Back to Nodes
Z-Image Turbo Image Edit

Z-Image Turbo Image Edit

Official

Z-Image Turbo is a fast 6B model for generating images from text and image inputs using image-to-image technology.

Nodespell AI
AI / Image / Alibaba

Z-Image Turbo is a fast 6B model for generating images from text and image inputs using image-to-image technology.

Overview

Z-Image Turbo by Tongyi-MAI is a super-fast 6 billion parameter model designed for image-to-image generation. It accepts both textual prompts and input images to generate high-quality transformed images. Users can control parameters such as image size, inference steps, strength of conditioning, and output format. The model supports prompt expansion and safety-checking features to enhance generation reliability.

Strengths / What it does well

  • Generates images from detailed text prompts combined with input images.
  • Fast inference with a maximum of 8 inference steps.
  • Supports prompt expansion and safety checks to improve outputs.
  • Flexible output format options: PNG, JPEG, and WEBP.
  • Allows fine control over image-to-image strength for customized transformations.

Best use cases

  • Creative image editing and style transfer via text plus input image.
  • Generating variations or enhancements on existing images.
  • Rapid prototyping of visual concepts combining textual description and images.

Model Examples (3)

Example Index01 / 03
Example 01

Example 1

Fast style-transfer variant for a fashion prop source.

Open
Source Inputs02
Prompt

Transform the dress image into a refined editorial fashion concept render with ink-sketch linework over soft color washes. Keep the full-garment pose and mannequin framing.

Image Url
Example input
Parameters09
Prompt
Transform the dress image into a refined editorial fashion concept render with ink-sketch linework over soft color washes. Keep the full-garment pose and mannequin framing.
Acceleration
regular
Output Format
png
Strength
0.6
Enable Safety Checker
true
Num Inference Steps
8
Width
1024
Height
1024
Auto Size
true
Image EditStyle TransferFashionConcept Art
Response
output
Inputs (2)

Image

String

Image for Image-to-Image generation.

Min: 0Max: 100

Prompt

String

The prompt to generate an image from.

Multi InputMin: 0Max: 100
Parameters (10)

Prompt

String

The prompt to generate an image from.

Default:

Acceleration

String

The acceleration level to use.

Default: none

Output Format

String

The format of the generated image.

Default: png

Strength

Number

The strength of the image-to-image conditioning.

Default: 0.6

Enable Safety Checker

Boolean

If set to true, the safety checker will be enabled.

Default: true

Number Of Inference Steps

Number

The number of inference steps to perform.

Default: 8

Seed

Number

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

Default: -1

width

Number
Default: 1024

height

Number
Default: 1024

autoSize

Boolean
Default: true
Outputs (1)

Output

Inferred

Output

Nodespell

Nodespell

London

Building the future. Join us!

nodespell.comnodespell.appNodespellAI
Creator profile

Type

Node

Status

Official

Package

Nodespell AI

Category

AI / Image / Alibaba

Input

TextImage

Output

Image

Keywords

Image EditImage GenerationAspect ControlResolution Control
Use in Workflow