ComfyUI > Nodes > ComfyUI-Segmentation-Agent > SAM3 Character Agent (Local)

ComfyUI Node: SAM3 Character Agent (Local)

Class Name

SAM3Agent

Category
SAM3-Agent
Author
adambarbato (Account age: 4567days)
Extension
ComfyUI-Segmentation-Agent
Latest Updated
2026-02-05
Github Stars
0.03K

How to Install ComfyUI-Segmentation-Agent

Install this extension via the ComfyUI Manager by searching for ComfyUI-Segmentation-Agent
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI-Segmentation-Agent in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

SAM3 Character Agent (Local) Description

SAM3Agent node segments characters in images using LLMs based on user-provided descriptions.

SAM3 Character Agent (Local):

The SAM3Agent node is designed to intelligently segment specific characters within an image using a Large Language Model (LLM). This node leverages advanced machine learning techniques to identify and isolate characters based on textual descriptions provided by the user. By integrating character descriptions with image data, SAM3Agent can effectively discern and highlight the desired elements within a visual scene. This capability is particularly beneficial for AI artists and designers who need precise character segmentation for creative projects, allowing for enhanced control over image manipulation and composition. The node's primary goal is to streamline the process of character segmentation, making it more intuitive and accessible without requiring extensive technical expertise.

SAM3 Character Agent (Local) Input Parameters:

image

This parameter expects an image input, which serves as the canvas for character segmentation. The image is analyzed by the node to identify and isolate characters based on the provided description.

character_description

This is a string parameter where you can describe the character you want to segment. It supports multiline input and defaults to "A person with brown hair." The description guides the LLM in identifying the specific character traits to focus on during segmentation.

llm_model

This parameter allows you to select the LLM model to be used for processing. The choice of model can affect the accuracy and efficiency of the segmentation process, as different models may have varying capabilities in understanding and processing character descriptions.

mmproj_model

This parameter specifies the model used for managing the segmentation project. It is crucial for ensuring that the segmentation process aligns with the desired project specifications and outputs.

max_iterations

This integer parameter controls the maximum number of iterations the node will perform during the segmentation process. It ranges from 1 to 20, with a default value of 5. Increasing the number of iterations can improve segmentation accuracy but may also increase processing time.

confidence_threshold

This float parameter sets the confidence level required for a segment to be considered valid. It ranges from 0.1 to 1.0, with a default value of 0.5. A higher threshold ensures that only segments with high confidence are accepted, potentially reducing false positives.

SAM3 Character Agent (Local) Output Parameters:

mask

The mask output is a binary representation of the segmented character within the image. It highlights the areas identified as part of the character, allowing for further manipulation or analysis.

debug_images

This output provides a visual representation of the segmentation process, showing intermediate results and aiding in debugging and refinement. It helps users understand how the node arrived at the final segmentation.

SAM3 Character Agent (Local) Usage Tips:

  • Ensure that the character description is as detailed as possible to improve segmentation accuracy.
  • Experiment with different LLM models to find the one that best suits your specific segmentation needs.
  • Adjust the confidence threshold to balance between precision and recall, depending on whether you prioritize accuracy or completeness.

SAM3 Character Agent (Local) Common Errors and Solutions:

Empty API response, retrying...

  • Explanation: This error occurs when the node fails to receive a response from the API during the segmentation process.
  • Solution: Check your internet connection and ensure that the API key is valid and correctly configured. Retry the operation after verifying these settings.

Interrupted by user

  • Explanation: This message indicates that the segmentation process was manually interrupted by the user.
  • Solution: If this was unintentional, ensure that no manual interruptions occur during processing. If needed, restart the process to continue segmentation.

SAM3 Character Agent (Local) Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI-Segmentation-Agent
RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

SAM3 Character Agent (Local)