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

ComfyUI Node: Wan Motion Scale Advanced (Experimental)

Class Name

WanMotionScaleAdvanced

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 Advanced (Experimental) Description

Enhances video motion scaling by adjusting RoPE theta for varied speed and coherence.

Wan Motion Scale Advanced (Experimental):

WanMotionScaleAdvanced is an experimental node designed to enhance motion scaling in video generation using the Wan model. It extends the basic motion scaling capabilities by introducing control over the RoPE (Rotary Position Embedding) theta parameter, which is crucial for adjusting the base frequency of position embeddings. This node allows you to manipulate how frames are perceived in terms of temporal distance, offering the ability to create videos with varying motion speeds and coherence. By adjusting the theta parameter, you can influence the effective context length, making frames appear closer or further apart, which can be particularly useful for generating longer videos or increasing motion intensity. However, due to its experimental nature, modifying the theta parameter can lead to unexpected results, so it should be used with caution.

Wan Motion Scale Advanced (Experimental) Input Parameters:

scale_t

This parameter controls the temporal scale of the motion. A value greater than 1 results in faster motion, while a value less than 1 slows down the motion. It functions similarly to the basic Motion Scale, allowing you to adjust the perceived speed of the video. The default value is 1.0, with a range from -10.0 to 10.0, and adjustments can be made in increments of 0.05.

scale_y

The scale_y parameter adjusts the height or Y position scale of the motion. It allows you to manipulate the vertical positioning of frames within the video. The default value is 1.0, with a range from -10.0 to 10.0, and changes can be made in steps of 0.05.

scale_x

This parameter controls the width or X position scale of the motion, enabling you to adjust the horizontal positioning of frames. Like scale_y, it has a default value of 1.0, with a range from -10.0 to 10.0, and can be modified in increments of 0.05.

theta

Theta is a critical parameter that influences the RoPE base frequency, which affects the temporal coherence of frames. The default value is 10000.0, which corresponds to the training settings of the Wan model. Increasing theta (20000-50000) results in a longer effective context, making frames appear closer together and potentially improving coherence in videos with more than 81 frames. Conversely, decreasing theta (2000-5000) makes frames seem further apart temporally, which can enhance motion intensity but may also cause instability. The range for theta is from 100.0 to 1000000.0, with adjustments possible in steps of 100.0. This parameter is experimental, and small changes are recommended to start with.

Wan Motion Scale Advanced (Experimental) Output Parameters:

control_video_out

This output parameter represents the processed video output after applying the motion scaling and theta adjustments. It reflects the changes made to the temporal and spatial positioning of frames, providing a video that aligns with the specified input parameters. The output is crucial for evaluating the effectiveness of the adjustments and ensuring the desired motion effects are achieved.

Wan Motion Scale Advanced (Experimental) Usage Tips:

  • Start with small adjustments to the theta parameter to understand its impact on your video generation, as it can significantly alter the model's behavior.
  • Use scale_t to fine-tune the speed of motion in your videos, and consider using interpolation techniques like RIFE to fill gaps and create smoother transitions.

Wan Motion Scale Advanced (Experimental) Common Errors and Solutions:

Unexpected Results with Theta Adjustments

  • Explanation: Modifying the theta parameter can lead to unexpected changes in video coherence and motion intensity.
  • Solution: Begin with small changes to the theta value and gradually adjust it while observing the effects on your video output.

Motion Instability

  • Explanation: Lowering the theta value too much can cause frames to appear too far apart, leading to instability in motion.
  • Solution: Increase the theta value incrementally to find a balance that maintains motion intensity without sacrificing stability.

Wan Motion Scale Advanced (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.

Wan Motion Scale Advanced (Experimental)