WanContextWindowsManual - ComfyUI Built-in Node Documentation

The WAN Context Windows (Manual) node allows you to manually configure context windows for WAN-like models with 2-dimensional processing. It applies custom context window settings during sampling by specifying the window length, overlap, scheduling method, and fusion technique. This gives you precise control over how the model processes information across different context regions.

Inputs

Parameter	Description	Data Type	Required	Range
`model`	The model to apply context windows to during sampling.	MODEL	Yes	-
`context_length`	The length of the context window (default: 81).	INT	Yes	1 to 1048576
`context_overlap`	The overlap of the context window (default: 30).	INT	Yes	0 to 1048576
`context_schedule`	The stride of the context window.	COMBO	Yes	`"static_standard"` `"uniform_standard"` `"uniform_looped"` `"batched"`
`context_stride`	The stride of the context window; only applicable to uniform schedules (default: 1).	INT	Yes	1 to 1048576
`closed_loop`	Whether to close the context window loop; only applicable to looped schedules (default: False).	BOOLEAN	Yes	-
`fuse_method`	The method to use to fuse the context windows (default: “pyramid”).	COMBO	Yes	`"pyramid"` `"gaussian"` `"average"` `"overlap"`
`freenoise`	Whether to apply FreeNoise noise shuffling, improves window blending (default: False).	BOOLEAN	Yes	-

Note: The context_stride parameter only affects uniform schedules, and closed_loop only applies to looped schedules. The context length and overlap values are automatically adjusted to ensure minimum valid values during processing. The fuse_method parameter now includes additional options beyond just “pyramid”.

Outputs

Output Name	Description	Data Type
`model`	The model with the applied context window configuration.	MODEL

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 941a12b45162fd97c21e071e8170ba7047487c0f312f20dac572ef1bc751c64d

​Inputs

​Outputs

Inputs

Outputs