Z-Image Base

Model Information

Display Name: Z-Image Base

API Model ID: zimage/z-image-base

Category: Text To Image

Description: Z-Image Base is a 6 billion parameter text-to-image foundation model with full CFG support, delivering high visual fidelity and strong prompt adherence. **Key Features:** - 6B parameter foundation model - Full CFG (Classifier-Free Guidance) support - Image variation generation (not editing) - Negative prompt support - Flexible output sizing up to 1536px **Capabilities:** - High-fidelity image generation from text - Strong prompt adherence - Diverse stylistic output - **Image Variation:** Send a reference image and the model generates a new variation based on it (controlled by strength parameter) **Output Options:** - **Aspect Ratios:** 1:1, 16:9, 9:16, 4:3, 3:4 - **Formats:** JPEG, PNG - **Resolution:** 256-1536px (default 1024x1024) **Note:** This model does NOT edit images. When you send a reference image, it creates a new variation inspired by it, not a modified version of the original.

How to Use This Model

To use Z-Image Base via the HInow.ai API, use the model ID: zimage/z-image-base

API Request Example (Chat/Text)


POST https://api.hinow.ai/v1/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

{
  "model": "zimage/z-image-base",
  "messages": [
    {"role": "user", "content": "Your message here"}
  ]
}
              

API Request Example (Image Generation)


POST https://api.hinow.ai/v1/images/generations
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

{
  "model": "zimage/z-image-base",
  "prompt": "Your image description here"
}
              

Pricing

  • total: $0.02

Available Parameters

  • aspect_ratio: Output image aspect ratio (Options: 1:1, 16:9, 9:16, 4:3, 3:4)
  • strength: Transformation intensity for img2img (default: 0.6) (Options: 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0)
  • output_format: Output image format (default: jpeg) (Options: jpeg, png)

Quick Reference

To use this model, set: "model": "zimage/z-image-base"

Featured: No

Documentation: https://hinow.ai/models/zimage/z-image-base

API Endpoint: https://api.hinow.ai/v1

Back to Models
Z-Image Base

Z-Image Base

zimage/z-image-base

$0.020
per image

About

Z-Image Base is a 6 billion parameter text-to-image foundation model with full CFG support, delivering high visual fidelity and strong prompt adherence.

Key Features:

  • 6B parameter foundation model
  • Full CFG (Classifier-Free Guidance) support
  • Image variation generation (not editing)
  • Negative prompt support
  • Flexible output sizing up to 1536px

Capabilities:

  • High-fidelity image generation from text
  • Strong prompt adherence
  • Diverse stylistic output
  • Image Variation: Send a reference image and the model generates a new variation based on it (controlled by strength parameter)

Output Options:

  • Aspect Ratios: 1:1, 16:9, 9:16, 4:3, 3:4
  • Formats: JPEG, PNG
  • Resolution: 256-1536px (default 1024x1024)

Note: This model does NOT edit images. When you send a reference image, it creates a new variation inspired by it, not a modified version of the original.

Capabilities

Text To ImageImage To Image

Parameters

aspect_ratio

Output image aspect ratio

1:116:99:164:33:4
strength

Transformation intensity for img2img (default: 0.6)

0.40.50.60.70.80.91.0
output_format

Output image format (default: jpeg)

jpegpng

Code Examples

curl -X POST https://api.hinow.ai/v1/images \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $HINOW_API_KEY" \
  -d '{
    "model": "zimage/z-image-base",
    "prompt": "Transform this image into cyberpunk style",
    "images": [
      "https://example.com/image1.jpg",
      "data:image/png;base64,iVBORw0KGgo..."
    ],
    "parameters": {
      "aspect_ratio": "1:1",
      "strength": "0.4",
      "output_format": "jpeg"
    }
  }'