Image Models Guide

This guide explains how to call VLX FLUX image generation models through the OpenAI-compatible protocol and the Midjourney-Proxy protocol.

Prerequisites

• Register on VLX FLUX and create an API key
• Confirm the API base URL https://api.vlxflux.io
• Install the required runtime locally

OpenAI-Compatible API

Through the standard /v1/images/generations endpoint, you can call DALL-E, proxied Midjourney models, and other image generation capabilities.

Install Dependencies

pip install openai requests

Python Usage

Basic Request

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxxxxxx",
    base_url="https://api.vlxflux.io/v1"
)

response = client.images.generate(
    model="dall-e-3",
    prompt="A cute cat drinking coffee in cyberpunk style",
    size="1024x1024",
    quality="standard",
    n=1,
)

image_url = response.data[0].url
print("Image URL:", image_url)

Return Base64

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxxxxxx",
    base_url="https://api.vlxflux.io/v1"
)

response = client.images.generate(
    model="dall-e-3",
    prompt="A cute cat drinking coffee in cyberpunk style",
    size="1024x1024",
    response_format="b64_json",
    n=1,
)

image_b64 = response.data[0].b64_json
print(image_b64[:50] + "...")

Save Image

import base64
from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxxxxxx",
    base_url="https://api.vlxflux.io/v1"
)

response = client.images.generate(
    model="dall-e-3",
    prompt="A cute cat drinking coffee in cyberpunk style",
    size="1024x1024",
    response_format="b64_json",
    n=1,
)

image_data = response.data[0].b64_json
with open("cat.png", "wb") as f:
    f.write(base64.b64decode(image_data))

print("Saved as cat.png")

curl Usage

curl https://api.vlxflux.io/v1/images/generations   -H "Content-Type: application/json"   -H "Authorization: Bearer sk-xxxxxxxx"   -d '{
    "model": "dall-e-3",
    "prompt": "a cute cat drinking coffee, cyberpunk style",
    "size": "1024x1024",
    "n": 1
  }'

Supported Models

Model	Type	Description
dall-e-2	Image	Official DALL-E 2
dall-e-3	Image	Better detail quality
midjourney	Image	Proxied Midjourney
stable-diffusion	Image	Stable Diffusion model

Extra Prompt Parameters

response = client.images.generate(
    model="midjourney",
    prompt="a cute cat drinking coffee --ar 16:9 --niji 6",
    n=1,
)

---

Midjourney-Proxy Protocol

If your application already uses the midjourney-proxy format, you can switch the Base URL and API secret directly.

Authentication

mj-api-secret: sk-xxxxxxxx

Python Usage

Submit Imagine Task

import requests

url = "https://api.vlxflux.io/mj/submit/imagine"
headers = {
    "mj-api-secret": "sk-xxxxxxxx",
    "Content-Type": "application/json"
}
data = {
    "prompt": "a futuristic city, neon lights --ar 16:9"
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

Fetch Task Status

import requests

task_id = "123456789"
url = f"https://api.vlxflux.io/mj/task/{task_id}/fetch"
headers = {
    "mj-api-secret": "sk-xxxxxxxx"
}

response = requests.get(url, headers=headers)
print(response.json())

Common Errors

Status	Cause	Solution
400	Invalid parameters	Check prompt, size, and related fields
401	Authentication failed	Check API key or Bearer prefix
402	Insufficient balance	Recharge and retry
403	No access to model	Check model permission
500	Upstream overload	Retry later or switch model