Image Generation

Create stunning images from text prompts using state-of-the-art AI models

Image generation is a Pro feature. Upgrade to access.

Generate high-quality images from text descriptions using our optimized Flux architecture.

Endpoint

POST https://api.llm.kiwi/v1/images/generations

Request Parameters

Parameter	Type	Required	Description
prompt	string	Yes	Text description of the desired image.
model	string	No	Model to use: flux (default) or dall-e-3.
n	integer	No	Number of images to generate (1-4). Default: 1.
size	string	No	Image dimensions: 1024x1024, 1792x1024, 1024x1792.
quality	string	No	Quality level: standard or hd. Default: standard.
style	string	No	Style preset: vivid or natural. Default: vivid.
response_format	string	No	Return format: url or b64_json. Default: url.

Example Usage

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llm.kiwi/v1",
    api_key="YOUR_API_KEY"
)

response = client.images.generate(
    model="flux",
    prompt="A futuristic city built on a floating island, digital art",
    size="1024x1024",
    quality="hd"
)

print(response.data[0].url)

Response Object

{
  "created": 1706745600,
  "data": [
    {
      "url": "https://cdn.llm.kiwi/images/abc123.png",
      "revised_prompt": "A cute kiwi bird in a detailed spacesuit..."
    }
  ]
}

Content Moderation

All prompts are filtered for safety. Requests that violate our content policy will be rejected with a 400 error.

Prohibited content includes:

• Violence or gore
• Adult or explicit content
• Hate speech or discrimination
• Real public figures without consent

Prompt Engineering Tips

• Be Specific: “A red sports car” → “A cherry red 1965 Ford Mustang convertible on a coastal highway at sunset”
• Add Style: Include terms like photorealistic, oil painting, 3D render, minimalist
• Set Mood: Use descriptors like golden hour lighting, moody atmosphere, high contrast
• Describe Composition: Specify camera angle, focal length, or framing

Need More?

Contact us for batch image generation or custom model training.