SmolVLM2

Run SmolVLM2 on an image.

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@v1 to add the block as a 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.

Runtime compatibility

hard - runtime self_hosted_cpu; execution local : Requires a GPU; run_locally() loads a model that needs CUDA.

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds SmolVLM2 in version v1 has.

Input and output 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

{
	    "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"
	}