ContextWindowsManual - ComfyUI Built-in Node Documentation

The Context Windows (Manual) node allows you to manually configure context windows for models during sampling. It creates overlapping context segments with specified length, overlap, and scheduling patterns to process data in manageable chunks while maintaining continuity between segments. This node provides advanced options for controlling how context windows are applied, including noise shuffling, conditioning retention, and causal window fixes.

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: 16).	INT	No	1+
`context_overlap`	The overlap of the context window (default: 4).	INT	No	0+
`context_schedule`	The stride of the context window.	COMBO	No	`STATIC_STANDARD` `UNIFORM_STANDARD` `UNIFORM_LOOPED` `BATCHED`
`context_stride`	The stride of the context window; only applicable to uniform schedules (default: 1).	INT	No	1+
`closed_loop`	Whether to close the context window loop; only applicable to looped schedules (default: False).	BOOLEAN	No	-
`fuse_method`	The method to use to fuse the context windows (default: PYRAMID).	COMBO	No	`PYRAMID` `LIST_STATIC`
`dim`	The dimension to apply the context windows to (default: 0).	INT	No	0-5
`freenoise`	Whether to apply FreeNoise noise shuffling, improves window blending (default: False).	BOOLEAN	No	-
`cond_retain_index_list`	List of latent indices to retain in the conditioning tensors for each window, for example setting this to ‘0’ will use the initial start image for each window (default: "").	STRING	No	-
`split_conds_to_windows`	Whether to split multiple conditionings (created by ConditionCombine) to each window based on region index (default: False).	BOOLEAN	No	-
`causal_window_fix`	Whether to add a causal fix frame to non-0-indexed context windows (default: True).	BOOLEAN	No	-

Parameter Constraints:

context_stride is only used when uniform schedules are selected
closed_loop is only applicable to looped schedules
dim must be between 0 and 5 inclusive
cond_retain_index_list expects a comma-separated list of integer indices as a string (e.g., “0,1,2”)

Outputs

Output Name	Description	Data Type
`model`	The model with context windows applied during sampling.	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): 1351789e54e6b4013331014a49b98c6f8b79692ddabed7a64eeb7463cda03cc5

​Inputs

​Outputs

Inputs

Outputs