ComfyUI > Nodes > SAMURAI Nodes for ComfyUI > SAMURAI Points Input

ComfyUI Node: SAMURAI Points Input

Class Name

SAMURAIPointsInputNode

Category
SAMURAI
Author
takemetosiberia (Account age: 642days)
Extension
SAMURAI Nodes for ComfyUI
Latest Updated
2024-12-01
Github Stars
0.03K

How to Install SAMURAI Nodes for ComfyUI

Install this extension via the ComfyUI Manager by searching for SAMURAI Nodes for ComfyUI
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter SAMURAI Nodes for ComfyUI 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

SAMURAI Points Input Description

Facilitates selection of points for object segmentation in video frames, enhancing accuracy and enabling precise segmentation in subsequent nodes.

SAMURAI Points Input:

The SAMURAIPointsInputNode is designed to facilitate the selection of specific points of interest within the first frame of a video sequence, which is crucial for object segmentation tasks. This node is particularly beneficial for users who need to manually define areas of interest and background in video frames, allowing for precise segmentation of objects. By enabling the selection of positive and negative points, the node helps in distinguishing between the object and the background, thus enhancing the accuracy of segmentation. The node's primary function is to capture these points and their corresponding labels, which are then used by subsequent nodes, such as the SAMURAI Refine Node, to perform detailed segmentation. This capability is essential for applications that require high precision in object tracking and segmentation across video sequences.

SAMURAI Points Input Input Parameters:

image

The image parameter is a required input that represents the sequence of video frames to be processed. It serves as the primary data source from which points of interest are selected. This parameter is crucial as it provides the visual content that the node will analyze to identify and label points for segmentation.

start_frame

The start_frame parameter specifies the frame number from which the point selection process should begin. It is an integer value with a default of 0, meaning the process starts from the first frame by default. This parameter allows users to control the starting point of the analysis, which can be useful in cases where the object of interest appears later in the video sequence.

refresh_input

The refresh_input parameter is an integer that acts as a trigger to refresh the points selection. By changing its value, users can reset the selection process, allowing for new points to be chosen. This is particularly useful when adjustments are needed after an initial selection, ensuring that the most accurate points are used for segmentation.

SAMURAI Points Input Output Parameters:

POINTS

The POINTS output provides the coordinates of the selected points within the video frame. These coordinates are essential for defining the areas of interest that will be used in the segmentation process. The output is typically in the form of an array, which can be easily utilized by subsequent nodes for further processing.

LABELS

The LABELS output contains the labels associated with each selected point, indicating whether they are positive (object) or negative (background). This labeling is crucial for distinguishing between the object and the background, thereby aiding in accurate segmentation. The labels are usually represented as an array of integers.

START_FRAME

The START_FRAME output simply returns the frame number from which the point selection process began. This information is useful for tracking the progress of the segmentation process and ensuring that the correct frames are being analyzed.

SAMURAI Points Input Usage Tips:

  • Ensure that the video input is correctly connected to the node to facilitate accurate point selection.
  • Use the start_frame parameter to skip to the relevant part of the video where the object of interest appears, saving time and computational resources.
  • Regularly adjust the refresh_input parameter to refine point selection, especially if the initial selection does not yield satisfactory results.

SAMURAI Points Input Common Errors and Solutions:

Error: "Invalid frame number"

  • Explanation: This error occurs when the start_frame parameter is set to a value that exceeds the total number of frames in the video sequence.
  • Solution: Ensure that the start_frame value is within the range of available frames in the video. Adjust the parameter to a valid frame number.

Error: "No points selected"

  • Explanation: This error indicates that no points have been selected for segmentation, which is necessary for the node to function.
  • Solution: Use the left and right mouse clicks to add positive and negative points, respectively, ensuring that both object and background areas are defined.

Error: "Refresh input not triggered"

  • Explanation: This error suggests that the refresh_input parameter has not been changed, preventing the selection of new points.
  • Solution: Modify the refresh_input value to trigger a refresh of the point selection process, allowing for new points to be chosen.

SAMURAI Points Input Related Nodes

Go back to the extension to check out more related nodes.
SAMURAI Nodes for ComfyUI
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 Playground, enabling artists to harness the latest AI tools to create incredible art.