Image Agents
Dense Captioning Agent
Image Agents
Dense Captioning Agent
The DenseCaptioningAgent generates detailed descriptions of images.
Initialization
Parameters
The DenseCaptioningAgent is initialized with 1 optional argument:
model
MultimodalLLM
requiredThe selected model. All supported MultimodalLLM models can be found below:
Example
Here is an example of the DenseCaptioningAgent designed for a Workflow to detect if workers are wearing personal protective equipment (PPE).
example.py