Inputs
Note: When the
samples latent includes coordinate counts, the counts must be non-negative, their total must match the number of coordinate rows, and each batch must have exactly the expected number of rows; otherwise the node raises an error. If the latent’s model frame is “z_up”, the decoded voxel coordinates are remapped to Y-up so they align with mesh vertices. When a coordinate resolution is supplied, the output texture resolution is that value multiplied by 16; otherwise it is inferred from the largest voxel coordinate and rounded up to one of 256, 512, 1024, 1536, or 2048 (1024 when no coordinates are available).
Outputs
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):
cfbe59efb18d2c3c7c597c5212900fea54d660aa98005817debf4711401a6967