Qwen3-VL¶
Deprecated
Use the unified Qwen-VL block (roboflow_core/qwen_vlm@v1), which exposes Qwen 3 VL alongside other Qwen variants and the OpenRouter passthrough.
Class: Qwen3VLBlockV1
Source: inference.core.workflows.core_steps.models.foundation.qwen3vl.v1.Qwen3VLBlockV1
This workflow block runs Qwen3-VL—a vision language model that accepts an image and an optional text prompt—and returns a text answer based on a conversation template.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/qwen3vl@v1to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
prompt |
str |
Optional text prompt to provide additional context to Qwen3-VL. Otherwise it will just be a default one, which may affect the desired model behavior.. | ❌ |
model_version |
str |
The Qwen3-VL model to be used for inference.. | ✅ |
system_prompt |
str |
Optional system prompt to provide additional context to Qwen3-VL.. | ❌ |
The Refs column marks possibility to parametrise the property with dynamic values available
in workflow runtime. See Bindings for more info.
Runtime compatibility¶
-
hard— runtimeself_hosted_cpu; executionlocal - Requires a GPU; run_locally() loads a model that needs CUDA.
Available Connections¶
Compatible Blocks
Check what blocks you can connect to Qwen3-VL in version v1.
- inputs:
Polygon Visualization,Polygon Visualization,SIFT,Circle Visualization,Classification Label Visualization,Line Counter Visualization,Stability AI Image Generation,Semantic Segmentation Model,Relative Static Crop,Instance Segmentation Model,Image Blur,Grid Visualization,Reference Path Visualization,Camera Focus,Image Preprocessing,Keypoint Visualization,Instance Segmentation Model,Icon Visualization,Color Visualization,Halo Visualization,Triangle Visualization,Object Detection Model,Dot Visualization,QR Code Generator,Contrast Enhancement,Absolute Static Crop,Dynamic Crop,Stability AI Inpainting,Image Slicer,Background Subtraction,Label Visualization,Background Color Visualization,Bounding Box Visualization,Polygon Zone Visualization,Stability AI Outpainting,Multi-Label Classification Model,Crop Visualization,Multi-Label Classification Model,Pixelate Visualization,Image Convert Grayscale,Mask Visualization,Halo Visualization,Heatmap Visualization,Image Slicer,Semantic Segmentation Model,Perspective Correction,Stitch Images,Text Display,Morphological Transformation,Morphological Transformation,Single-Label Classification Model,Image Threshold,Single-Label Classification Model,Blur Visualization,Depth Estimation,Trace Visualization,Camera Focus,Contrast Equalization,Camera Calibration,Corner Visualization,Ellipse Visualization,Model Comparison Visualization,SIFT Comparison,Keypoint Detection Model,Keypoint Detection Model,Image Contours,Object Detection Model,Instance Segmentation Model - outputs:
Per-Class Confidence Filter,PLC EthernetIP,Detections Consensus,Microsoft SQL Server Sink,SAM 3,Roboflow Asset Library Attributes
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Qwen3-VL in version v1 has.
Bindings
-
input
images(image): The image to infer on..model_version(roboflow_model_id): The Qwen3-VL model to be used for inference..
-
output
parsed_output(dictionary): Dictionary.
Example JSON definition of step Qwen3-VL in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/qwen3vl@v1",
"images": "$inputs.image",
"prompt": "What is in this image?",
"model_version": "qwen3vl-2b-instruct",
"system_prompt": "You are a helpful assistant."
}