BFL FLUX Models

Black Forest Labs' FLUX series image generation models, known for outstanding image quality and text rendering capabilities.

Try it Online

Test in Playground ↗ · View Models ↗

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://open.dieyuyun.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.images.generate(
    model="flux-1.1-pro",
    prompt="A neon-lit cyberpunk city street at night, rain reflections on the ground",
    size="1024x1024",
    n=1
)

print(response.data[0].url)

Endpoint

Item	Value
Method	POST
Path	/v1/images/generations
Base URL	https://open.dieyuyun.com
Protocol	OpenAI Images API

Authentication

Bearer Token: Authorization: Bearer YOUR_API_KEY

Available Models

Model Code	Description
flux-1.1-pro	FLUX 1.1 Pro, high-quality professional version (default)
flux-pro	FLUX Pro, high-quality version
flux-dev	FLUX Dev, development version, faster speed
flux-schnell	FLUX Schnell, fastest version, ideal for rapid iteration

Standard Request Fields

Field	Type	Required	Default	Description
model	string	Yes	—	Model identifier, e.g. flux-1.1-pro
prompt	string	Yes	—	Image description text
size	string	No	1024x1024	Image size
quality	string	No	standard	Generation quality: standard, hd
n	integer	No	1	Number of images to generate
response_format	string	No	url	Response format: url or b64_json

Supported Sizes

Size	Aspect Ratio	Description
1024x1024	1:1	Square
1536x1024	3:2	Landscape
1024x1536	2:3	Portrait
1344x768	16:9	Widescreen
768x1344	9:16	Vertical

Request Examples

cURL

curl https://open.dieyuyun.com/v1/images/generations \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-1.1-pro",
    "prompt": "A neon-lit cyberpunk city street at night, rain reflections on the ground",
    "size": "1024x1024",
    "n": 1
  }'

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://open.dieyuyun.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.images.generate(
    model="flux-1.1-pro",
    prompt="A neon-lit cyberpunk city street at night, rain reflections on the ground",
    size="1024x1024",
    n=1
)

print(response.data[0].url)

Node.js

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://open.dieyuyun.com/v1',
  apiKey: 'YOUR_API_KEY',
})

const response = await client.images.generate({
  model: 'flux-1.1-pro',
  prompt: 'A neon-lit cyberpunk city street at night, rain reflections on the ground',
  size: '1024x1024',
  n: 1,
})

console.log(response.data[0].url)

Response Format

Success Response

{
  "created": 1717000000,
  "data": [
    {
      "url": "https://...",
      "revised_prompt": "..."
    }
  ]
}

Field	Type	Description
created	integer	Unix timestamp
data	array	Array of generated results
data[].url	string	Image URL
data[].revised_prompt	string	The revised/optimized prompt used for generation

Error Response

See Error Codes for details.

Best Practices

• Model selection: Choose flux-1.1-pro for the highest quality, flux-schnell for rapid iteration, and flux-dev for a balance of speed and quality.
• Text rendering: The FLUX series excels at rendering text within images compared to most models, making it ideal for scenes with text elements (posters, banners, etc.).
• Prompt style: FLUX responds well to natural language descriptions. Write prompts like you would describe a scene naturally, without excessive keyword stacking.
• High-resolution output: For larger dimensions, choose non-square resolutions like 1536x1024 or 1344x768 for better widescreen results.

Rate Limits

See Rate Limits for details.

Related Documentation

• GPT Image 2 - OpenAI image generation model
• Model List & Pricing - Browse available models and pricing
• Playground - Test image generation interactively