GPT Image 2 API

import sys

import numpy as np
from PIL import Image, ImageFilter


def round_trip_psnr(img):
    w, h = img.size
    back = img.resize((w // 2, h // 2), Image.LANCZOS).resize((w, h), Image.LANCZOS)
    mse = np.mean((np.asarray(img, dtype=np.float64) - np.asarray(back, dtype=np.float64)) ** 2)
    return float("inf") if mse == 0 else 10 * np.log10(255**2 / mse)


def most_detailed_quarter(img):
    w, h = img.size
    cw, ch = w // 2, h // 2
    edges = np.asarray(img.convert("L").filter(ImageFilter.FIND_EDGES), dtype=np.float64)
    best, box = -1.0, (0, 0, cw, ch)
    for y in range(0, h - ch + 1, h // 8):
        for x in range(0, w - cw + 1, w // 8):
            score = edges[y:y + ch, x:x + cw].mean()
            if score > best:
                best, box = score, (x, y, x + cw, y + ch)
    return box


image = Image.open(sys.argv[1]).convert("RGB")
box = most_detailed_quarter(image)
print(f"whole image PSNR      = {round_trip_psnr(image):.1f} dB")
print(f"detailed quarter PSNR = {round_trip_psnr(image.crop(box)):.1f} dB")

python3 check_4k.py image.png
c2patool image.png

export LAOZHANG_API_KEY="YOUR_LAOZHANG_API_KEY"

curl https://api.laozhang.ai/v1/images/generations \
  --max-time 600 \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2-vip",
    "prompt": "A product photo of a ceramic mug on a wooden desk, morning light, a small handwritten label on the mug",
    "size": "3840x2160",
    "quality": "high",
    "response_format": "b64_json"
  }' \
  -o gpt-image-2-4k.json

import base64
import os

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["LAOZHANG_API_KEY"],
    base_url="https://api.laozhang.ai/v1",
    timeout=600,
)

result = client.images.generate(
    model="gpt-image-2-vip",
    prompt="A product photo of a ceramic mug on a wooden desk, morning light",
    size="3840x2160",
    quality="high",
    response_format="b64_json",
)

with open("gpt-image-2-4k.png", "wb") as f:
    f.write(base64.b64decode(result.data[0].b64_json))

import { writeFile } from "node:fs/promises";

const response = await fetch("https://api.laozhang.ai/v1/images/generations", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${process.env.LAOZHANG_API_KEY}`,
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "gpt-image-2-vip",
    prompt: "A product photo of a ceramic mug on a wooden desk, morning light",
    size: "3840x2160",
    quality: "high",
    response_format: "b64_json"
  }),
  signal: AbortSignal.timeout(600_000)
});

if (!response.ok) throw new Error(`HTTP ${response.status}: ${await response.text()}`);
const { data } = await response.json();
await writeFile("gpt-image-2-4k.png", Buffer.from(data[0].b64_json, "base64"));