Input Image
ID: 01
Click or drop image here
—
Model Selector
ID: 02
QWEN3-VL · 2B
Qwen3-VL-2B-Instruct — dedicated vision-language model by Alibaba Cloud. Strong spatial grounding, OCR & instruction-following.
Qwen3-VL-2B-Instruct — dedicated vision-language model by Alibaba Cloud. Strong spatial grounding, OCR & instruction-following.
Task Config
ID: 03
Output Stream
ID: 04
Results will stream here...
View Grounding
ID: 05
Active for Point / Detect tasks.
Run inference to visualise.
Run inference to visualise.