Documentation Index
Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
Use this file to discover all available pages before exploring further.
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHubThe HyperTile node applies a tiling technique to the attention mechanism in diffusion models to optimize memory usage during image generation. It divides the latent space into smaller tiles and processes them separately, then reassembles the results. This allows for working with larger image sizes without running out of memory.
Inputs
| Parameter | Data Type | Required | Range | Description |
|---|---|---|---|---|
model | MODEL | Yes | - | The diffusion model to apply the HyperTile optimization to |
tile_size | INT | No | 1 - 2048 | The target tile size for processing (default: 256). The effective tile size is rounded down to a multiple of 8, with a minimum of 32. |
swap_size | INT | No | 1 - 128 | Controls how the tiles are rearranged during processing to improve efficiency (default: 2) |
max_depth | INT | No | 0 - 10 | The maximum depth level (resolution scale) to apply tiling. A value of 0 applies tiling only at the highest resolution (default: 0) |
scale_depth | BOOLEAN | No | True / False | When enabled, the tile size is scaled proportionally at deeper depth levels. This can help maintain quality at lower resolutions (default: False) |
Outputs
| Output Name | Data Type | Description |
|---|---|---|
model | MODEL | The modified model with HyperTile optimization applied |
Source fingerprint (SHA-256):
ea770eea3c628ffb166c2a15a6f75757cebd99c3fdd6225f041b3ef01a0e73c7