Image Generation

The Image Generation API creates images from text descriptions using DALL-E models. Supports both DALL-E 3 and DALL-E 2 with various size and quality options.

Endpoint Info

Item	Value
URL	/v1/images/generations
Method	POST
Auth	Bearer Token (API Key)
Content-Type	application/json

Request Parameters

Parameter	Type	Required	Description
model	string	No	Model: dall-e-3 (default) or dall-e-2
prompt	string	Yes	Text description of the desired image
n	integer	No	Number of images to generate. Default 1 (DALL-E 3 only supports 1)
size	string	No	Image size. DALL-E 3: 1024x1024, 1792x1024, 1024x1792. DALL-E 2: 256x256, 512x512, 1024x1024
quality	string	No	Image quality: standard or hd (DALL-E 3 only)
style	string	No	Style: vivid or natural (DALL-E 3 only)
response_format	string	No	Response format: url or b64_json. Default url

cURL Examples

Text-to-Image (DALL-E 3)

curl https://api.quickapi.store/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "dall-e-3",
    "prompt": "A futuristic city at sunset with flying cars and neon lights",
    "n": 1,
    "size": "1024x1024",
    "quality": "hd",
    "style": "vivid"
  }'

URL Format Response

curl https://api.quickapi.store/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "dall-e-3",
    "prompt": "A cute robot reading a book in a cozy library",
    "size": "1024x1024",
    "response_format": "url"
  }'

Base64 JSON Format

curl https://api.quickapi.store/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "dall-e-3",
    "prompt": "An oil painting of a mountain landscape",
    "size": "1792x1024",
    "response_format": "b64_json"
  }'

DALL-E 2 Multiple Images

curl https://api.quickapi.store/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "dall-e-2",
    "prompt": "A cat wearing a space suit on Mars",
    "n": 4,
    "size": "512x512",
    "response_format": "url"
  }'

💡 Prompt Quality

Detailed, descriptive prompts produce better results. Include style, lighting, composition, and mood for optimal image generation.

Response Example

URL Format

{
  "created": 1700000000,
  "data": [
    {
      "url": "https://api.quickapi.store/images/gen_abc123.png",
      "revised_prompt": "A futuristic city at sunset with flying cars and neon lights, in a cyberpunk art style with dramatic lighting"
    }
  ]
}

Base64 JSON Format

{
  "created": 1700000000,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAABAAAA...",
      "revised_prompt": "An oil painting of a mountain landscape with dramatic clouds and golden hour lighting"
    }
  ]
}

Python Example

from openai import OpenAI

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

# Generate image with URL response
response = client.images.generate(
    model="dall-e-3",
    prompt="A futuristic city at sunset with flying cars and neon lights",
    size="1024x1024",
    quality="hd",
    style="vivid"
)
image_url = response.data[0].url
print(f"Image URL: {image_url}")
print(f"Revised prompt: {response.data[0].revised_prompt}")

# Generate image with base64 response
response = client.images.generate(
    model="dall-e-3",
    prompt="An oil painting of a mountain landscape",
    size="1792x1024",
    response_format="b64_json"
)
b64_data = response.data[0].b64_json

# Save base64 image to file
import base64
with open("generated_image.png", "wb") as f:
    f.write(base64.b64decode(b64_data))
print("Image saved to generated_image.png")

# DALL-E 2 with multiple images
response = client.images.generate(
    model="dall-e-2",
    prompt="A cat wearing a space suit on Mars",
    n=4,
    size="512x512"
)
for i, img in enumerate(response.data):
    print(f"Image {i+1}: {img.url}")

⚠️ URL Expiration

Image URLs returned by the API expire after 1 hour. For persistent storage, either download the image immediately or use b64_json format and save the file yourself.