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:
Icon Visualization,Line Counter Visualization,Stability AI Outpainting,Image Contours,Image Slicer,Pixelate Visualization,Keypoint Detection Model,Image Preprocessing,Polygon Zone Visualization,Color Visualization,Reference Path Visualization,Object Detection Model,Blur Visualization,Multi-Label Classification Model,Background Subtraction,Text Display,Ellipse Visualization,Polygon Visualization,Single-Label Classification Model,Relative Static Crop,Stability AI Image Generation,Perspective Correction,Model Comparison Visualization,Bounding Box Visualization,Trace Visualization,Depth Estimation,Camera Focus,Classification Label Visualization,Image Slicer,Absolute Static Crop,Image Blur,Stability AI Inpainting,Object Detection Model,Polygon Visualization,Image Convert Grayscale,Instance Segmentation Model,SIFT,Single-Label Classification Model,Semantic Segmentation Model,Label Visualization,Image Threshold,Corner Visualization,Grid Visualization,Dynamic Crop,Contrast Equalization,Heatmap Visualization,SIFT Comparison,Stitch Images,Triangle Visualization,Morphological Transformation,Keypoint Visualization,QR Code Generator,Halo Visualization,Circle Visualization,Camera Focus,Halo Visualization,Mask Visualization,Instance Segmentation Model,Crop Visualization,Morphological Transformation,Camera Calibration,Contrast Enhancement,Multi-Label Classification Model,Background Color Visualization,Dot Visualization,Keypoint Detection Model,Semantic Segmentation Model - outputs:
Detections Consensus,SAM 3,Per-Class Confidence Filter
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"
}