OpenAI GPT Image 2 Edit

openai/gpt-image-2/edit

OpenAI's GPT Image 2 Edit enables image editing from natural-language instructions with one or more reference images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Examples

OpenAI GPT Image 2 Edit example 1

Parameters

NameTypeDefaultConstraintsDescription
images *Imagesimage_uploadimage/* · 1–10 itemsList of URLs of input images for editing.
prompt *Prompttextarea≤ 5000 charsThe positive prompt for the generation.
nImage Countslider11 ~ 10The number of images to generate (1-10). Each image is billed separately.
aspect_ratioAspect Ratioselect1:1 | 1:2 | 1:3 | 2:1 | 2:3 | 3:1 | 3:2 | 3:4 | …The aspect ratio of the generated image. Ignored if 'size' is specified.
resolutionResolutionselect1k | 2k | 4kOutput resolution level. Ignored if 'size' is specified.
sizeSizetextautoSpecific image resolution. The format is [width]x[height]. If specified, aspect_ratio and resolution will be ignored.
qualityQualityselectautoauto | low | medium | highRendering quality. Higher quality costs more and takes longer.
maskMask Imageimage_uploadimage/* · 0–1 itemsReference an input image by URL. Provide exactly one.
backgroundBackgroundselectautoauto | transparent | opaqueBackground behavior for generated image output.
input_fidelityInput Fidelityselectlowlow | highControls fidelity to the original input image(s).
output_formatOutput Formatselectpngpng | jpeg | webpThe format of the output image. JPEG is faster for low latency.
output_compressionCompressionnumber0 ~ 100Compression level, only valid for JPEG/WebP (0-100).
moderationModerationselectautoauto | lowContent moderation level.

Output fields

FieldTypeDescription
imagesarray<string>

API

Call this model through one unified REST API. Get a key on the API Keys page.

cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/openai/gpt-image-2/edit" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "images": [
      "https://assets-public.namifusion.com/uploads/images/2026-04-24/b96da2a48506.png",
      "https://assets-public.namifusion.com/uploads/images/2026-04-24/4831013a68e1.png"
    ],
    "prompt": "A futuristic cityscape at sunset, with glowing skyscrapers and flying cars.",
    "n": 3,
    "aspect_ratio": "16:9",
    "resolution": "4k",
    "size": "1024x1024",
    "quality": "high",
    "background": "auto",
    "input_fidelity": "low",
    "output_format": "jpeg",
    "output_compression": 85,
    "moderation": "auto"
  }
}'

# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
  -H "Authorization: Bearer YOUR_API_KEY"
Python
import time, requests

API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}

# 1) Submit
resp = requests.post(
    "https://www.namifusion.com/api/v1/marketplace/run/openai/gpt-image-2/edit",
    headers=HEADERS,
    json={
        "input": {
            "images": [
                "https://assets-public.namifusion.com/uploads/images/2026-04-24/b96da2a48506.png",
                "https://assets-public.namifusion.com/uploads/images/2026-04-24/4831013a68e1.png"
            ],
            "prompt": "A futuristic cityscape at sunset, with glowing skyscrapers and flying cars.",
            "n": 3,
            "aspect_ratio": "16:9",
            "resolution": "4k",
            "size": "1024x1024",
            "quality": "high",
            "background": "auto",
            "input_fidelity": "low",
            "output_format": "jpeg",
            "output_compression": 85,
            "moderation": "auto"
        }
    },
)
resp.raise_for_status()  # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()

# 2) Poll until a terminal state (completed / failed / cancelled).
#    This model is allowed up to 600s server-side.
deadline = time.time() + 660
while task.get("status") not in ("completed", "failed", "cancelled"):
    if time.time() > deadline:
        raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
    time.sleep(3)
    poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
    poll.raise_for_status()
    task = poll.json()

print(task["status"], task.get("output"))
JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };

// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/openai/gpt-image-2/edit", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "images": [
        "https://assets-public.namifusion.com/uploads/images/2026-04-24/b96da2a48506.png",
        "https://assets-public.namifusion.com/uploads/images/2026-04-24/4831013a68e1.png"
      ],
      "prompt": "A futuristic cityscape at sunset, with glowing skyscrapers and flying cars.",
      "n": 3,
      "aspect_ratio": "16:9",
      "resolution": "4k",
      "size": "1024x1024",
      "quality": "high",
      "background": "auto",
      "input_fidelity": "low",
      "output_format": "jpeg",
      "output_compression": 85,
      "moderation": "auto"
    }
  }),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();

// 2) Poll until a terminal state (completed / failed / cancelled).
//    This model is allowed up to 600s server-side.
const deadline = Date.now() + 660 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
  if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
  await new Promise((r) => setTimeout(r, 3000));
  const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
  if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
  task = await poll.json();
}

console.log(task.status, task.output);

Documentation

OpenAI GPT Image 2 Edit

Effortless Image Editing with Natural Language Instructions

OpenAI GPT Image 2 Edit is a cutting-edge text-to-image model designed for seamless image editing using natural-language instructions. By leveraging one or more reference images, this model delivers high-quality edits with strong prompt alignment, production-ready results, and flexible aspect ratio options. With its ready-to-use REST API, developers can integrate it into creative workflows without cold start delays.


🚀 Key Features

  • Natural-Language Image Editing: Modify images by describing changes in plain language—no manual masking or complex editing required.
  • Reference Image Support: Use one or more input images as the visual source for edits, transformations, or style adjustments.
  • Flexible Aspect Ratios: Generate outputs in square, portrait, landscape, or widescreen formats to suit diverse design needs.
  • Production-Ready API: Access a robust REST API for easy integration into applications, tools, and creative pipelines.
  • Fast and Affordable: Enjoy high-quality image edits with usage-based pricing and no cold-start friction.

🛠️ Technical Specifications

ParameterTypeRequiredDefaultOptionsDescription
imagesArrayYesN/AN/AList of URLs of input images for editing.
promptStringYesN/AN/AText description of the desired edit.
aspect_ratioStringNoAuto-detect1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9Aspect ratio of the generated image. Auto-detected from input image if not specified.
resolutionStringNo1k1k, 2kResolution of the output image.
qualityStringNoMediumLow, Medium, HighQuality of the generated image. Higher quality costs more.

Example Prompt

Turn this product photo into a premium studio advertisement with soft cinematic lighting, a clean beige background, subtle shadows, realistic reflections, and luxury brand aesthetics.


💰 Pricing

ModelModalityInputCached inputOutput
gpt-image-2Image$8.00$2.00$30.00
Text$5.00$1.25-

💡 Best Use Cases

  • Product Photo Enhancement: Transform basic product shots into premium marketing visuals.
  • Creative Retouching: Modify backgrounds, lighting, styling, or composition using natural-language instructions.
  • Marketing Adaptation: Rework existing brand assets into new campaign visuals without recreating them from scratch.
  • Social Media Content: Edit images into platform-ready formats for posts, ads, and promos.
  • Design Iteration: Explore multiple visual directions from the same base image with different prompts.
  • E-Commerce Optimization: Improve product presentation for listings, hero banners, and promotional creatives.

🔗 Related Models

  • OpenAI GPT Image 2 Text-to-Image: Generate new images directly from natural-language prompts.

Pro Tip: Be specific about what should stay unchanged and what should be modified. Mention visual styles, lighting, and mood clearly for optimal results.


Related models

xAI Grok Imagine Image v2.0 Text to Image
Text to ImageX Ai

xAI Grok Imagine Image v2.0 Text to Image

xAI Grok Imagine Image V2.0 Text-to-Image generates high-quality images from text prompts, with configurable aspect ratio, resolution, and quality for creative visuals, social content, marketing assets, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

from $0.080 / per run
Qwen Image 3.0 Pro Text to Image
Text to ImageQwen Image 3.0 Pro

Qwen Image 3.0 Pro Text to Image

Qwen Image 3.0 Pro is a professional-grade text-to-image model with superior quality and advanced prompt understanding. Up to 2k. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

from $0.080 / per run
OpenAI GPT Image 2 Text-to-Image
Text to ImageOpenAI

OpenAI GPT Image 2 Text-to-Image

OpenAI's GPT Image 2 Text-to-Image generates high-quality images from natural-language prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

from $0.660 / per run
Nami Z-Image T2I Spicy
Text to Image

Nami Z-Image T2I Spicy

Generate an image from a text prompt with configurable width, height, prompt enhancement, and seed.

from $0.020 / per run
Nano Banana Text to Image
Text to ImageGoogle

Nano Banana Text to Image

Gemini 2.5 Flash Image. Lightweight and fast. The most affordable option for instant, high-volume generation.

from $0.040 / per run
Nano Banana Pro Text to Image
Text to ImageGoogle

Nano Banana Pro Text to Image

Gemini 3.0 Pro Image. The high-fidelity choice for 4K visuals, multilingual text rendering, and pro camera controls.

from $0.140 / per run
Nano Banana Pro Text to Image
Text to ImageGoogle

Nano Banana Pro Text to Image

Gemini 3.0 Pro Image. The high-fidelity choice for 4K visuals, multilingual text rendering, and pro camera controls.

from $0.070 / per run
Google Nano Banana Lite Text to Image API
Text to ImageGoogle

Google Nano Banana Lite Text to Image API

Google Nano Banana 2 Lite Text to Image generates high-quality images from text prompts with low latency, flexible aspect ratios, and fast image creation for creative and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

from $0.040 / per run