SmolVLM2

Class: SmolVLM2BlockV1

Source: inference.core.workflows.core_steps.models.foundation.smolvlm.v1.SmolVLM2BlockV1

This workflow block runs SmolVLM2, a multimodal vision-language model. You can ask questions about images -- including documents and photos -- and get answers in natural language.

Type identifier

Use the following identifier in step "type" field: roboflow_core/smolvlm2@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 SmolVLM2. Otherwise it will just be None.	❌
model_version	str	The SmolVLM2 model to be used for inference..	✅

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Available Connections

Compatible Blocks

Check what blocks you can connect to SmolVLM2 in version v1.

• inputs: Instance Segmentation Model, Heatmap Visualization, Background Subtraction, Ellipse Visualization, Line Counter Visualization, Polygon Zone Visualization, Depth Estimation, SIFT Comparison, Camera Focus, QR Code Generator, Image Contours, Absolute Static Crop, Label Visualization, Morphological Transformation, Classification Label Visualization, Stability AI Image Generation, Multi-Label Classification Model, Polygon Visualization, Image Threshold, Text Display, SIFT, Triangle Visualization, Bounding Box Visualization, Blur Visualization, Image Preprocessing, Camera Calibration, Corner Visualization, Dot Visualization, Relative Static Crop, Image Slicer, Model Comparison Visualization, Object Detection Model, Icon Visualization, Contrast Equalization, Keypoint Detection Model, Reference Path Visualization, Pixelate Visualization, Halo Visualization, Background Color Visualization, Mask Visualization, Stability AI Outpainting, Circle Visualization, Halo Visualization, Image Blur, Dynamic Crop, Keypoint Visualization, Single-Label Classification Model, Perspective Correction, Image Convert Grayscale, Grid Visualization, Polygon Visualization, Stitch Images, Camera Focus, Stability AI Inpainting, Color Visualization, Trace Visualization, Crop Visualization, Image Slicer
• outputs: Detections Consensus

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds SmolVLM2 in version v1 has.

Bindings

• input

  • images (image): The image to infer on..
  • model_version (roboflow_model_id): The SmolVLM2 model to be used for inference..

• output

  • parsed_output (dictionary): Dictionary.

Example JSON definition of step SmolVLM2 in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/smolvlm2@v1",
    "images": "$inputs.image",
    "prompt": "What is in this image?",
    "model_version": "smolvlm2/smolvlm-2.2b-instruct"
}