Midjourney

Neural Network

Beep-boop, writing text for you...
pc1pc2pc3pc4

Specifications

Input
text, images
Output
text, images
Resolution
1024x1024

Caps remaining: 0 CAPS
Code example and API for MidjourneyWe offer full access to the OpenAI API through our service. All our endpoints fully comply with OpenAI endpoints and can be used both with plugins and when developing your own software through the SDK.Create API key
import OpenAI from 'openai';
const openai = new OpenAI({
  apiKey: '<your bothub access token>',
  baseURL: 'https://openai.bothub.chat/v1'
});

async function main() {
  const response = await openai.images.generate({
    model: 'midjourney',
    prompt: 'a white siamese cat',
    n: 1,
    size: '1024x1024'
  });

  const imageUrl = response.data[0].url;
} 
main();

How it works Midjourney?

Bothubs gather information...empty

Frequently asked questions about Midjourney

You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.

Midjourney creates images from text descriptions, can redraw and refine uploaded images, and describe them in words. It is suitable for concept art, illustrations, posters, avatars, visuals for social media and advertising, mood boards, and quick style exploration before production.

You get a finished image that you can download and use in your work. Midjourney is known for its sophisticated artistic style: from photorealistic shots to painting and graphics. Detail and composition depend on how detailed your description of the scene, lighting, and angle is.

A separate step-by-step reasoning mode is not noted for this model in our data: it proceeds directly to image generation. The result depends most heavily on the prompt, so describe the object, style, lighting, and composition, and then refine the wording based on the initial results.

Function calling and structured output are not noted for Midjourney in our data; it is a visual model. If your project requires tools and strict JSON, use a text model: BotHub's unified OpenAI-compatible API allows you to switch without rewriting the integration.

You can upload images: the model supports working with references, i.e., generating a new image from an existing one, as well as describing an uploaded image with text. Audio and video input is not supported for this model, so rely on text and visual references.

We have no confirmed data on how the model processes Russian-language prompts, so we cannot promise accuracy. The practical approach is: describe the scene as specifically as possible, check the result, and rephrase if necessary. The BotHub interface is in Russian, payment is in rubles, and no VPN is required.

Support ServiceOpen from 10:00 to 18:00 MSK