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