Welcome to the Image Generation API documentation.

Our platform enables developers to generate high-quality, customizable images using advanced models like Flux, SDXL, and Hive's fine-tuned enhancements.

This guide covers everything you need to get started with our latest V3 API to build creative applications, enhance your content workflows, and more.

🛝

If you'd like to get started right away - head to our Playground and sign up a (free!) account to test our models.

Why Choose Hive's Image Generation APIs?

• State-of-the-Art Models: Access open-source favorites like Flux and SDXL, plus Hive’s exclusive enhanced versions.
• Customizable Outputs: Generate images tailored to your needs—from photorealistic visuals to unique, branded emojis.
• Seamless Integration: Quick and easy API setup with detailed documentation and a testing Playground.
• Proven Results: Used by leading platforms to power creative and visual workflows.

Getting Started with Hive

1. Explore the Playground: Try out different models, prompts, and settings to see what works best for your use case.
   1. Go to Playground
2. Choose Your Model:👇
   1. SDXL: Stability AI's flagship model.
   2. SDXL Enhanced: Hive's enhanced version of SDXL, served exclusively to our users.
   3. Flux Schnell: Flux's fastest version of their state-of-the-art image gen suite.
   4. Flux Schnell Enhanced: Hive's enhanced version that generates photorealistic images with stunning success.
   5. Emojis: Hive's Emoji model to generate custom, high-quality emojis with transparent backgrounds.
3. Integrate the API:
   1. Our playgrounds include step-by-step integration docs to connect your app or workflow with Hive's APIs and start generating images immediately.
      1. Docs
   2. You can also keep reading below to learn how more!

Key Features of the V3 API:

• Flexible Input Options: Generate images using detailed text prompts with optional negative prompts to exclude unwanted elements.
• Multiple Models: Choose from a lineup of models optimized for speed, photorealism, or artistic expression.
• Content Moderation: Built-in moderation ensures generated content aligns with safety and quality guidelines.
• Customizable Outputs: Control the number of images, output size, and more.

Generating Images

How it Works

The Image Generation APIs enable you to create visuals by sending a text prompt to one of our supported models. The API processes the prompt and returns links to the generated images, along with relevant metadata.

Getting your V3 API Key

Your V3 API Key can be created in the left sidebar of the Hive UI, under "API Keys."

Follow these steps to generate your key:

• Click ‘API Keys’ in the sidebar.
• Click ‘+’ to create a new key scoped to your organization. The same key can be used with any "Playground available" model.

⚠️ Important: Keep your API Key secure. Do not expose it in client-side environments like browsers or mobile apps.

Request Format

To generate images using the V3 API, you need to send a POST request with a JSON payload that includes details about your prompt and desired output settings.

Here's an example calling the flux-schnell model:

curl --location --request POST 'https://api.thehive.ai/api/v3/black-forest-labs/flux-schnell' \
--header 'authorization: Bearer <API_KEY>' \
--header 'Content-Type: application/json' \
--data '{
  "input": {
    "prompt": "Nestled within the depths of an enchanted forest, a wooden bridge serves as a pathway lined with glowing lanterns, casting a warm, golden light across its surface. Surrounded by dense trees, the bridge is carpeted with fallen leaves, adding to the mystical ambiance of the setting. The air seems filled with a magical mist, enhancing the dreamlike quality of the forest, inviting onlookers into a tranquil, otherworldly journey.",
    "image_size": { "width": 1024, "height": 1024},
    "num_inference_steps": 15,
    "num_images": 2,
    "seed": 123456789,
    "output_format": "jpeg",
    "output_quality": 90
  }
}'

Input Parameters

Example Response

After a successful request, the API returns a JSON response with details of the generated images and their respective URLs.

{
  "id": "<task_id>",
  "model": "<model_name>",
  "version": "1",
  "input": {
    "prompt": "Nestled within the depths of an enchanted forest, a wooden bridge serves as a pathway lined with glowing lanterns, casting a warm, golden light across its surface. Surrounded by dense trees, the bridge is carpeted with fallen leaves, adding to the mystical ambiance of the setting. The air seems filled with a magical mist, enhancing the dreamlike quality of the forest, inviting onlookers into a tranquil, otherworldly journey.",
    "image_size": { "width": 1024, "height": 1024},
    "num_inference_steps": 15,
    "num_images": 2,
    "seed": 123456789,
    "output_format": "jpeg",
    "output_quality": 90
  },
  "output": [
    {
      "url": "https://cdn.thehive.ai/generated-image1.jpeg"
    },
    {
      "url": "https://cdn.thehive.ai/generated-image2.jpeg"
    }
  ]
}

View and download your images by using output.url.

Our Available Models

We have five different image generation models available, with additional models to be served in the near future.

Here are the differences between our current model offerings:

Content Moderation

Hive's powerful content moderation is enabled by default on all of our image generation models. When a request is made to our image generation models, it gets passed through two moderation filters. First, the prompt is run through our text moderation model. If the prompt gets flagged, image generation will not occur. If the prompt does not get flagged, the resulting generated images are run through our visual classification model.

If the image generated does not meet our guidelines for text or visual moderation, the task will not be charged, and the following message will be returned.

 { "return_code": 451, "message": "Images did not pass moderation filters.” }

Legacy Support for our Deprecated V2 API

If you’re a legacy user, we’ve included details about our older V2 API. While we recommend upgrading to V3 for the best experience, we’re here to support your existing workflows.

Below are the input fields for an image generation cURL request. The asterisk (*) next to an input field designates that it is required.

text_data*: The text prompt the model uses for image generation.
neg_text: Text prompt where the user can detail aspects that should not be included in the generated image.
num_images: The number of images to generate per request. The default value is 2, with a range of 1 to 6, inclusive.
callback_url: When the task is completed, we will send a callback from our servers to this callback url.

Here is an example of a cURL request using the following format:

curl --location --request POST 'https://api.thehive.ai/api/v2/task/async' \
--header 'authorization: Token <YOUR_TOKEN>' \
--header 'Content-Type: application/json' \
--data-raw '{
  "options": {
    "neg_text": "grass, pool",
    "num_images": 3
  },
  "text_data": "modern architecture house",
  "callback_url": "example_url"
}'

V2 Response

After making an image generation model cURL request, you will receive a response consisting of links to the resulting generated images. To see an example API response for this model, you can visit our V2 API reference page.

Hive makes image generation fast, reliable, and customizable.

Let’s get started—sign up here or contact us for any questions!