Fuser

Z-Image

Provided by Fal — Learn More

Z-Image is a fast and efficient image generation model from Alibaba. It delivers photorealistic images with excellent aesthetic quality and excels at accurately rendering both Chinese and English text directly in generated images. With built-in prompt enhancement and reasoning capabilities, Z-Image helps bring your creative visions to life with sub-second inference speed.

Preview

Inputs

Prompt
text

The prompt to generate an image from.

LoRA Weights
text
Accepts multiple

List of LoRA weights to apply (maximum 3). To provide LoRA weights, use a text node that contains the URL of .safetensors file.

optional: true
Image Size
dropdown

The size of the generated image.

default: 1024x1024Accepts: Square, Landscape 4:3, Portrait 4:3, Landscape 16:9, Portrait 16:9
Resolution
dropdown

The resolution of the generated image.

default: 2KAccepts: 1K, 2K
Steps
number

The number of inference steps to perform.

default: 8•minimum: 1•maximum: 8
Seed
seed

The same seed and prompt will output the same image every time.

default: 1510
Block NSFW
toggle

Prevents the model from generating images that portray nudity, violence, and other unsafe content.

default: false

Outputs

Generated Image
image

The generated image from the model.