Tag

Model Terkait

GPT Image 2.6

Bangun dengan CometAPIButuh satu API untuk banyak model?Uji alur kerja di Playground, lalu buat API key saat model dan biayanya sesuai dengan use case Anda.

guide/Riset CometAPI

Cara Menggunakan API GPT Image 2.6: Pembuatan SVG dan Pengeditan Gambar

Pelajari alur kerja API GPT Image 2.6 dengan CometAPI: pembuatan SVG, PNG transparan, pengeditan multi-gambar, markup, parameter, penetapan harga, dan migrasi.

Deon GoodwinTim riset model AI dan API

Diperbarui Nov 6, 2026 11 menit baca

Cara Menggunakan API GPT Image 2.6: Pembuatan SVG dan Pengeditan Gambar

Gunakan pola ini

Lakukan API call pertama.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_COMETAPI_KEY",
    base_url="https://api.cometapi.com/v1",
)

response = client.chat.completions.create(
    model="gpt-5-mini",
    messages=[{"role": "user", "content": "Build this workflow."}],
)

print(response.choices[0].message.content)

TL;DR

GPT Image 2.6 API di CometAPI memberi pengembang jalur praktis untuk pembuatan dan pengeditan gambar dengan dua varian: Sunburst dan Flare.

Bangun aset gambar dengan Python dan kunci CometAPI: mulai dengan permintaan raster, lalu tambahkan output SVG, gambar referensi, atau lapisan anotasi PNG transparan saat rute Anda mendukungnya. Contoh menggunakan Python 3.10 atau lebih baru dan menyimpan kunci API di server Anda.

Perbedaan paling penting: output PNG transparan adalah aset final; file markup PNG transparan adalah input yang memberi tahu model di mana harus mengedit.

Key Takeaways

Gunakan GPT Image 2.6 Flare untuk draf cepat dan Sunburst untuk revisi terperinci.
Kirim permintaan generasi dan permintaan edit ke endpoint Image API masing-masing.

Lanjut belajar

Hubungkan artikel ini ke keputusan berikutnya.

Lihat semua topik

Panduan API AI

Beralih dari shortlist model ke request produksi yang berfungsi.

Infrastruktur LLM

Bangun lapisan permintaan AI yang tetap bertahan saat provider dan model berubah.

Agen AI

Beralih dari demo prompt ke alur kerja agen yang dapat diamati.

Optimasi Biaya

Menurunkan biaya tanpa menutupi trade-off kualitas atau keandalan.

Dipublikasikan pada Nov 6, 2026

Terakhir diperbarui Nov 6, 2026

8 tampilan

Ditinjau untuk kejelasan, atribusi sumber, dan terminologi API terkini.

Spesifikasi	Sunburst	Flare
Pengenal API	gpt-image-2.6-sunburst	gpt-image-2.6-flare
Fokus utama	Pekerjaan visual terperinci	Iterasi cepat
Modalitas input	Teks dan gambar	Teks dan gambar
Modalitas output	Gambar	Gambar
Titik awal praktis	Aset final dan revisi saksama	Draf dan pengeditan interaktif
Dukungan audio	Tidak	Tidak

Parameter	Permintaan generasi	Penggunaan praktis
model	Pengenal varian eksplisit	Jaga pemilihan model dapat direproduksi
prompt	Instruksi teks	Jelaskan aset dan batasannya
quality	Mulai dari low, medium, atau high	Sesuaikan kualitas rendering
complexity	low, medium, atau high	Sesuaikan upaya perencanaan
size	Misalnya, 1024x1024	Tetapkan dimensi untuk perbandingan
n	Gunakan 1 terlebih dahulu	Sederhanakan pengujian dan tinjauan biaya
output_format	PNG, JPEG, WebP, SVG, atau GIF, sesuai dukungan endpoint	Cocokkan dengan aset tujuan
background	auto, opaque, atau transparent	Kendalikan perilaku latar belakang raster

pip install requests pillow

export COMETAPI_KEY="YOUR_COMETAPI_KEY"

$env:COMETAPI_KEY = "YOUR_COMETAPI_KEY"

import base64
import os
from pathlib import Path
import requests

BASE_URL = "https://api.cometapi.com/v1"
HEADERS = {"Authorization": f"Bearer {os.environ['COMETAPI_KEY']}"}
MODEL = "gpt-image-2.6-flare"

def save_result(response, destination):
    response.raise_for_status()
    payload = response.json()
    Path(destination).write_bytes(
        base64.b64decode(payload["data"][0]["b64_json"], validate=True)
    )
    print(f"Saved: {destination}; usage: {payload.get('usage', 'Not returned')}")

def generate(prompt, destination, **options):
    response = requests.post(
        f"{BASE_URL}/images/generations", headers=HEADERS,
        json={"model": MODEL, "prompt": prompt, "n": 1, "size": "1024x1024",
              "quality": "medium", "complexity": "low", **options},
        timeout=(15, 300),
    )
    save_result(response, destination)

generate(
    prompt=(
        "Create a studio product photograph of an unbranded teal "
        "ceramic travel cup on a warm cream background. "
        "Show one cup, a clean silhouette, and a soft contact shadow. "
        "No text or decorative objects."
    ),
    destination="cup.png",
    output_format="png",
)

generate(
    prompt=(
        "Design an original minimalist icon of a teal travel cup "
        "with a small leaf motif. Use simple closed vector shapes, "
        "two flat colors, and generous negative space. "
        "No text, gradients, photographs, or background scenery."
    ),
    destination="cup-icon.svg",
    output_format="svg",
)

generate(
    prompt=(
        "Create a single teal ceramic travel cup as an isolated "
        "e-commerce asset. Center the entire cup with generous padding. "
        "Keep clean edges and a fully transparent background. "
        "No floor, backdrop, checkerboard pattern, or text."
    ),
    destination="cup-transparent.png",
    output_format="png",
    background="transparent",
)

from PIL import Image

with Image.open("cup-transparent.png") as image:
    alpha = image.convert("RGBA").getchannel("A")
    minimum, maximum = alpha.getextrema()

    if minimum == 255:
        raise RuntimeError("The output contains no transparent pixels.")

    if maximum == 0:
        raise RuntimeError("The output is entirely transparent.")

    print("The output contains visible content and transparency.")

with (
    open("product.png", "rb") as product,
    open("setting.png", "rb") as setting,
):
    response = requests.post(
        f"{BASE_URL}/images/edits",
        headers=HEADERS,
        data={
            "model": "gpt-image-2.6-sunburst",
            "prompt": (
                "Use the cup in the first image as the exact product "
                "reference. Use the second image only for the setting. "
                "Place the cup naturally in that setting. Preserve its "
                "silhouette, lid, color, and printed details. "
                "Do not copy other products from the second image."
            ),
            "quality": "high",
            "complexity": "medium",
            "output_format": "png",
        },
        files=[
            ("image[]", ("product.png", product, "image/png")),
            ("image[]", ("setting.png", setting, "image/png")),
        ],
        timeout=(15, 300),
    )

save_result(response, "product-in-setting.png")

from PIL import Image, ImageDraw, ImageOps

with Image.open("product.png") as source:
    oriented = ImageOps.exif_transpose(source).convert("RGBA")
    oriented.save("product-oriented.png")

overlay = Image.new("RGBA", oriented.size, (0, 0, 0, 0))
draw = ImageDraw.Draw(overlay)

width, height = oriented.size
region = (
    int(width * 0.25),
    int(height * 0.15),
    int(width * 0.75),
    int(height * 0.85),
)

draw.ellipse(region, outline=(255, 0, 0, 255), width=6)
overlay.save("markup.png")

with (
    open("product-oriented.png", "rb") as source,
    open("markup.png", "rb") as markup,
):
    response = requests.post(
        f"{BASE_URL}/images/edits",
        headers=HEADERS,
        data={
            "model": MODEL,
            "prompt": (
                "Change the body of the cup inside the red circle "
                "to matte cobalt blue. Preserve the lid, shape, "
                "lighting, and surrounding scene. "
                "Remove the annotation from the finished image."
            ),
            "quality": "medium",
            "complexity": "low",
            "output_format": "png",
        },
        files={
            "image": ("product.png", source, "image/png"),
            "markup": ("markup.png", markup, "image/png"),
        },
        timeout=(15, 300),
    )

save_result(response, "cup-edited.png")

Kategori token	Tarif Sunburst per 1M token	Tarif Flare per 1M token
Text input	$5.00	$5.00
Cached text input	$1.25	$1.25
Image input	$8.00	$8.00
Cached image input	$2.00	$2.00
Image output	$30.00	$30.00

Cost =
(text input tokens × $5
 + image input tokens × $8
 + image output tokens × $30)
÷ 1,000,000

Cost per accepted asset =
total workflow spending ÷ number of approved assets

GPT Image 2.6

GPT Image 2.6

Baca Selengkapnya

Cara Menggunakan API GPT Image 2.6: Pembuatan SVG dan Pengeditan Gambar

Lakukan API call pertama.

TL;DR

Key Takeaways

Hubungkan artikel ini ke keputusan berikutnya.

What Is the GPT Image 2.6 API?

What Parameters Does the GPT Image 2.6 API Support?

How Do You Use GPT Image 2.6 API with CometAPI?

Install the dependencies

Create shared request helpers

Generate a first image

How Do You Generate SVG with GPT Image 2.6?

How Do You Create Transparent PNG Assets with GPT Image 2.6?

How Do You Edit Images with Multiple GPT Image 2.6 References?

How Does Transparent PNG Markup Work in GPT Image 2.6?

Prepare an annotation layer

Submit the guided edit

GPT Image 2.6 API Pricing: Token Rates and SVG Costs

How Do You Migrate an Existing Image Workflow to GPT Image 2.6?

Conclusion

FAQ

How should I handle a GPT Image 2.6 request timeout?

Why does my application fail to save the returned image?

How can I keep edit files from being overwritten?

What should I check before embedding a generated SVG?