Api.Airforce
API REFERENCE

Generación de imágenes

Genere y edite imágenes con un punto final unificado y compatible con OpenAI que se distribuye en Flux, Nano-Banana, Wan y más.

POST /v1/images/generations

Compatible con OpenAI images.generate SDK. Los parámetros específicos del proveedor conviven con los estándar: el backend transmite lo que entiende cada modelo.

POSThttps://api.airforce/v1/images/generations

Modelos de imagen

· live

Parámetros comunes

ParameterTypeRequiredDescription
modelstringRequiredImage model ID. Filter /v1/models by output_modalities.includes("image").
promptstringRequiredImage description.
nintegerOptionalNumber of variations to generate per request. Capped by the model's image_caps.max_n.
sizestringOptionalOpenAI-style WxH, e.g. "1024x1024". Provider-specific values pass through.
aspect_ratiostringOptionalAlternative to size. "16:9", "1:1", "9:16", … Validated against image_caps.aspect_ratios.
qualitystringOptional"standard" | "hd" (OpenAI) or model-specific labels. Validated.
response_formatstringOptional"url" (default) or "b64_json".
seedintegerOptionalReproducibility seed. Same prompt + same seed = same image (where the upstream supports it).
input_imagesarrayOptional[{ url? } | { b64_json? }] for image-to-image / reference / first-frame.
ssebooleanOptionalWhen true the response is sent as Server-Sent Events. The full JSON arrives in one event followed by [DONE]. Useful to keep long upstream renders from timing out at proxies.

Ejemplo básico

curl https://api.airforce/v1/images/generations \
  -H "Authorization: Bearer sk-air-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-2-dev",
    "prompt": "A cute baby sea otter floating on its back",
    "n": 1,
    "response_format": "url"
  }'

Forma de respuesta

ParameterTypeRequiredDescription
createdintegerOptionalUnix timestamp.
dataarrayOptionalGenerated assets.
data[].urlstringOptionalPre-signed CDN URL when response_format is "url".
data[].b64_jsonstringOptionalBase64-encoded PNG when response_format is "b64_json".
data[].revised_promptstringOptionalSome models rewrite the prompt before generating; the rewritten version is returned here.
{
  "created": 1715000000,
  "data": [{
    "url": "https://cdn.api.airforce/images/abc123.png"
  }]
}

Variante de transmisión

Aprobar sse: true al realizar proxy a través de middleware que tiene tiempos de inactividad ajustados. La respuesta es un evento SSE con el JSON completo, luego [DONE].

data: {"created":1715000000,"data":[{"url":"https://cdn.api.airforce/images/abc123.png"}]}

data: [DONE]

Imagen a imagen y referencia

Modelos con image_caps.max_input_images > 0 aceptar imágenes de referencia. Pase URL o datos codificados en base64.

curl https://api.airforce/v1/images/generations \
  -H "Authorization: Bearer sk-air-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-2-dev",
    "prompt": "Same character, now in a snowy forest",
    "aspect_ratio": "16:9",
    "input_images": [
      {"url": "https://example.com/character.jpg"}
    ]
  }'

Parámetros específicos del modelo

Más allá de los parámetros comunes anteriores, las familias de modelos individuales aceptan extras. Los parámetros desconocidos se envían al canal ascendente tal cual, por lo que cualquier mando específico del proveedor futuro también funcionará sin una actualización del SDK.

Flux

flux-2-klein-4b, flux-2-klein-9b, flux-2-dev

ParameterTypeRequiredDescription
aspect_ratiostringOptional"1:1", "16:9", "9:16", "4:3", "3:4", "21:9", "9:21".
image_urlsarrayOptionalReference images for img2img mode.

Nano-Banana

nano-banana-2, nano-banana-2-search, nano-banana-pro

ParameterTypeRequiredDescription
aspect_ratiostringOptional"1:1", "16:9", "9:16", "4:3".
resolutionstringOptional"512", "1024", "2048".
image_urlsarrayOptionalReference images.

Suno (music via /v1/images/generations)

suno-v4.5, suno-v5 — Suno historically routes through this endpoint. Native music API at /v1/audio/music is preferred for new code.

ParameterTypeRequiredDescription
custombooleanOptionalSwitch from "auto" to fully custom mode.
instrumentalbooleanOptionalSuppress vocals.
stylestringOptionalGenre tag list, e.g. "EDM, Bass".

Descubriendo capacidades

Cada modelo de imagen expone image_caps en /v1/models para que los clientes puedan validar las entradas antes de enviar:

ParameterTypeRequiredDescription
image_caps.max_nintegerOptionalMaximum n per request.
image_caps.aspect_ratiosarrayOptionalAllowed aspect_ratio values.
image_caps.qualitiesarrayOptionalAllowed quality values.
image_caps.sizesarrayOptionalAllowed size values when applicable.
image_caps.max_input_imagesintegerOptional0 = text-only model. Higher = supports reference images.
image_caps.price_per_image_centsintegerOptionalCost per generated image. Multiply by n for the total request cost.