# LTXV Context Windows

This node sets context windows for LTXV-like models during sampling. It divides generation into overlapping windows to help manage memory usage and improve temporal coherence.

## 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 in real frames. Must be 8*n + 1. (default: 145) | INT | Yes | Minimum: 1<br>Maximum: nodes.MAX_RESOLUTION<br>Step: 8 |
| `context_overlap` | The overlap of the context window in real frames. (default: 40) | INT | Yes | Minimum: 0<br>Step: 8 |
| `context_schedule` | Step-dependent scheduling algorithm for context windows. (default: "UNIFORM_STANDARD") | COMBO | Yes | `"STATIC_STANDARD"`<br>`"UNIFORM_STANDARD"`<br>`"UNIFORM_LOOPED"`<br>`"BATCHED"` |
| `context_stride` | The stride of the context window; only applicable to uniform schedules. (default: 1) | INT | Yes | Minimum: 1 |
| `closed_loop` | Whether to close the context window loop; only applicable to looped schedules. (default: False) | BOOLEAN | Yes | True<br>False |
| `fuse_method` | The method to use to fuse the context windows. Available options are defined by `ContextFuseMethods.LIST_STATIC`. (default: "PYRAMID") | COMBO | Yes | Defined by `ContextFuseMethods.LIST_STATIC` |
| `freenoise` | Whether to apply FreeNoise noise shuffling, improves window blending. (default: True) | BOOLEAN | Yes | True<br>False |
| `retain_first_frame` | Retain the first latent frame in every context window (may help retain initial reference). (default: False) | BOOLEAN | Yes | True<br>False |
| `split_conds_to_windows` | Whether to split multiple conditionings (created by ConditionCombine) to each window based on region index. (default: False) | BOOLEAN | Yes | True<br>False |

**Note:** The `context_length` value is provided in real frames and is internally converted to latent frames using the formula `((context_length - 1) // 8) + 1`, with a minimum of 1. The `context_overlap` value is also provided in real frames and is converted to latent frames using integer division by 8, with a minimum of 0. The tooltip for `context_length` indicates it must follow the pattern 8*n + 1.

## Outputs

| Output Name | Description | Data Type |
|-------------|-------------|-----------|
| `MODEL` | The model with context windows applied for 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](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVContextWindows/en.md)

---
**Source fingerprint (SHA-256):** `148649d0a938e08c932a163f5d7614332626fba37b8f79db7f92bbcf422e692f`
