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