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