Langsung ke konten utama
POST
/
v1
/
images
/
generations
curl --request POST \
  --url https://api.cometapi.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-image-2",
  "prompt": "A paper boat floating on calm water at sunrise."
}
'
{
  "created": 1776841943,
  "background": "opaque",
  "output_format": "jpeg",
  "quality": "low",
  "size": "1024x1024",
  "usage": {
    "input_tokens": 16,
    "input_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 16
    },
    "output_tokens": 208,
    "total_tokens": 224
  },
  "data": [
    {
      "b64_json": "<base64-image-data>"
    }
  ]
}
Gunakan rute ini untuk membuat gambar dari teks dengan bentuk request yang kompatibel dengan OpenAI di CometAPI.

​
Referensi resmi

​
Pilih model terlebih dahulu

  • Gunakan dall-e-3 saat Anda menginginkan request awal yang sederhana dengan response_format
  • Gunakan model GPT image saat Anda memerlukan kontrol khusus GPT seperti output_format, quality, atau background
  • Gunakan qwen-image saat Anda memerlukan provider tersebut secara spesifik, tetapi biarkan n tetap 1

​
Request awal yang aman

  • Mulai dengan dall-e-3
  • Pertahankan size di 1024x1024
  • Setel response_format: "url" jika Anda menginginkan respons JSON kecil dan URL unduhan sementara
  • Gunakan contoh request GPT yang tervalidasi di referensi API jika Anda memerlukan parameter model GPT image
  • Tambahkan output_format hanya ketika Anda memerlukan tipe gambar terenkode tertentu seperti jpeg
  • Periksa panduan pembuatan gambar OpenAI sebelum Anda menambahkan background, output_compression, atau streaming
  • Gunakan satu prompt dan satu gambar keluaran sebelum Anda menambahkan pembuatan batch atau penyesuaian gaya

​
Perilaku request spesifik model

  • response_format berlaku untuk dall-e-2 dan dall-e-3
  • Model GPT image menggunakan kontrol khusus GPT seperti output_format, quality, background, dan output_compression
  • Ikuti panduan pembuatan gambar OpenAI untuk opsi spesifik model terbaru
  • qwen-image tidak mendukung n > 1
Gambar yang dihasilkan harus mematuhi kebijakan penggunaan provider. Jangan kirim prompt ilegal, penuh kekerasan, pornografis, atau yang melanggar hak cipta.

Otorisasi

​
Authorization
string
header
wajib

Bearer token authentication. Use your CometAPI key.

Body

application/json
​
model
string
default:dall-e-3
wajib

The image generation model to use. Choose a current model from the Models page.

​
prompt
string
wajib

Text description of the image you want to generate.

Contoh:

"A paper boat floating on calm water at sunrise."

​
n
integer
default:1

Number of images to generate. Keep this at 1 for the broadest compatibility.

​
quality
string

Quality setting for models that support it. See the OpenAI image generation guide for the latest model-specific values.

​
size
string

Requested output size. Supported values depend on the selected model. See the OpenAI image generation guide for the latest model-specific ranges.

Contoh:

"1024x1024"

​
response_format
enum<string>

The response container for dall-e-2 and dall-e-3. This parameter is not supported for GPT image models, which return base64-encoded image data.

Opsi yang tersedia:
url,
b64_json
​
output_format
string

The encoded image type for GPT image model results, such as png, jpeg, or webp. See the OpenAI image generation guide for current GPT image output controls.

Contoh:

"jpeg"

Respons

200 - application/json

Image generation result.

​
created
integer
wajib

Unix timestamp for the completed generation.

​
usage
object
wajib
​
data
object[]
wajib
​
background
string

Background mode returned by models that expose it.

​
output_format
string

Encoded image type returned by GPT image models.

​
quality
string

Quality level returned by models that expose it.

​
size
string

Output size returned by models that expose it.