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 VAEDecodeTiled node decodes latent representations into images using a tiled approach to handle large images efficiently. It processes the input in smaller tiles to manage memory usage while maintaining image quality. The node also supports video VAEs by processing temporal frames in chunks with overlap for smooth transitions.

Inputs

ParameterData TypeRequiredRangeDescription
samplesLATENTYes-The latent representation to be decoded into images
vaeVAEYes-The VAE model used for decoding the latent samples
tile_sizeINTYes64-4096 (step: 32)The size of each tile for processing (default: 512)
overlapINTYes0-4096 (step: 32)The amount of overlap between adjacent tiles (default: 64)
temporal_sizeINTYes8-4096 (step: 4)Only used for video VAEs: Amount of frames to decode at a time (default: 64)
temporal_overlapINTYes4-4096 (step: 4)Only used for video VAEs: Amount of frames to overlap (default: 8)
Note: The node automatically adjusts overlap values if they exceed practical limits. If tile_size is less than 4 times the overlap, the overlap is reduced to one quarter of the tile size. Similarly, if temporal_size is less than twice the temporal_overlap, the temporal overlap is halved.

Outputs

Output NameData TypeDescription
IMAGEIMAGEThe decoded image or images generated from the latent representation