Available now

Z-Image Turbo: masked editing

Z-Image Turbo makes images from a text prompt in a few steps, reworks an image you upload, and repaints only the area you mask.

Model ID

Input

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

Example prompt. Edit it or write your own.

The Image for Inpaint generation.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

The Mask for Inpaint generation.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

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.

Whether to enable prompt expansion.

The scale of the controlnet conditioning.

The start of the controlnet conditioning.

The end of the controlnet conditioning.

The strength of the inpaint conditioning.

Price$0.02 / megapixel

You sign up first. Your settings are kept.

About this model

Overview

Z-Image Turbo runs at most eight sampling steps and gives one to four images per run, in square, portrait or landscape presets. An acceleration setting and an optional prompt expansion sit beside the prompt.

The image to image mode redraws an upload; its strength setting decides how far the result moves from it. The inpaint mode takes an image and a mask and changes only the masked part.

What you can build

  • Quick drafts to compare several ideas
  • A photo restyled as a painting or a sketch
  • An object removed or replaced inside a marked area
  • Batches of variations from one prompt

Prompting tips

  • Lower the strength in the image to image mode to keep more of the original layout; raise it for a bigger change.
  • For inpainting, paint the mask a little larger than the object and describe only what should appear there.
  • Keep the seed fixed while you edit the wording, so changes come from the prompt alone.

What to check

Inspect fine detail; for masked edits, check the boundary and nearby untouched areas.

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 8.
  • 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.
  • Enable Prompt Expansion (optional): Whether to enable prompt expansion.
  • Image (required): URL of Image for Inpaint generation.
  • Control Scale (optional): The scale of the controlnet conditioning. From 0 to 1.
  • Control Start (optional): The start of the controlnet conditioning. From 0 to 1.
  • Control End (optional): The end of the controlnet conditioning. From 0 to 1.
  • Mask Image (required): URL of Mask for Inpaint generation.
  • Strength (optional): The strength of the inpaint conditioning.

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