New Model Available

Z-Image Base

A 6-billion parameter text-to-image model from Tongyi-MAI that generates photorealistic images with optional reference image guidance.

Why Choose Z-Image Base?

Reference Image Guidance

Optionally provide a reference image to influence the generated output's composition, style, or subject matter.

Flexible Output Sizing

Customize width and height up to 1024px for any aspect ratio you need.

Strength Control

Fine-tune how much the reference image influences the output with the strength parameter.

Prompt Enhancer

Built-in tool to automatically improve your prompts for better results.

Photorealistic Quality

6 billion parameters dedicated to creating lifelike visuals.

Just 5 Credits

Premium quality generation for just 5 credits per image.

How to Use

Text-to-Image (No Reference)

  1. Write your prompt: Describe the image you want to create in detail.
  2. Negative prompt: Optionally specify what to avoid (e.g., blurry, low quality).
  3. Set dimensions: Adjust width and height for your needs.
  4. Run: Click Generate to create your image.

With Reference Image

  1. Upload reference: Choose an image to guide composition or style.
  2. Write prompt: Describe the desired output provided the context.
  3. Adjust strength: Control influence (0.6 is a good start).
  4. Run: Generate your image.

Strength Guide

  • 0.2 - 0.4: Strong reference influence, output closely follows original.
  • 0.5 - 0.7: Balanced blend of reference and prompt.
  • 0.8 - 1.0: Prompt dominates, reference is loose inspiration.

Parameters

ParameterRequiredDescription
promptYesText description of the image to generate.
negative_promptNoElements to avoid in the output.
imageNoReference image to guide generation.
strengthNoInfluence of reference image (0-1). Default: 0.6
seedNoRandom seed for reproducibility (-1 for random).

Pricing

Per Image5 Credits

Takes 5 credits per generation due to the high computational power of the 6B parameter model.

Get Credits

Best Use Cases

  • Rapid Prototyping: Generate concepts quickly.
  • Style-guided Generation: Maintain consistent aesthetics using reference images.
  • Content Creation: High quality visuals for social media.

Pro Tips

  • 💡For pure text-to-image, be specific about style and lighting.
  • 💡When using reference, start with strength 0.6 and adjust.
  • 💡Keep the same seed to iterate on a specific composition.