UIPro-WebUI-Data-v1

Part of the UIPro GUI-agent training suite (ICCV 2025). This repository packages the WebUI source into the unified UIPro instruction-tuning format, with coordinates normalized to a [0, 1000] grid.

Web-page screenshots with icon grounding/referring, element classification, intent grounding and widget listing.

Dataset at a glance

Total samples	488,499
Valid images	327,280
Avg. samples / image	1.49
Coordinate scale	0–1000
Source dataset	WebUI

Samples by task

Task	Count
WidgetList	160,266
IconRef	116,403
IntentGnd	110,800
IconGnd	59,561
ElemClass	41,469

Repository file structure

File	Description
WebUI_scale1000_488k.json	The dataset: a JSON list of 488,499 sample objects (schema below).
WebUI_scale1000_488k_sample.json	A small preview slice of the same schema, for quick inspection without downloading everything.
WebUI_scale1000_488k_images.zip	All screenshots referenced by the image field, preserving the relative paths stored there.
WebUI_scale1000_488k_info.json	Full generation report — per-task counts, image statistics, invalid-element breakdown, and the exact processing config.

Unzip WebUI_scale1000_488k_images.zip and each sample's image path resolves relative to the extraction root.

Sample schema — every field explained

Each element of the main JSON list is one training sample. This dataset's samples use the following fields:

Field	Meaning
conversations	The vision-language dialogue: a list of turns, each `{"from": "human"
id	Unique sample identifier, formatted autogui_<dataset>_<task>_<n>. The <task> segment (e.g. intentgnd, textloc, ocr, elemgnd, elemref) tells you which task the sample belongs to.
image	Path to the screenshot inside _images.zip, relative to the archive root. Load the image by joining this path with your extraction directory.
task_attr	The task's target attribute in plain form — for grounding tasks the referred element's text/instruction; for OCR/referring tasks the queried coordinate string. Useful for filtering or building custom prompts without parsing the conversation.
unnormalized_box	Ground-truth bounding box in original image pixels, as [x1, y1, x2, y2] (top-left, bottom-right). Present when a box is available. Note: the answer in the gpt turn is normalized to 0–1000, while this field is the raw-pixel box — divide by width/height and multiply by 1000 to reconcile them.
wxh	Original screenshot size as the string "<width>x<height>" in pixels — use it to convert between the normalized 0–1000 coordinates and raw pixels.

Note: Fields tied to a bounding box (e.g. unnormalized_box) are only present on samples that have a box; point-only answers (e.g. some intent-grounding samples) may omit them.

The conversations field in detail

conversations is a list of turns that a vision-language model consumes directly:

• Each turn is {"from": "...", "value": "..."}.
• from is either human (the prompt) or gpt (the ground-truth response).
• The token <image> inside a human turn marks where the screenshot is spliced into the prompt — replace it with the actual image when tokenizing.

Coordinate system

• Answers are normalized to the 0–1000 range relative to image width/height.
• A point answer is formatted (x,y); a bounding box answer is (x1,y1,x2,y2).
• Prompts ending in (with point) expect a point; (with bbox) expect a box.
• unnormalized_box, when present, is the same box in raw pixels — combine it with wxh (or the image's true size) to convert between pixels and the normalized grid.

Example

{
  "id": "autogui_webui_widgetlist_107976",
  "conversations": [
    {
      "from": "human",
      "value": "<image>\nPlease list all the elements on the UI screen."
    },
    {
      "from": "gpt",
      "value": "0 StaticText '3个月考上北大法硕，她说普通人成功很简单' (26,14,708,64)\n1 link '' (731,14,972,90)\n2 StaticText '时间：2022-07-20 18:11' (26,71,405,88)\n3 StaticText '老鼠吓退大猫抢吃猫粮 猫连连后退拱手相让' (26,121,692,171)\n4 link '' (731,121,972,197)\n5 StaticText '时间：2022-07-20 17:32' (26,178,405,194)\n6 StaticText '普通人镜头下的真生活' (26,227,462,251)\n7 link '' (731,227,972,303)\n8 StaticText '时间：2022-07-20 16:15' (26,284,405,301)\n9 StaticText '加载更多' (413,333,587,355)\n10 emphasis '' (26,416,33,440)\n11 StaticText '更多' (887,418,959,437)\n12 StaticText '吴亦凡打卡的面馆被整改' (26,461,505,485)\n13 link '' (731,461,972,537)\n14 StaticText '时间：2022-07-20 18:34' (26,518,405,534)\n15 StaticText '广州人才入户年龄放宽5年 本科40岁硕士45岁博士50岁' (26,568,690,617)\n16 link '' (731,568,972,643)\n17 StaticText '时间：2022-07-20 17:58' (26,624,405,641)\n18 StaticText '兵马俑手指在美被折断盗走' (26,674,549,698)\n19 link '' (731,674,972,750)\n20 StaticText '时间：2022-07-20 17:03' (26,731,405,748)\n21 StaticText '凤凰周刊：如果不靠高考，你该如何体面地出人头..' (26,781,679,831)\n22 link '' (731,781,972,857)\n23 StaticText '时间：2022-07-20 17:03' (26,838,405,854)\n24 StaticText '王中磊夫妇为儿子庆生 威廉弟弟长高了许多' (26,887,692,937)\n25 link '' (731,887,972,963)\n26 StaticText '时间：2022-07-20 16:16' (26,944,405,961)"
    }
  ],
  "unnormalized_box": [
    [
      30,
      36,
      828,
      162
    ],
    [
      855,
      36,
      1137,
      228
    ],
    [
      30,
      180,
      474,
      22
  ... (truncated)

Usage

import json, os, zipfile
from PIL import Image
from huggingface_hub import hf_hub_download

repo = "HongxinLi/UIPro-WebUI-Data-v1"
samples = json.load(open(hf_hub_download(repo, "WebUI_scale1000_488k.json", repo_type="dataset")))

images_zip = hf_hub_download(repo, "WebUI_scale1000_488k_images.zip", repo_type="dataset")
with zipfile.ZipFile(images_zip) as zf:
    zf.extractall("images/")

s = samples[0]
print(s["conversations"])
img = Image.open(os.path.join("images", s["image"]))   # screenshot for this sample
print("image size:", img.size)

About UIPro

UIPro is a generalist GUI agent trained on 20.6M understanding tasks across 13 task types, followed by agent continued fine-tuning. See the project repository for the full data pipeline, training recipes and evaluation scripts: https://github.com/ZJULiHongxin/UIPro

License

Released under CC BY-NC 4.0 (non-commercial research use). The underlying screenshots and annotations remain subject to the terms of their original source, WebUI.

Citation

@inproceedings{uipro2025,
  title     = {UIPro: A Generalist GUI Agent},
  author    = {Li, Hongxin and others},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  year      = {2025}
}