Read images and videos with Qwen vision models.
What it does
Extracts descriptions, answers, and text from images and videos using Qwen vision models.
When to use it
Use for image or video analysis, OCR, chart and table reading, visual reasoning, screenshot understanding, or multi-image comparison.
How to use it
Give it images or videos, optionally with a question; it returns analysis, visual reasoning, or extracted text.
What you provide
- Your files
Uses
DA
Good to know
- cannot be undone: QwenCloud
- acts without asking
Latest review
What you need · 4
The default script workflow requires Python 3.9 or newer and uses only the standard library.
Requires QwenCloud API access through a standard PAYG key or a Token Plan key; Coding Plan keys cannot make direct API calls.
Access · 6
This skill
QwenCloud
Write
Sends media to QwenCloud (irreversible)
DashScope temp storage
Write
Uploads large local media