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

ParameterData TypeRequiredRangeDescription
modelMODELYes-The diffusion model to apply the HyperTile optimization to
tile_sizeINTNo1-2048The target tile size for processing (default: 256)
swap_sizeINTNo1-128Controls how the tiles are rearranged during processing (default: 2)
max_depthINTNo0-10Maximum depth level to apply tiling (default: 0)
scale_depthBOOLEANNo-Whether to scale tile size based on depth level (default: False)

Outputs

Output NameData TypeDescription
modelMODELThe modified model with HyperTile optimization applied