ComfyUI > Nodes > ComfyUI-WanVideoWrapper > WanVideoSampler v2 Extra Args

ComfyUI Node: WanVideoSampler v2 Extra Args

Class Name

WanVideoSamplerExtraArgs

Category
WanVideoWrapper
Author
kijai (Account age: 2871days)
Extension
ComfyUI-WanVideoWrapper
Latest Updated
2026-05-05
Github Stars
6.41K

How to Install ComfyUI-WanVideoWrapper

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

WanVideoSampler v2 Extra Args Description

Enhance WanVideo sampling with customizable parameters for optimized video generation.

WanVideoSampler v2 Extra Args:

The WanVideoSamplerExtraArgs node is designed to enhance the functionality of the WanVideo sampling process by providing additional, customizable parameters that can be adjusted to fine-tune the video generation process. This node allows you to specify a range of optional arguments that can influence the behavior of the video sampler, offering greater control over the output without requiring a deep technical understanding. By utilizing these extra arguments, you can optimize the video generation process, potentially improving performance and achieving desired effects more efficiently. The node's primary function is to process these additional arguments and integrate them into the video sampling workflow, thereby expanding the capabilities of the WanVideo system.

WanVideoSampler v2 Extra Args Input Parameters:

riflex_freq_index

The riflex_freq_index parameter is an integer that determines the frequency index for RIFLEX. It is disabled when set to 0, with a default value of 6. This parameter allows for new frames to be generated without looping, providing flexibility in the video generation process. The value can range from 0 to 1000, with a step of 1, allowing for precise control over the frequency index.

feta_args

The feta_args parameter is a placeholder for FETAARGS, which are additional arguments that can be used to customize the video sampling process. These arguments provide further options for fine-tuning the behavior of the sampler.

context_options

The context_options parameter represents WANVIDCONTEXT, which allows you to specify context-related options that can influence the video generation process. This parameter provides a way to incorporate contextual information into the sampling workflow.

cache_args

The cache_args parameter is associated with CACHEARGS, which are arguments related to caching mechanisms. These arguments can be used to optimize the performance of the video sampler by managing how data is cached during the process.

slg_args

The slg_args parameter corresponds to SLGARGS, which are additional arguments that can be used to adjust the behavior of the video sampler. These arguments provide further customization options for the sampling process.

rope_function

The rope_function parameter allows you to select a specific RoPE implementation. The default option is "comfy," which does not use complex numbers and can be compiled for faster performance when using torch.compile. The chunked version of this implementation reduces peak VRAM usage when not using torch.compile, offering a balance between speed and resource efficiency.

loop_args

The loop_args parameter represents LOOPARGS, which are arguments related to looping behavior in the video generation process. These arguments provide control over how loops are handled during sampling.

experimental_args

The experimental_args parameter is associated with EXPERIMENTALARGS, which are experimental arguments that can be used to test new features or behaviors in the video sampler. These arguments offer a way to explore cutting-edge options in the sampling process.

unianimate_poses

The unianimate_poses parameter corresponds to UNIANIMATE_POSE, which allows you to specify poses for unianimate functionality. This parameter provides a way to incorporate pose information into the video generation process.

fantasytalking_embeds

The fantasytalking_embeds parameter represents FANTASYTALKING_EMBEDS, which are embeddings related to fantasy talking features. These embeddings can be used to enhance the video sampling process with fantasy talking elements.

uni3c_embeds

The uni3c_embeds parameter corresponds to UNI3C_EMBEDS, which are embeddings related to the UNI3C feature. These embeddings provide additional customization options for the video generation process.

multitalk_embeds

The multitalk_embeds parameter represents MULTITALK_EMBEDS, which are embeddings related to multitalk functionality. These embeddings can be used to incorporate multitalk elements into the video sampling process.

WanVideoSampler v2 Extra Args Output Parameters:

extra_args

The extra_args output parameter is of type WANVIDSAMPLEREXTRAARGS and represents the processed extra arguments that have been integrated into the video sampling workflow. This output is crucial as it encapsulates all the additional parameters specified, allowing them to be utilized effectively in the video generation process. By providing these extra arguments, the node enhances the flexibility and capability of the WanVideo system, enabling more tailored and optimized video outputs.

WanVideoSampler v2 Extra Args Usage Tips:

  • Experiment with the riflex_freq_index to find the optimal frequency index for your specific video generation needs, especially if you want to generate new frames without looping.
  • Utilize the rope_function parameter to select the "comfy" implementation for faster performance, particularly if you are using torch.compile to optimize your workflow.

WanVideoSampler v2 Extra Args Common Errors and Solutions:

MissingParameterError

  • Explanation: This error occurs when a required parameter is not provided to the node.
  • Solution: Ensure that all necessary parameters are specified when configuring the node. Double-check the input parameters to confirm that none are missing.

InvalidParameterValueError

  • Explanation: This error is raised when a parameter value is outside the acceptable range or not of the expected type.
  • Solution: Verify that all parameter values are within the specified ranges and of the correct type. Adjust any values that do not meet these criteria.

UnsupportedRoPEFunctionError

  • Explanation: This error occurs if an unsupported RoPE function is selected.
  • Solution: Ensure that the rope_function parameter is set to a supported option, such as "comfy," to avoid this error.

WanVideoSampler v2 Extra Args Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI-WanVideoWrapper
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.

WanVideoSampler v2 Extra Args