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 StableCascade_EmptyLatentImage node creates empty latent tensors for Stable Cascade models. It generates two separate latent representations - one for stage C and another for stage B - with appropriate dimensions based on the input resolution and compression settings. This node provides the starting point for the Stable Cascade generation pipeline.

Inputs

ParameterData TypeRequiredRangeDescription
widthINTYes256 to MAX_RESOLUTIONThe width of the output image in pixels (default: 1024, step: 8)
heightINTYes256 to MAX_RESOLUTIONThe height of the output image in pixels (default: 1024, step: 8)
compressionINTYes4 to 128The compression factor that determines the latent dimensions for stage C (default: 42, step: 1)
batch_sizeINTNo1 to 4096The number of latent samples to generate in a batch (default: 1)

Outputs

Output NameData TypeDescription
stage_cLATENTThe stage C latent tensor with dimensions [batch_size, 16, height//compression, width//compression]
stage_bLATENTThe stage B latent tensor with dimensions [batch_size, 4, height//4, width//4]