Skip to Content

Image Generation

Generate high-quality images from text prompts using state-of-the-art AI models.

Stable

Overview

elizaOS Cloud provides image generation through multiple providers:

Quick Start

Dashboard

Navigate to Dashboard → Images for the visual interface.

API

curl -X POST "https://cloud.milady.ai/api/v1/generate-image" \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "prompt": "A futuristic cityscape at sunset, cyberpunk style", "model": "google/gemini-2.5-flash-image", "aspectRatio": "16:9", "numImages": 1 }'

Response

{ "images": [ { "url": "https://your-storage.vercel-storage.com/images/abc123.webp", "text": "Optional model response text", "mimeType": "image/webp", "fileSize": 102400 } ], "numImages": 1 }

Available Models

ModelProviderSpeedBest For
`google/gemini-2.5-flash-image`GoogleFastGeneral use (default)
`google/gemini-3.1-flash-image-preview`GoogleFastPreview/testing
`google/gemini-3-pro-image`GoogleMediumHigher quality
`openai/gpt-5-nano`OpenAIMediumOpenAI image generation
`bfl/flux-kontext-max`BFLMediumContext-aware generation

Request Parameters

ParameterTypeRequiredDescription
`prompt`stringText description of the image
`model`stringModel to use (default: `google/gemini-2.5-flash-image`)
`aspectRatio`stringOutput aspect ratio (default: `1:1`)
`numImages`integerNumber of images (1-4, default: 1)
`stylePreset`stringStyle preset to apply
`sourceImage`stringBase64 data URL for image-to-image

Available Aspect Ratios

Aspect RatioDescription
`1:1`Square (default)
`16:9`Wide landscape
`9:16`Tall portrait
`4:3`Standard landscape
`3:4`Standard portrait
`21:9`Ultra-wide cinematic
`9:21`Ultra-tall vertical

Style Presets

PresetDescription
`none`No style modification (default)
`photographic`Realistic lighting and details
`digital-art`Vibrant colors, modern aesthetics
`comic-book`Bold lines, dramatic shading
`fantasy-art`Magical and ethereal elements
`analog-film`Film grain and vintage tones
`neon-punk`Cyberpunk style with neon colors
`cinematic`Dramatic lighting and composition

Image-to-Image Generation

Transform existing images by providing a `sourceImage` parameter:

const response = await fetch("https://cloud.milady.ai/api/v1/generate-image", { method: "POST", headers: { Authorization: "Bearer YOUR_API_KEY", "Content-Type": "application/json", }, body: JSON.stringify({ prompt: "Transform this into a watercolor painting", sourceImage: "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...", }), });

Prompt Engineering

Basic Structure

[Subject] [Style] [Details] [Lighting] [Mood]

Example Prompts

Photorealistic:

{ "prompt": "Professional headshot of a business executive, studio lighting, neutral background, sharp focus", "stylePreset": "photographic" }

Artistic:

{ "prompt": "Enchanted forest with glowing mushrooms, magical atmosphere, soft moonlight filtering through trees", "stylePreset": "fantasy-art" }

Product:

{ "prompt": "Modern smartphone on white background, professional product photography, soft shadows", "aspectRatio": "4:3" }

Best Practices

Error Handling

CodeErrorSolution
400Invalid promptEnsure prompt is non-empty
400Invalid modelUse a supported model
402Insufficient creditsAdd credits to your account
429Rate limitedWait and retry
500Generation failedRetry or try a different model

Next Steps