Wiro AIActive
kristaller486 / dots.ocr-1.5
dots.ocr-1.5
dots.ocr-1.5 is a 3B-parameter multimodal model composed of a 1.2B vision encoder and a 1.7B language model. Designed for universal accessibility, it possesses the capability to recognize virtually any human script.
Fast InferenceBf16
Model ID
dots.ocr-1.5
Provider
kristaller486
Updated
1776084021
wiro playground—kristaller486/dots.ocr-1.5
Updated 1776084021
# dots.ocr-1.5
3B parameter multimodal OCR model. Performs layout analysis, text extraction, and structural conversion from images and PDF files.
## Parameters
- `files` (required) — Input file path (.pdf, .jpg, .jpeg, .png, .webp, .bmp, .heic, .tiff, .avif)
- `prompt_mode` — Prompt mode (default: `prompt_layout_all_en`)
- `prompt` — Custom prompt, overrides prompt_mode when provided
- `min_pixels` — Minimum pixel count for image resizing
- `max_pixels` — Maximum pixel count for image resizing
## Prompt Modes
- `prompt_layout_all_en` — Layout analysis + text extraction
- `prompt_layout_only_en` — Layout detection only (bbox + category)
- `prompt_ocr` — Text extraction only
- `prompt_web_parsing` — Web page parsing
- `prompt_scene_spotting` — Scene text detection
## Outputs
- `image.jpg` / `pdf_page_N.jpg` — Layout visualization
- `image.txt` / `pdf_page_N.txt` — TextExample prompts
Great starting points for dots.ocr-1.5.
Please output the layout information from this PDF image, including each layout's bbox and its category. The bbox should be in the format [x1, y1, x2, y2]. The layout categories for the PDF document include ['Caption', 'Footnote', 'Formula', 'List-item', 'Page-footer', 'Page-header', 'Picture', 'Section-header', 'Table', 'Text', 'Title']. Do not output the corresponding text. The layout result should be in JSON format.Wiro AI
Extract the text content from this image.Wiro AI
Parsing the layout info of this webpage image with format json:Wiro AI
Detect and recognize the text in the image.Wiro AI
API quick start
Run dots.ocr-1.5 with a single API call.
POST https://api.wiro.ai/v1/Run/kristaller486/dots.ocr-1.5
{
"prompt": "Please output the layout information from…",
"promptMode": "prompt_layout_all_en",
"inputDocumentMultiple": "https://your-cdn.com/input.png",
"minPixels": 3136
}