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