ComfyUI custom node pack for SAM3 (Segment Anything Model 3) - Meta's state-of-the-art image segmentation model. This extension enables text-prompt-based object segmentation directly within your ComfyUI workflows.

Overview

SAM3 is a powerful zero-shot segmentation model that can identify and segment objects in images using natural language prompts. This custom node pack brings SAM3's capabilities to ComfyUI, allowing you to:

Segment objects using text descriptions (e.g., "person", "car", "dog")
Filter results by confidence threshold
Control minimum object dimensions
Output individual masks for each detected object
Generate a combined mask of all detections
Visualize results with colored overlays, bounding boxes, and confidence scores

Quickstart

Install ComfyUI.
Install ComfyUI-Manager
Look up this extension in ComfyUI-Manager. If you are installing manually, clone this repository under ComfyUI/custom_nodes.
Install SAM3 dependencies (if not already installed):
```
pip install -r requirements.txt
```
Restart ComfyUI.

Features

SAM3 Segmentation Node

Inputs:

image - Input image to segment
prompt (STRING) - Text description of objects to segment (e.g., "person", "car", "building")
threshold (FLOAT, 0.0-1.0) - Minimum confidence score threshold for detections (default: 0.5)
min_width_pixels (INT) - Minimum bounding box width in pixels (default: 0)
min_height_pixels (INT) - Minimum bounding box height in pixels (default: 0)

Outputs:

segmented_image (IMAGE) - Visualization with colored mask overlays, bounding boxes, and confidence scores
masks (MASK) - Batch of individual binary masks, one for each detected object [B, H, W]
mask_combined (MASK) - Single merged mask containing all detected objects [1, H, W]

Example Use Cases:

Remove backgrounds by segmenting people or objects
Isolate specific elements in a scene for further processing
Create masks for inpainting workflows
Generate batch masks for multiple objects of the same type
Filter detections by size to focus on foreground/background objects

Develop

To install the dev dependencies and pre-commit (will run the ruff hook), do:

cd comfyui_sam3
pip install -e .[dev]
pre-commit install

The -e flag above will result in a "live" install, in the sense that any changes you make to your node extension will automatically be picked up the next time you run ComfyUI.

Publish to Github

Install Github Desktop or follow these instructions for ssh.

Create a Github repository that matches the directory name.
Push the files to Git

git add .
git commit -m "project scaffolding"
git push

Writing custom nodes

An example custom node is located in node.py. To learn more, read the docs.

Tests

This repo contains unit tests written in Pytest in the tests/ directory. It is recommended to unit test your custom node.

build-pipeline.yml will run pytest and linter on any open PRs
validate.yml will run node-diff to check for breaking changes

Publishing to Registry

If you wish to share this custom node with others in the community, you can publish it to the registry. We've already auto-populated some fields in pyproject.toml under tool.comfy, but please double-check that they are correct.

You need to make an account on https://registry.comfy.org and create an API key token.

Go to the registry. Login and create a publisher id (everything after the @ sign on your registry profile).
Add the publisher id into the pyproject.toml file.
Create an api key on the Registry for publishing from Github. Instructions.
Add it to your Github Repository Secrets as REGISTRY_ACCESS_TOKEN.

A Github action will run on every git push. You can also run the Github action manually. Full instructions here. Join our discord if you have any questions!