ComfyUI Node Runs on cloud
Context Windows (Manual)
Manually set context windows.
Context Windows (Manual)
- model
- MODEL
◄context_length16►
◄context_overlap4►
◄context_schedulestandard_static►
◄context_stride1►
◄closed_loopfalse►
◄fuse_methodpyramid►
◄dim0►
◄freenoisefalse►
◄cond_retain_index_list►
◄split_conds_to_windowsfalse►
◄latent_retain_index_list►
◄causal_window_fixtrue►
Categorymodel/patch
Inputs (13)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | The model to apply context windows to during sampling. | |
| context_length | INT | 16 | The length of the context window. |
| context_overlap | INT | 4 | The overlap of the context window. |
| context_schedule | COMBO | standard_static | Step-dependent scheduling algorithm for context windows. |
| context_stride | INT | 1 | The stride of the context window; only applicable to uniform schedules. |
| closed_loop | BOOLEAN | false | Whether to close the context window loop; only applicable to looped schedules. |
| fuse_method | COMBO | pyramid | The method to use to fuse the context windows. |
| dim | INT | 00–5 | The dimension to apply the context windows to. |
| freenoise | BOOLEAN | false | Whether to apply FreeNoise noise shuffling, improves window blending. |
| cond_retain_index_list | STRING | List of latent indices to retain in the conditioning tensors for each window. For concat-style I2V models (e.g. Wan I2V, HunyuanVideo I2V, Cosmos I2V, SVD) the encoded start image lives in the c_concat conditioning channels; setting this to '0' will retain that start image content at sub-pos 0 of every window. | |
| split_conds_to_windows | BOOLEAN | false | Whether to split multiple conditionings (created by ConditionCombine) to each window based on region index. |
| latent_retain_index_list | STRING | List of latent indices to retain in the noise latent itself for each window. Use for workflows where reference content (e.g. a start image) lives directly in the noise latent rather than in separate conditioning channels (e.g. inplace-style I2V like LTXV, AnimateDiff). Independent of cond_retain_index_list. | |
| causal_window_fix | BOOLEAN | true | Whether to add a causal fix frame to non-0-indexed context windows. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| MODEL | MODEL | The model with context windows applied during sampling. |