Beeldgeneratie
Genereer en bewerk afbeeldingen via één OpenAI-compatibel eindpunt. Dezelfde verzoekvorm bereikt elk afbeeldingsmodel in de catalogus.
Eén OpenAI-compatibel image-endpoint verdeelt naar Flux, Nano-Banana, Wan en andere providers. Stuur dezelfde request-shape ongeacht de upstream; provider-specifieke opties gaan door en worden gevalideerd tegen de capabilities van elk model.
Ontdek image-modellen door het models-endpoint op te vragen en degene te behouden waarvan de output-modalities image bevatten.
POST /v1/images/generations
Drop-in compatibel met de OpenAI images.generate SDK. Provider-specifieke parameters leven naast de standaardparameters: de backend geeft door wat elk model begrijpt.
https://api.airforce/v1/images/generationsBeeldmodellen
…· liveGemeenschappelijke parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
| model | string | Required | Image model ID. Find them on /v1/models: image models carry media_type: "image" and an image_caps block. |
| prompt | string | Required | Image description. |
| n | integer | Optional | Number of variations to generate per request. Capped by the model's image_caps.max_n. |
| size | string | Optional | OpenAI-style WxH, e.g. "1024x1024". Provider-specific values pass through. |
| aspect_ratio | string | Optional | Alternative to size. "16:9", "1:1", "9:16", … Validated against image_caps.aspect_ratios. |
| quality | string | Optional | "standard" | "hd" (OpenAI) or model-specific labels. Validated. |
| response_format | string | Optional | "url" (default) or "b64_json". |
| seed | integer | Optional | Reproducibility seed. Same prompt + same seed = same image (where the upstream supports it). |
| input_images | array | Optional | [{ url? } | { b64_json? }] for image-to-image / reference / first-frame. |
| sse | boolean | Optional | When 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. |
Eenvoudig voorbeeld
curl https://api.airforce/v1/images/generations \
-H "Authorization: Bearer sk-air-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nano-banana-2",
"prompt": "A cute baby sea otter floating on its back",
"n": 1,
"response_format": "url"
}'Reactie vorm
| Parameter | Type | Required | Description |
|---|---|---|---|
| created | integer | Optional | Unix timestamp. |
| data | array | Optional | Generated assets. |
| data[].url | string | Optional | Image URL when response_format is "url" (default). The image is re-hosted to a file host and the link ends in /image.jpeg; null if the re-host fails. |
| data[].b64_json | string | Optional | Base64-encoded image bytes when response_format is "b64_json". The format follows the upstream provider (often JPEG), not necessarily PNG. |
{
"created": 1715000000,
"data": [{
"url": "https://.../image.jpeg"
}]
}Streaming-variant
Doorgang sse: true bij proxying via middleware met krappe time-outs voor inactiviteit. Het antwoord is dan één SSE-gebeurtenis met de volledige JSON [DONE].
data: {"created":1715000000,"data":[{"url":"https://.../image.jpeg"}]}
data: [DONE]Afbeelding-naar-afbeelding en referentie
Modellen met image_caps.max_input_images > 0 accepteer referentieafbeeldingen. Geef URL's of base64-gecodeerde gegevens door.
curl https://api.airforce/v1/images/generations \
-H "Authorization: Bearer sk-air-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nano-banana-2",
"prompt": "Same character, now in a snowy forest",
"aspect_ratio": "16:9",
"input_images": [
{"url": "https://example.com/character.jpg"}
]
}'Afbeeldingen bewerken
Het OpenAI-compatibele edit-endpoint. Stuur de bronafbeelding als multipart-bestand, zoals de OpenAI-SDK’s doen voor images.edit, of stuur de JSON-body van hierboven met input_images. Het volgt hetzelfde pad als /v1/images/generations: dezelfde modellen, prijzen en hetzelfde antwoordformaat.
https://api.airforce/v1/images/edits| Parameter | Type | Required | Description |
|---|---|---|---|
| model | string | Required | An image model with image_caps.max_input_images > 0 (see Discovering capabilities below). |
| prompt | string | Required | What to change or create from the input image(s). |
| image | file | Required | The source image. Repeat as image[] for several references; images, images[] and input_images are accepted too, as files or as image URLs. |
| mask | file | Optional | Forwarded as is, but no listed model declares mask support, so the serving model may ignore it. |
| n | integer | Optional | Number of images to generate. |
| size | string | Optional | Output size, e.g. "1024x1024", where the model supports it. |
| aspect_ratio | string | Optional | Output aspect ratio, e.g. "16:9", where the model supports it. |
| quality | string | Optional | Model-specific quality level. |
| response_format | string | Optional | "url" or "b64_json", as on /v1/images/generations. |
curl https://api.airforce/v1/images/edits \
-H "Authorization: Bearer sk-air-YOUR_API_KEY" \
-F "model=nano-banana-2" \
-F "prompt=Same character, now in a snowy forest" \
-F "[email protected]" \
-F "aspect_ratio=16:9"from openai import OpenAI
client = OpenAI(base_url="https://api.airforce/v1", api_key="sk-air-YOUR_API_KEY")
with open("character.png", "rb") as image:
result = client.images.edit(
model="nano-banana-2",
image=image,
prompt="Same character, now in a snowy forest",
)
print(result.data[0].url)Tot 16 invoerafbeeldingen per verzoek, elk 25 MB; de eigen limiet van het model staat in image_caps.max_input_images. Een verzoek zonder invoerafbeelding wordt met 400 geweigerd in plaats van een tekst-naar-afbeelding-aanroep te worden. Elke invoerafbeelding kan de prijs verhogen, zoals op de modelpagina staat.
Modelspecifieke parameters
Naast de bovenstaande gemeenschappelijke parameters accepteren individuele modelfamilies extra's. Onbekende parameters worden as-is doorgestuurd naar de upstream, dus elke toekomstige providerspecifieke knop werkt ook zonder SDK-update.
Nano-Banana
nano-banana-2, nano-banana-pro
| Parameter | Type | Required | Description |
|---|---|---|---|
| aspect_ratio | string | Optional | "1:1", "16:9", "9:16", "4:3". |
| resolution | string | Optional | "512", "1024", "2048". |
| image_urls | array | Optional | Reference images. |
Suno (music)
suno-v4.5, suno-v5 en suno-v5.5 werden hier historisch geaccepteerd. Ze horen nu bij de native muziek-API op /v1/audio/music — aanroepen hier worden geweigerd met `wrong_endpoint`.
Mogelijkheden ontdekken
Elk beeldmodel legt bloot image_caps op /v1/models zodat klanten de invoer kunnen valideren voordat ze het volgende verzenden:
| Parameter | Type | Required | Description |
|---|---|---|---|
| image_caps.max_n | integer | Optional | Maximum n per request. |
| image_caps.aspect_ratios | array | Optional | Allowed aspect_ratio values. |
| image_caps.qualities | array | Optional | Allowed quality values. |
| image_caps.max_input_images | integer | Optional | 0 = text-only model. Higher = supports reference images. |
| image_caps.supports_url_input | boolean | Optional | Whether input_images may be passed as URLs (vs base64). |
| image_caps.supports_seed | boolean | Optional | Whether the model honours a seed value (most scraping-proxy upstreams ignore it). |
Image-prijzen staan niet op image_caps — gebruik de prijsvelden van het model op /v1/models voor de kosten.