EmptySD3LatentImage - ComfyUI Built-in Node Documentation

Complete documentation for the EmptySD3LatentImage node in ComfyUI. Learn its inputs, outputs, parameters and usage.

The EmptySD3LatentImage node creates a blank latent image tensor specifically formatted for Stable Diffusion 3 models. It generates a tensor filled with zeros that has the correct dimensions and structure expected by SD3 pipelines. This is commonly used as a starting point for image generation workflows.

Inputs

Parameter	Description	Data Type	Required	Range
width	The width of the output latent image in pixels (default: 1024)	INT	Yes	16 to MAX_RESOLUTION (step: 16)
height	The height of the output latent image in pixels (default: 1024)	INT	Yes	16 to MAX_RESOLUTION (step: 16)
batch_size	The number of latent images to generate in a batch (default: 1)	INT	Yes	1 to 4096

Outputs

Output Name	Description	Data Type
LATENT	A latent tensor containing blank samples with SD3-compatible dimensions. The tensor has 16 channels and is spatially downscaled by a factor of 8 compared to the input width and height.	LATENT

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): 7a4b2454807bc905f26b96c0ff98706fa3e248bbf2b3995d5d38ebc3c5663fd6