Image Generation

Supported Models

Model	Provider	Max Size	Notes
`azure/flux-kontext-pro`	Azure (FLUX)	1440x1440	Flux Kontext Pro, high quality
`azure/flux-2-pro`	Azure (FLUX)	1440x1440	Flux 2 Pro
`google/imagen-4.0`	Google Vertex	2048x2048	Google Imagen 4
`google/imagen-4.0-fast`	Google Vertex	2048x2048	Faster variant
`google/imagen-4.0-ultra`	Google Vertex	2048x2048	Highest quality
`bailian/wan2.7-image`	Alibaba Bailian	1024x1024	Wanxiang image generation
`bailian/wan2.7-image-pro`	Alibaba Bailian	1024x1024	Pro variant
`azure/mai-image-2`	Azure	2048x2048	Microsoft MAI Image 2
`bedrock/stability-*`	Amazon Bedrock	1024x1024	Stability AI models

Text-to-Image

Request

POST https://api.chuizi.ai/v1/images/generations

Parameters

Parameter	Type	Required	Default	Description
`model`	string	Yes	--	Model name
`prompt`	string	Yes	--	Image description
`size`	string	No	`"1024x1024"`	Image dimensions
`n`	integer	No	`1`	Number of images (1-4)
`response_format`	string	No	`"url"`	`url` or `b64_json`

Size Options

Size	Aspect Ratio	Supported Models
`1024x1024`	1:1 (square)	All models
`1792x1024`	16:9 (landscape)	Most models
`1024x1792`	9:16 (portrait)	Most models
`2048x2048`	1:1 (large square)	Imagen, MAI Image

Example

terminal

bash

curl -X POST https://api.chuizi.ai/v1/images/generations \
  -H "Authorization: Bearer ck-your-key-here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "azure/flux-kontext-pro",
    "prompt": "A minimalist logo design for a coffee shop called 'Morning Brew', clean lines, warm colors",
    "size": "1024x1024",
    "n": 1
  }'

Response

config.json

json

{
  "created": 1712000000,
  "data": [
    {
      "url": "https://media.chuizi.ai/images/gen-xxxxxxxxxxxxxxxx.png"
    }
  ],
  "x_chuizi": {
    "generation_id": "gen-xxxxxxxxxxxxxxxx",
    "cost": "0.05000000",
    "latency_ms": 8500
  }
}

The url is a permanent link hosted on the R2 CDN. It does not expire.

Code Examples

example.py

python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.chuizi.ai/v1",
    api_key="ck-your-key-here",
)

# Generate an image
response = client.images.generate(
    model="azure/flux-kontext-pro",
    prompt="A futuristic cityscape at night, neon lights, cyberpunk style, detailed",
    size="1792x1024",
    n=1,
)
print(f"Image URL: {response.data[0].url}")

# Generate multiple images
response = client.images.generate(
    model="google/imagen-4.0-fast",
    prompt="A watercolor painting of a mountain lake at sunrise",
    size="1024x1024",
    n=4,
)
for i, image in enumerate(response.data):
    print(f"Image {i + 1}: {image.url}")

# Edit an existing image
response = client.images.edit(
    model="azure/flux-kontext-pro",
    image=open("photo.png", "rb"),
    prompt="Add a rainbow in the sky",
    size="1024x1024",
)
print(f"Edited image: {response.data[0].url}")

Next Steps

Image Generations API — full API reference
Image Edits API — background removal, inpainting, and upscaling
Video Generation — generate videos from text prompts