Skip to main content
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

ParameterDescriptionData TypeRequiredRange
samplesThe latent representation to be decoded into imagesLATENTYes-
vaeThe VAE model used for decoding the latent samplesVAEYes-
tile_sizeThe size of each tile for processing (default: 512)INTYes64-4096 (step: 32)
overlapThe amount of overlap between adjacent tiles (default: 64)INTYes0-4096 (step: 32)
temporal_sizeOnly used for video VAEs: Amount of frames to decode at a time (default: 64)INTYes8-4096 (step: 4)
temporal_overlapOnly used for video VAEs: Amount of frames to overlap (default: 8)INTYes4-4096 (step: 4)
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. The node also accounts for the VAE’s internal compression ratios when calculating tile and overlap sizes for both spatial and temporal dimensions.

Outputs

Output NameDescriptionData Type
IMAGEThe decoded image or images generated from the latent representationIMAGE
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 193d5cb219d66855ae581d3e4488b7b6ae3a45b735fb0f9f784fea1f5d466e46