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