liveBook · Manning

Empty Latent Image

As explained in Local Image Generation

Empty Latent Image is a ComfyUI node that creates an initial latent tensor with configurable image dimensions and batch count.

Start a ComfyUI diffusion workflow with a blank canvas in latent form. Add Empty Latent Image through Add Node > latent, then send its LATENT output to KSampler. section 8.2.4

Configure the initial image here:

Basic connection

Create Empty Latent Image, set the desired width, height, and batch_size, and connect LATENT to KSampler’s latent_image input. section 8.2.4

Figure 8.12 The Empty Latent Images is where we specify image dimensions and batch size.

Use the figure to identify the node controls for image dimensions and batch size. section 8.2.4

How Local Image Generation covers it

How deep it goes
Defines node placement, LATENT wiring, and dimension settings, without detailing latent tensor internals.
Examples
Uses a ComfyUI node connected from LATENT to KSampler’s latent_image input.
What it assumes
Assumes a ComfyUI workflow containing KSampler and teaches node creation and connection directly.
What you can do after
Operate/configure a ComfyUI workflow with chosen image dimensions and batch count.
How it connects
Connects latent input with diffusion models and KSampler.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Local Image Generation. The section links point to the parts of the book it draws on.