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