> ## Documentation Index > Fetch the complete documentation index at: https://runcrate.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # AI Image Generation API > Generate images with FLUX, Stable Diffusion, and Ideogram via a single API. Text-to-image, image editing, and batch generation. export const RuncrateStyles = () => { if (typeof document !== 'undefined' && !document.getElementById('runcrate-overrides')) { const s = document.createElement('style'); s.id = 'runcrate-overrides'; s.textContent = ` /* Match Runcrate's rounding scale (--radius: 0.75rem) */ .rounded-sm { border-radius: 0.5rem !important; } /* 8px */ .rounded-md { border-radius: 0.625rem !important; } /* 10px */ .rounded-lg { border-radius: 0.75rem !important; } /* 12px */ .rounded-l-sm { border-top-left-radius: 0.5rem !important; border-bottom-left-radius: 0.5rem !important; } .rounded-r-sm { border-top-right-radius: 0.5rem !important; border-bottom-right-radius: 0.5rem !important; } .rounded-l-md { border-top-left-radius: 0.625rem !important; border-bottom-left-radius: 0.625rem !important; } .rounded-r-md { border-top-right-radius: 0.625rem !important; border-bottom-right-radius: 0.625rem !important; } .rounded-l-lg { border-top-left-radius: 0.75rem !important; border-bottom-left-radius: 0.75rem !important; } .rounded-r-lg { border-top-right-radius: 0.75rem !important; border-bottom-right-radius: 0.75rem !important; } /* Cards: never pure white in light mode */ .card { background-color: #fcfcfc !important; border-radius: 0.75rem !important; } html.dark .card { background-color: #141414 !important; } /* Docs hero box */ .rc-hero { background-color: #fcfcfc; border: 1px solid #e0e0e0; } html.dark .rc-hero { background-color: #141414; border-color: #242424; } html.dark .rc-hero h1 { color: #f5f5f5; } /* Runcrate scrollbar — thin, transparent track, hide-until-hover thumb */ ::-webkit-scrollbar { width: 6px; height: 6px; background-color: transparent; } ::-webkit-scrollbar-track { background-color: transparent; } ::-webkit-scrollbar-thumb { background-color: rgba(155, 155, 155, 0.5); border-radius: 10px; transition: opacity 0.3s ease; opacity: 0; } ::-webkit-scrollbar-thumb:hover { background-color: rgba(155, 155, 155, 0.7); } *:hover::-webkit-scrollbar-thumb, *:focus::-webkit-scrollbar-thumb, *:active::-webkit-scrollbar-thumb { opacity: 1; } * { scrollbar-width: thin; scrollbar-color: rgba(155, 155, 155, 0.5) transparent; } `; document.head.appendChild(s); } return null; }; Generate images from text prompts using FLUX.1, FLUX.2, Stable Diffusion, and Ideogram through a single API. One API key, one endpoint, eight model families — no GPU management. ## Available models | Model | Speed | Quality | Features | | ------------------------ | ------ | --------- | ------------------------------------ | | **FLUX.1 Schnell** | Fast | Good | Text-to-image, best for prototyping | | **FLUX.1 Dev** | Medium | High | Open weights, img2img support | | **FLUX.1 Pro** | Medium | Very High | Production-grade | | **FLUX.1.1 Pro** | Medium | Very High | Updated Pro model | | **FLUX.2 Pro** | Medium | Highest | Up to 4MP, multi-reference images | | **FLUX Kontext** | Medium | High | Image editing with text instructions | | **Stable Diffusion 3.5** | Medium | High | Open weights | | **Ideogram v2** | Medium | High | Best text rendering in images | *** ## Basic text-to-image ```bash curl theme={"theme":"github-dark"} curl https://api.runcrate.ai/v1/images/generations \ -H "Content-Type: application/json" \ -H "Authorization: Bearer rc_live_YOUR_API_KEY" \ -d '{ "model": "black-forest-labs/FLUX.1-schnell", "prompt": "A minimalist product photo of wireless earbuds on a marble surface, soft studio lighting, white background", "aspect_ratio": "1:1" }' ``` ```python Python (OpenAI SDK) theme={"theme":"github-dark"} from openai import OpenAI client = OpenAI( base_url="https://api.runcrate.ai/v1", api_key="rc_live_YOUR_API_KEY", ) response = client.images.generate( model="black-forest-labs/FLUX.1-schnell", prompt="A minimalist product photo of wireless earbuds on a marble surface, soft studio lighting, white background", ) print(response.data[0].url) ``` ```python Python (Runcrate SDK) theme={"theme":"github-dark"} from runcrate import Runcrate client = Runcrate(api_key="rc_live_YOUR_API_KEY") image = client.models.generate_image( model="black-forest-labs/FLUX.1-schnell", prompt="A minimalist product photo of wireless earbuds on a marble surface, soft studio lighting, white background", ) # Save directly to disk image.data[0].save("earbuds.png") ``` ```typescript TypeScript (Runcrate SDK) theme={"theme":"github-dark"} import Runcrate from '@runcrate/sdk'; const rc = new Runcrate({ apiKey: 'rc_live_YOUR_API_KEY' }); const image = await rc.models.generateImage({ model: 'black-forest-labs/FLUX.1-schnell', prompt: 'A minimalist product photo of wireless earbuds on a marble surface, soft studio lighting, white background', }); // Save directly — handles base64, data URIs, and URLs await image.save('earbuds.png'); ``` ```typescript Vercel AI SDK theme={"theme":"github-dark"} import { runcrate } from '@runcrate/ai'; import { generateImage } from 'ai'; const { image } = await generateImage({ model: runcrate.imageModel('black-forest-labs/FLUX.1-schnell'), prompt: 'A minimalist product photo of wireless earbuds on a marble surface, soft studio lighting, white background', size: '1024x1024', }); console.log(image.base64); ``` *** ## Image editing with FLUX Kontext FLUX Kontext models accept an existing image and a text instruction describing the edit. Pass a file path, URL, or base64 string as the `image` parameter. ```python Python theme={"theme":"github-dark"} from runcrate import Runcrate client = Runcrate(api_key="rc_live_YOUR_API_KEY") # Edit an existing image with a text instruction edited = client.models.generate_image( model="black-forest-labs/FLUX.1-kontext-pro", prompt="Change the background to a tropical beach at sunset", image="./product-photo.png", # file path (auto base64-encoded) ) edited.data[0].save("product-beach.png") ``` ```typescript TypeScript theme={"theme":"github-dark"} import Runcrate from '@runcrate/sdk'; const rc = new Runcrate({ apiKey: 'rc_live_YOUR_API_KEY' }); const edited = await rc.models.generateImage({ model: 'black-forest-labs/FLUX.1-kontext-pro', prompt: 'Change the background to a tropical beach at sunset', image: './product-photo.png', // file path (auto base64-encoded) }); await edited.save('product-beach.png'); ``` The `image` field accepts three formats: * **File path** — `"./photo.png"` (auto-detected, read and base64-encoded) * **URL** — `"https://..."` (passed through as-is) * **Base64 string** — raw base64 data (passed through as-is) *** ## Batch generation — product catalog Generate a full set of product images in one script. This example creates hero images for an e-commerce catalog: ```python theme={"theme":"github-dark"} from runcrate import Runcrate client = Runcrate(api_key="rc_live_YOUR_API_KEY") products = [ {"name": "Running Shoe", "prompt": "A sleek running shoe, white background, studio lighting"}, {"name": "Backpack", "prompt": "A modern laptop backpack, minimalist, product photography"}, {"name": "Watch", "prompt": "A luxury watch on marble surface, soft shadows"}, ] for product in products: image = client.models.generate_image( model="black-forest-labs/FLUX.1-schnell", prompt=product["prompt"], ) filename = f"{product['name'].lower().replace(' ', '-')}.png" image.data[0].save(filename) print(f"Saved {filename}") ``` For higher throughput, run generations in parallel: ```python theme={"theme":"github-dark"} from runcrate import Runcrate from concurrent.futures import ThreadPoolExecutor client = Runcrate(api_key="rc_live_YOUR_API_KEY") products = [ {"name": "Running Shoe", "prompt": "A sleek running shoe, white background, studio lighting"}, {"name": "Backpack", "prompt": "A modern laptop backpack, minimalist, product photography"}, {"name": "Watch", "prompt": "A luxury watch on marble surface, soft shadows"}, {"name": "Sunglasses", "prompt": "Designer sunglasses on a reflective surface, dramatic lighting"}, {"name": "Headphones", "prompt": "Over-ear headphones floating, dark background, rim lighting"}, ] def generate(product): image = client.models.generate_image( model="black-forest-labs/FLUX.1-schnell", prompt=product["prompt"], ) filename = f"{product['name'].lower().replace(' ', '-')}.png" image.data[0].save(filename) print(f"Saved {filename}") with ThreadPoolExecutor(max_workers=5) as pool: pool.map(generate, products) print("All product images generated.") ``` *** ## Parameters reference Parameters vary by model. These are the most common: | Parameter | Type | Description | | --------------------- | ------- | ------------------------------------------------------------ | | `model` | string | Model ID (required) | | `prompt` | string | Text description of the image (required) | | `aspect_ratio` | string | Output ratio: `1:1`, `16:9`, `9:16`, `4:3`, `3:2` | | `seed` | integer | Reproducibility seed (omit for random) | | `num_inference_steps` | integer | Number of diffusion steps — more steps = more detail, slower | | `guidance` | number | How closely to follow the prompt | | `negative_prompt` | string | What to avoid in the image | ### Model-specific parameters * **FLUX Kontext models**: Accept `image` for image editing * **FLUX Canny**: Requires `control_image` for edge-guided generation * **FLUX.2 Pro**: Accepts up to 8 `input_images` for reference-based generation * **FLUX Dev/Krea**: Accept `image` for img2img mode with `prompt_strength` control Check the [Playground](/models/playground) to see the exact parameters available for each model. *** ## Next.js API route Add image generation to a web app with a single API route: ```typescript theme={"theme":"github-dark"} // app/api/generate-image/route.ts import { runcrate } from '@runcrate/ai'; import { generateImage } from 'ai'; export async function POST(req: Request) { const { prompt, model, aspectRatio } = await req.json(); const { image } = await generateImage({ model: runcrate.imageModel(model || 'black-forest-labs/FLUX.1-schnell'), prompt, size: aspectRatio === '16:9' ? '1792x1024' : '1024x1024', }); return Response.json({ image: image.base64 }); } ``` Call it from the frontend: ```typescript theme={"theme":"github-dark"} const response = await fetch('/api/generate-image', { method: 'POST', headers: { 'Content-Type': 'application/json' }, body: JSON.stringify({ prompt: 'A mountain landscape at golden hour', model: 'black-forest-labs/FLUX.1-schnell', aspectRatio: '16:9', }), }); const { image } = await response.json(); // image is a base64 string — render it in an tag ``` *** ## Response format All image generation requests return the same shape: ```json theme={"theme":"github-dark"} { "data": [ { "url": "https://...", "b64_json": "..." } ] } ``` The response includes either a `url` to the generated image or `b64_json` base64-encoded image data. The Runcrate SDKs provide a `.save()` helper that handles both formats automatically. *** ## Pricing Image generation pricing varies by model. FLUX.1 Schnell starts at \~\$0.003/image. Higher-quality models like FLUX.2 Pro cost more per generation. Check the [Model Catalog](/models/model-catalog) for current per-model pricing.