This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHubThe Empty Qwen Image Layered Latent node creates a blank, multi-layered latent representation for use with Qwen image models. It generates a tensor filled with zeros, structured with a specified number of layers, batch size, and spatial dimensions. This empty latent serves as a starting point for subsequent image generation or manipulation workflows.
Inputs
| Parameter | Data Type | Required | Range | Description |
|---|---|---|---|---|
width | INT | Yes | 16 to MAX_RESOLUTION | The width of the latent image to create. The value must be divisible by 16. (default: 640) |
height | INT | Yes | 16 to MAX_RESOLUTION | The height of the latent image to create. The value must be divisible by 16. (default: 640) |
layers | INT | Yes | 0 to MAX_RESOLUTION | The number of additional layers to add to the latent structure. This defines the depth of the latent representation. (default: 3) |
batch_size | INT | No | 1 to 4096 | The number of latent samples to generate in a batch. (default: 1) |
width and height parameters are internally divided by 8 to determine the spatial dimensions of the output latent tensor.
Outputs
| Output Name | Data Type | Description |
|---|---|---|
samples | LATENT | A latent tensor filled with zeros. Its shape is [batch_size, 16, layers + 1, height // 8, width // 8]. |