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