Save 4 hours! We auto-setup your workflow! Free!

Drop your workflow.json — we handle every dependency, custom node, and model. Just open the link and run.

Auto-Setup Workflow Json (Free) Now!
ComfyUI > Nodes > MaskVidExperiments > MVEx Subject Crop

ComfyUI Node: MVEx Subject Crop

Class Name

MVEx_SubjectCrop

Category
MaskVidExperiments
Author
drozbay (Account age: 3838days)
Extension
MaskVidExperiments
Latest Updated
2026-08-20
Github Stars
0.09K

How to Install MaskVidExperiments

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

MVEx Subject Crop Description

Node crops masked subject region from video frames for consistent tensor stacking, stabilizing against jitter for smooth tracking.

MVEx Subject Crop:

The MVEx_SubjectCrop node is designed to crop a region around a masked subject from each frame of a video, ensuring that the entire batch of frames can be stacked into a single tensor. This node is particularly useful for maintaining consistency across frames, as it selects the position, size, and shape of the crop based on the entire video clip. This approach helps to stabilize the crop against mask jitter and ensures that it only follows sustained motion, rather than reacting to every minor movement. By doing so, it provides a smooth and coherent cropping experience, which is essential for tasks that require precise and consistent subject tracking across multiple frames.

MVEx Subject Crop Input Parameters:

mode

The mode parameter determines the complexity and behavior of the cropping operation. It offers three options: combined, tracked, and zoomed. The combined mode creates a single static crop with padding around the subject's entire movement path, ensuring that the subject remains within the frame throughout its travel. The tracked mode maintains a constant-size crop that remains stationary until the subject is about to exit the frame, at which point it moves minimally to keep the subject in view. The zoomed mode not only tracks the subject's position but also adjusts the crop size according to the subject's size, resampling each crop to a fixed output resolution. This parameter allows you to choose the level of dynamism and adaptability in the cropping process, depending on the specific requirements of your project.

MVEx Subject Crop Output Parameters:

CroppedFrames

The CroppedFrames output parameter provides the resulting frames after the cropping operation has been applied. Each frame is cropped according to the selected mode, ensuring that the subject is consistently framed across the entire video clip. This output is crucial for further processing or analysis, as it delivers a sequence of frames where the subject is prominently featured and stabilized, facilitating tasks such as video editing, analysis, or machine learning applications.

MVEx Subject Crop Usage Tips:

  • To achieve a stable crop that minimizes unnecessary movement, use the combined mode, which provides a static crop with padding around the subject's entire travel path.
  • For dynamic scenes where the subject moves significantly, consider using the tracked or zoomed modes to ensure the subject remains in view without abrupt changes in the crop position or size.

MVEx Subject Crop Common Errors and Solutions:

Error: "Invalid mask input"

  • Explanation: This error occurs when the mask provided does not match the expected format or dimensions required by the node.
  • Solution: Ensure that the mask input is correctly formatted and matches the dimensions of the video frames being processed.

Error: "Crop size exceeds frame dimensions"

  • Explanation: This error indicates that the calculated crop size is larger than the original frame dimensions.
  • Solution: Adjust the crop settings or mode to ensure that the crop size remains within the bounds of the original frame dimensions.

MVEx Subject Crop Related Nodes

Go back to the extension to check out more related nodes.
MaskVidExperiments
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.

MVEx Subject Crop