EmptyFlux2LatentImage - ComfyUI Built-in Node Documentation

The Empty Flux 2 Latent node creates a blank latent representation filled with zeros.

The Empty Flux 2 Latent node creates a blank latent representation filled with zeros. It is used as a starting point for the Flux model’s denoising process. The latent dimensions are taken from the input width and height, each divided by 16.

Inputs

Parameter	Description	Data Type	Required	Range
width	The width of the final image to generate. The latent width will be this value divided by 16. The default value is 1024.	INT	Yes	16 to 16384
height	The height of the final image to generate. The latent height will be this value divided by 16. The default value is 1024.	INT	Yes	16 to 16384
batch_size	The number of latent samples to generate in a single batch. The default value is 1.	INT	No	1 to 4096

Note: The width and height inputs use a step of 16, so they must be divisible by 16. This is because the node divides them by this factor to create the latent dimensions.

Outputs

Output Name	Description	Data Type
samples	A latent tensor filled with zeros. The shape is [batch_size, 128, height // 16, width // 16].	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): f8356568f0ab521a3f246d1f672492e74f9a2f449694961b913bd14a5f0f3878