ComfyUI > Nodes > comfyUI-LongLook > Wan Motion Scale (Experimental)

ComfyUI Node: Wan Motion Scale (Experimental)

Class Name

WanMotionScale

Category
video/wan
Author
shootthesound (Account age: 1325days)
Extension
comfyUI-LongLook
Latest Updated
2025-12-30
Github Stars
0.15K

How to Install comfyUI-LongLook

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

Wan Motion Scale (Experimental) Description

Enhances video motion by scaling temporal embeddings for customizable speed control.

Wan Motion Scale (Experimental):

WanMotionScale is a node designed to enhance the motion dynamics in video generation using ComfyUI's framework. It achieves this by scaling temporal position embeddings, which effectively alters the perceived speed of motion in generated videos. By manipulating these embeddings, the node makes the model interpret frames as being spaced further apart in time, allowing for the creation of longer videos with more pronounced motion coverage. This is particularly useful when combined with RIFE interpolation, which fills in the gaps between frames, resulting in smoother and more continuous motion sequences. The primary goal of WanMotionScale is to provide users with the ability to control and customize the motion speed in their video projects, making it a valuable tool for AI artists looking to experiment with temporal dynamics in their creations.

Wan Motion Scale (Experimental) Input Parameters:

scale_t

The scale_t parameter controls the temporal scale of the motion in the video. A value greater than 1 results in faster motion, while a value less than 1 slows down the motion. This parameter allows you to adjust the speed of the motion to suit your creative needs. The default value is 1.0, with a minimum of -10.0 and a maximum of 10.0, and it can be adjusted in increments of 0.05.

scale_y

The scale_y parameter adjusts the height or Y position scale of the video frames. This parameter can be used to manipulate the vertical positioning of the motion, providing additional control over the visual dynamics of the video. The default value is 1.0, with a range from -10.0 to 10.0, and it can be modified in steps of 0.05.

scale_x

The scale_x parameter is responsible for scaling the width or X position of the video frames. Similar to scale_y, this parameter allows you to control the horizontal positioning of the motion, offering further customization of the video's visual elements. The default value is 1.0, with a minimum of -10.0 and a maximum of 10.0, adjustable in increments of 0.05.

theta

The theta parameter is an experimental feature that controls the RoPE base frequency, which affects the temporal coherence of the frames. A higher theta value (e.g., 20000-50000) results in a longer effective context, making frames appear closer together and potentially improving coherence in longer video sequences. Conversely, a lower theta value (e.g., 2000-5000) makes frames seem further apart temporally, which can increase motion intensity but may also lead to instability. The default value is 10000.0, with a range from 100.0 to 1000000.0, and it can be adjusted in steps of 100.0.

Wan Motion Scale (Experimental) Output Parameters:

None

The context does not provide specific output parameters for WanMotionScale. Typically, the output would be the modified video frames with adjusted motion dynamics based on the input parameters.

Wan Motion Scale (Experimental) Usage Tips:

  • Experiment with scale_t to find the optimal motion speed for your video. Start with small adjustments to see how it affects the overall motion dynamics.
  • Use theta cautiously, as it is an experimental feature. Begin with minor changes to understand its impact on frame coherence and motion intensity.
  • Combine WanMotionScale with RIFE interpolation to achieve smoother transitions and fill in gaps between frames for a more continuous video output.

Wan Motion Scale (Experimental) Common Errors and Solutions:

Unexpected motion artifacts

  • Explanation: This may occur if the theta parameter is set too high or too low, causing instability in the motion dynamics.
  • Solution: Adjust the theta parameter gradually and observe the changes. Start with values closer to the default and make incremental changes.

Video output not as expected

  • Explanation: Incorrect settings in scale_t, scale_x, or scale_y can lead to unexpected motion speeds or positioning.
  • Solution: Double-check the input parameters and ensure they are set within the recommended ranges. Adjust them incrementally to achieve the desired effect.

Wan Motion Scale (Experimental) Related Nodes

Go back to the extension to check out more related nodes.
comfyUI-LongLook
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.