point)? This element provides access to a section related to the platform's virtual currency.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSelect and drag the rotation handle of the text box containing the text \"Implement personalized engagem....\" to adjust its orientation.",
"role": "user"
},
{
"content": "(847,563)",
"role": "assistant"
}
] |
[842, 558, 852, 568]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Select and drag the rotation handle of the text box containing the text "Implement personalized engagem...." to adjust its orientation.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSelect the handle located at the bottom of the text box labeled \"Project Resources.\"",
"role": "user"
},
{
"content": "(930,778)",
"role": "assistant"
}
] |
[923, 771, 937, 785]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Select the handle located at the bottom of the text box labeled "Project Resources."
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nChoose the menu, on the top right of the screenshot",
"role": "user"
},
{
"content": "(841,102)",
"role": "assistant"
}
] |
[793, 84, 889, 121]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Choose the menu, on the top right of the screenshot
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nTap on Intel on Instagram",
"role": "user"
},
{
"content": "(631,982)",
"role": "assistant"
}
] |
[611, 962, 652, 1002]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Tap on Intel on Instagram
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nIn the screenshot of this web page, please give me the coordinates of the element I want to click on according to my instructions (with point). This element triggers a search operation on the documentation content, allowing users to find relevant information more efficiently. Interacting with this button would initiate a search query based on the user's input in the search box.",
"role": "user"
},
{
"content": "(202,178)",
"role": "assistant"
}
] |
[190, 167, 215, 189]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
In the screenshot of this web page, please give me the coordinates of the element I want to click on according to my instructions (with point). This element triggers a search operation on the documentation content, allowing users to find relevant information more efficiently. Interacting with this button would initiate a search query based on the user's input in the search box.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nFrom the given webpage screenshot, I need you to identify the locations of the described element (with point). This element launches the Gmail application, opening a welcome tour upon initialization.",
"role": "user"
},
{
"content": "(148,187)",
"role": "assistant"
}
] |
[136, 171, 160, 204]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
From the given webpage screenshot, I need you to identify the locations of the described element (with point). This element launches the Gmail application, opening a welcome tour upon initialization.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nUsing the screenshot of this webpage, identify the coordinates of the element I describe (with point). This element provides access to a specific legal document, allowing users to view detailed information about Amazon's privacy practices and policies.",
"role": "user"
},
{
"content": "(111,225)",
"role": "assistant"
}
] |
[6, 212, 216, 239]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Using the screenshot of this webpage, identify the coordinates of the element I describe (with point). This element provides access to a specific legal document, allowing users to view detailed information about Amazon's privacy practices and policies.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nTop left corner of cell X-1",
"role": "user"
},
{
"content": "(1307,103)",
"role": "assistant"
}
] |
[1301, 96, 1314, 110]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Top left corner of cell X-1
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nGiven the following text: \"https://arxiv.org/pdf/2402.19173.pdf\" , find the text in the document and click the 1th character \"1\" in the text.",
"role": "user"
},
{
"content": "(622,447)",
"role": "assistant"
}
] |
[617, 442, 627, 452]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Given the following text: "https://arxiv.org/pdf/2402.19173.pdf" , find the text in the document and click the 1th character "1" in the text.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nGiven the following text: \"Since Spanish explorers brought back chocolate from the new world, chocolate consumption has become a worldwide phenomenon\" , find the text in the document and click the 1th character \"f\" in the text.",
"role": "user"
},
{
"content": "(708,142)",
"role": "assistant"
}
] |
[705, 139, 712, 146]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Given the following text: "Since Spanish explorers brought back chocolate from the new world, chocolate consumption has become a worldwide phenomenon" , find the text in the document and click the 1th character "f" in the text.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nIdentify council (12 items), in \"Tech In Asia\"",
"role": "user"
},
{
"content": "(835,1299)",
"role": "assistant"
}
] |
[792, 1280, 878, 1318]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Identify council (12 items), in "Tech In Asia"
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on the handle at the bottom side of the bounding box of the image depicting a close-up of a dry branch or shrub on a sandy surface under a cloudy sky to resize it.",
"role": "user"
},
{
"content": "(1008,566)",
"role": "assistant"
}
] |
[1003, 561, 1013, 571]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on the handle at the bottom side of the bounding box of the image depicting a close-up of a dry branch or shrub on a sandy surface under a cloudy sky to resize it.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSelect the handle located at the bottom-left corner of the text box containing the text \"Product benefits.\"",
"role": "user"
},
{
"content": "(607,833)",
"role": "assistant"
}
] |
[602, 828, 612, 838]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Select the handle located at the bottom-left corner of the text box containing the text "Product benefits."
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nNavigate to News",
"role": "user"
},
{
"content": "(927,217)",
"role": "assistant"
}
] |
[891, 187, 964, 248]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Navigate to News
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick left edge of S4",
"role": "user"
},
{
"content": "(1498,229)",
"role": "assistant"
}
] |
[1493, 224, 1503, 234]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click left edge of S4
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nWhat is the element that is horizontally to the right of the \"New Java class options\" and closest to it?",
"role": "user"
},
{
"content": "(403,99)",
"role": "assistant"
}
] |
[392, 89, 415, 109]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
What is the element that is horizontally to the right of the "New Java class options" and closest to it?
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nModify text appearance by changing font color",
"role": "user"
},
{
"content": "(547,107)",
"role": "assistant"
}
] |
[520, 85, 574, 130]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Modify text appearance by changing font color
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nFor the element I describe in this page capture, can you predict their positions (with point)? This element provides a way to navigate back to the website's main page or a higher-level page, allowing users to access other sections or features of the website.",
"role": "user"
},
{
"content": "(62,30)",
"role": "assistant"
}
] |
[26, 17, 99, 43]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
For the element I describe in this page capture, can you predict their positions (with point)? This element provides a way to navigate back to the website's main page or a higher-level page, allowing users to access other sections or features of the website.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nEnable image reading functionality using OpenImageIO.",
"role": "user"
},
{
"content": "(1784,156)",
"role": "assistant"
}
] |
[1771, 142, 1798, 170]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Enable image reading functionality using OpenImageIO.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nGiven the following text: \"10:34:46,E225,MOK,3\" , find the text in the document and click the space between the continuous character \"1\" and \"0\" in the text.",
"role": "user"
},
{
"content": "(676,1046)",
"role": "assistant"
}
] |
[671, 1041, 681, 1051]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Given the following text: "10:34:46,E225,MOK,3" , find the text in the document and click the space between the continuous character "1" and "0" in the text.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick \"Page Number\" from the submenu",
"role": "user"
},
{
"content": "(375,476)",
"role": "assistant"
}
] |
[297, 466, 454, 487]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click "Page Number" from the submenu
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nLocate Latest Indian Movies News, Photos, Videos & Trailers: MellowPlex",
"role": "user"
},
{
"content": "(11,101)",
"role": "assistant"
}
] |
[0, 88, 22, 114]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Locate Latest Indian Movies News, Photos, Videos & Trailers: MellowPlex
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\nIf the users' element description is unfeasible because the element is missing or the purpose is not achievable, return <refusal>.\n\nOtherwise, output the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSend the Styles pane behind the document so it no longer covers the page.",
"role": "user"
},
{
"content": "<refusal>",
"role": "assistant"
}
] |
<refusal>
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
If the users' element description is unfeasible because the element is missing or the purpose is not achievable, return <refusal>.
Otherwise, output the coordinate pair exactly:
(x,y)
Send the Styles pane behind the document so it no longer covers the page.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nWhat is the element that is horizontally closest to the \"insert chart\" and to the left of it?",
"role": "user"
},
{
"content": "(868,67)",
"role": "assistant"
}
] |
[852, 51, 884, 83]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
What is the element that is horizontally closest to the "insert chart" and to the left of it?
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nNavigate to ESPN Cricket Home Page",
"role": "user"
},
{
"content": "(322,96)",
"role": "assistant"
}
] |
[289, 73, 356, 120]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Navigate to ESPN Cricket Home Page
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nActivate the Clone tool for duplicating selected areas.",
"role": "user"
},
{
"content": "(246,79)",
"role": "assistant"
}
] |
[236, 70, 257, 88]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Activate the Clone tool for duplicating selected areas.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick fill handle of J34",
"role": "user"
},
{
"content": "(854,917)",
"role": "assistant"
}
] |
[849, 912, 859, 922]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click fill handle of J34
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\ncreate a local coordinate system",
"role": "user"
},
{
"content": "(348,153)",
"role": "assistant"
}
] |
[334, 136, 363, 171]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
create a local coordinate system
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\nIf the users' element description is unfeasible because the element is missing or the purpose is not achievable, return <refusal>.\n\nOtherwise, output the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nNone",
"role": "user"
},
{
"content": "<refusal>",
"role": "assistant"
}
] |
<refusal>
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
If the users' element description is unfeasible because the element is missing or the purpose is not achievable, return <refusal>.
Otherwise, output the coordinate pair exactly:
(x,y)
None
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\nIf the users' element description is unfeasible because the element is missing or the purpose is not achievable, return <refusal>.\n\nOtherwise, output the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nMake the System Settings window 50% transparent.",
"role": "user"
},
{
"content": "<refusal>",
"role": "assistant"
}
] |
<refusal>
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
If the users' element description is unfeasible because the element is missing or the purpose is not achievable, return <refusal>.
Otherwise, output the coordinate pair exactly:
(x,y)
Make the System Settings window 50% transparent.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on \"Contact Us\"",
"role": "user"
},
{
"content": "(1242,31)",
"role": "assistant"
}
] |
[1163, 0, 1321, 62]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on "Contact Us"
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nPoint to Open Neural Network Exchange (ONNX) Model and ONNX Runtime* Learn More",
"role": "user"
},
{
"content": "(782,521)",
"role": "assistant"
}
] |
[689, 491, 875, 552]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Point to Open Neural Network Exchange (ONNX) Model and ONNX Runtime* Learn More
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nadd 'in' mark",
"role": "user"
},
{
"content": "(1608,839)",
"role": "assistant"
}
] |
[1591, 822, 1625, 856]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
add 'in' mark
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nNorthwest corner of cell P31",
"role": "user"
},
{
"content": "(1256,932)",
"role": "assistant"
}
] |
[1251, 927, 1261, 937]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Northwest corner of cell P31
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on Settings",
"role": "user"
},
{
"content": "(673,260)",
"role": "assistant"
}
] |
[589, 251, 757, 269]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on Settings
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\nIf the users' element description is unfeasible because the element is missing or the purpose is not achievable, return <refusal>.\n\nOtherwise, output the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nPin the “These tiny creatures…” article card to the Windows taskbar.",
"role": "user"
},
{
"content": "<refusal>",
"role": "assistant"
}
] |
<refusal>
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
If the users' element description is unfeasible because the element is missing or the purpose is not achievable, return <refusal>.
Otherwise, output the coordinate pair exactly:
(x,y)
Pin the “These tiny creatures…” article card to the Windows taskbar.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nIn this webpage capture, I will describe a certain element. Please locate it for me (with point). This element triggers a permission request for YouTube, allowing the user to choose whether to enable or disable notifications for the app.",
"role": "user"
},
{
"content": "(315,218)",
"role": "assistant"
}
] |
[284, 199, 346, 238]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
In this webpage capture, I will describe a certain element. Please locate it for me (with point). This element triggers a permission request for YouTube, allowing the user to choose whether to enable or disable notifications for the app.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nV-61",
"role": "user"
},
{
"content": "(1781,693)",
"role": "assistant"
}
] |
[1776, 688, 1786, 698]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
V-61
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\nIf the users' element description is unfeasible because the element is missing or the purpose is not achievable, return <refusal>.\n\nOtherwise, output the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick the green \"Discover\" tab in the top-right navigation bar.",
"role": "user"
},
{
"content": "<refusal>",
"role": "assistant"
}
] |
<refusal>
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
If the users' element description is unfeasible because the element is missing or the purpose is not achievable, return <refusal>.
Otherwise, output the coordinate pair exactly:
(x,y)
Click the green "Discover" tab in the top-right navigation bar.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nAdds a page break at the current cursor position.",
"role": "user"
},
{
"content": "(1057,92)",
"role": "assistant"
}
] |
[1037, 72, 1078, 112]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Adds a page break at the current cursor position.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSelect the center of the text box containing the text \"Mirjam Nilsson\" and the email \"mirjam@contoso....\"",
"role": "user"
},
{
"content": "(807,801)",
"role": "assistant"
}
] |
[802, 796, 812, 806]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Select the center of the text box containing the text "Mirjam Nilsson" and the email "mirjam@contoso...."
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on the handle on the bottom side of the bounding box surrounding the photograph of a person sitting on a rocky cliff overlooking the ocean during daylight.",
"role": "user"
},
{
"content": "(1583,1129)",
"role": "assistant"
}
] |
[1576, 1122, 1590, 1136]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on the handle on the bottom side of the bounding box surrounding the photograph of a person sitting on a rocky cliff overlooking the ocean during daylight.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\nIf the users' element description is unfeasible because the element is missing or the purpose is not achievable, return <refusal>.\n\nOtherwise, output the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick the \"Activities\" button in the top-right corner.",
"role": "user"
},
{
"content": "<refusal>",
"role": "assistant"
}
] |
<refusal>
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
If the users' element description is unfeasible because the element is missing or the purpose is not achievable, return <refusal>.
Otherwise, output the coordinate pair exactly:
(x,y)
Click the "Activities" button in the top-right corner.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nUpper left corner of cell R8",
"role": "user"
},
{
"content": "(1418,338)",
"role": "assistant"
}
] |
[1413, 333, 1423, 343]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Upper left corner of cell R8
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nI will describe an element from a webpage screenshot; your role is to locate it (with point). This element launches the Gmail app, displaying a welcome tour with its new features.",
"role": "user"
},
{
"content": "(58,270)",
"role": "assistant"
}
] |
[41, 260, 76, 280]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
I will describe an element from a webpage screenshot; your role is to locate it (with point). This element launches the Gmail app, displaying a welcome tour with its new features.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSelect fill handle point of M73",
"role": "user"
},
{
"content": "(1095,1003)",
"role": "assistant"
}
] |
[1090, 998, 1100, 1008]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Select fill handle point of M73
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick on orbitz in white",
"role": "user"
},
{
"content": "(73,26)",
"role": "assistant"
}
] |
[2, 18, 144, 35]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click on orbitz in white
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nLocate particular input/output signals",
"role": "user"
},
{
"content": "(1195,358)",
"role": "assistant"
}
] |
[1168, 332, 1222, 385]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Locate particular input/output signals
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSelect the rotate handle of the text box containing the number 10.",
"role": "user"
},
{
"content": "(1579,887)",
"role": "assistant"
}
] |
[1574, 882, 1584, 892]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Select the rotate handle of the text box containing the number 10.
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSelect the rotate handle of the text box labeled \"FINAL TIPS & TAKEAWAYS.\"",
"role": "user"
},
{
"content": "(768,203)",
"role": "assistant"
}
] |
[763, 198, 774, 208]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Select the rotate handle of the text box labeled "FINAL TIPS & TAKEAWAYS."
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nClick right border at column B row 19",
"role": "user"
},
{
"content": "(211,549)",
"role": "assistant"
}
] |
[206, 544, 216, 554]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Click right border at column B row 19
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nEnter precise Y-axis position value for object placement",
"role": "user"
},
{
"content": "(2013,218)",
"role": "assistant"
}
] |
[1890, 204, 2136, 233]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Enter precise Y-axis position value for object placement
|
|
[
{
"content": "You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.\n\nOutput the coordinate pair exactly:\n(x,y)",
"role": "system"
},
{
"content": "<image>\nSelect Item 2",
"role": "user"
},
{
"content": "(786,746)",
"role": "assistant"
}
] |
[771, 724, 802, 769]
|
You are an expert UI element locator. Given a GUI image and a user's element description, provide the coordinates of the specified element as a single (x,y) point. For elements with area, return the center point.
Output the coordinate pair exactly:
(x,y)
<image>
Select Item 2
|
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 21