Available now

Z-Image Base: text to image

Z-Image Base is the base model of the Z-Image family: it turns a written prompt into one to four images, with a negative prompt and sampling settings.

Model ID

Input

Fields marked * are required. Review the price before generating.

Example prompt. Edit it or write your own.

Additional settings

The number of inference steps to perform.

The same seed and the same prompt given to the same version of the model will output the same image every time.

The acceleration level to use.

Price$0.02 / megapixel

You sign up first. Your settings are kept.

About this model

Overview

Z-Image Base makes one to four images per run in six preset shapes, as PNG, JPEG or WebP. A negative prompt keeps unwanted details out.

Steps run from 1 to 50 and the guidance scale from 1 to 20, and an acceleration level can shorten drafts.

What you can build

  • Illustrations and photo-style scenes in many styles
  • Square, portrait and landscape images for posts
  • Variations of one idea with different seeds
  • Test images before choosing a style for a project

Prompting tips

  • Name the style in the prompt, such as ink drawing, film photo or flat illustration.
  • Use the negative prompt for details to avoid, such as text, blur or extra objects.

What to check

Compare texture, geometry and unwanted elements at full size; higher settings need visual review.

Inputs

  • Prompt (required): The prompt to generate an image from.
  • Image Size (optional): The size of the generated image. Options: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • Number of Inference Steps (optional): The number of inference steps to perform. From 1 to 50.
  • Guidance Scale (optional): The guidance scale to use for the image generation. From 1 to 20.
  • Seed (optional): The same seed and the same prompt given to the same version of the model will output the same image every time.
  • Number of Images (optional): The number of images to generate. From 1 to 4.
  • Output Format (optional): The format of the generated image. Options: jpeg, png, webp.
  • Acceleration (optional): The acceleration level to use. Options: none, regular, high.
  • Negative Prompt (optional): The negative prompt to use for the image generation.

Output and limits

  • Image sizes: Square HD (1024×1024), Square (512×512), Portrait 4:3 (768×1024), Portrait 16:9 (576×1024), Landscape 4:3 (1024×768), Landscape 16:9 (1024×576).
  • File formats: JPEG, PNG, WEBP.
  • Up to 4 images per run.
  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • 1 megapixel: $0.02 / megapixel