Moondream2

Run Moondream2 on an image.

This workflow block runs Moondream2, a multimodal vision-language model. You can use this block to run zero-shot object detection.

Type identifier

Use the following identifier in step "type" field: roboflow_core/moondream2@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 Moondream2..	✅
model_version	str	The Moondream2 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 Moondream2 in version v1 has.

Input and output bindings

• input

  • images (image): The image to infer on..

  • prompt (string): Optional text prompt to provide additional context to Moondream2..

  • model_version (roboflow_model_id): The Moondream2 model to be used for inference..

• output

  • predictions (object_detection_prediction): Prediction with detected bounding boxes in form of sv.Detections(...) object.

Example JSON definition

{
	    "name": "<your_step_name_here>",
	    "type": "roboflow_core/moondream2@v1",
	    "images": "$inputs.image",
	    "prompt": "my prompt",
	    "model_version": "moondream2/moondream2_2b_jul24"
	}