Ai Image Generation Deepinfra

AI Image Generation (DeepInfra FLUX-2)

Generate high-quality images using DeepInfra's FLUX-2 model family via an OpenAI-compatible API. No additional subscriptions required — uses your existing DeepInfra API key.

Requirements

• A DeepInfra API key (set as DEEPINFRA_API_KEY environment variable)
• Any HTTP client or OpenAI SDK

Model Tiers

| Model | Quality | Cost | Best For | |-------|---------|------|----------| | black-forest-labs/FLUX-2-max | Best | ~$0.07/image | Final published images, hero art | | black-forest-labs/FLUX-2-dev | Good | ~$0.01/image | Drafts, iterations, social cards | | black-forest-labs/FLUX-2-klein-9b | Fast | ~$0.015/image | Thumbnails, quick previews |

Default to FLUX-2-dev for drafts. Upgrade to FLUX-2-max only for final/published images.

API Reference

Endpoint: https://api.deepinfra.com/v1/openai/images/generations Auth: Authorization: Bearer $DEEPINFRA_API_KEY

Request

{
  "prompt": "Detailed image description",
  "model": "black-forest-labs/FLUX-2-dev",
  "size": "1024x1024",
  "n": 1
}

Response

{
  "created": 1707000000,
  "data": [
    {
      "revised_prompt": "...",
      "b64_json": "/9j/4AAQ..."
    }
  ]
}

Supported Sizes

• 1024x1024 — Square (social media, thumbnails)
• 1536x1024 — Landscape 3:2 (article covers, headers)
• 1024x1536 — Portrait 2:3 (mobile, stories)
• 1920x1080 — Widescreen 16:9 (video thumbnails, banners)

Prompt Engineering

Structure prompts as: {subject}, {style}, {composition}, {lighting}, {color_palette}

Example:
"Close-up of polished gold bars stacked in a vault with soft warm lighting,
professional photography style, shallow depth of field, dark background
with golden amber highlights, 4K quality"

Tips:

• Be specific about style and lighting
• Include negative constraints ("no text", "no watermarks") when needed
• Specify aspect-appropriate composition for the chosen size
• Iterate with FLUX-2-dev before committing to FLUX-2-max

Workflow

1. Craft a detailed prompt for the desired image
2. Generate a draft with FLUX-2-dev (~$0.01)
3. Review and refine the prompt if needed
4. For final use, regenerate with FLUX-2-max (~$0.07)
5. Decode the base64 response and save to your storage backend

Example (Python)

import requests, base64, os

resp = requests.post(
    "https://api.deepinfra.com/v1/openai/images/generations",
    headers={"Authorization": f"Bearer {os.environ['DEEPINFRA_API_KEY']}"},
    json={
        "prompt": "Abstract data visualization with flowing blue particle streams, dark background, modern minimalist style",
        "model": "black-forest-labs/FLUX-2-dev",
        "size": "1536x1024",
        "n": 1,
    },
)

image_data = base64.b64decode(resp.json()["data"][0]["b64_json"])
with open("output.jpg", "wb") as f:
    f.write(image_data)

Example (curl)

curl -X POST https://api.deepinfra.com/v1/openai/images/generations \
  -H "Authorization: Bearer $DEEPINFRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Professional corporate abstract background",
    "model": "black-forest-labs/FLUX-2-dev",
    "size": "1024x1024",
    "n": 1
  }'

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: marketintellabs
• Source: marketintellabs/agent-skills
• License: MIT

Install and usage instructions live in the source repository linked above.