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
Parameters
| Name | Type | Default | Constraints | Description |
|---|---|---|---|---|
| images *Images | image_upload | — | image/* · 1–10 items | List of URLs of input images for editing. |
| prompt *Prompt | textarea | — | ≤ 5000 chars | The positive prompt for the generation. |
| nImage Count | slider | 1 | 1 ~ 10 | The number of images to generate (1-10). Each image is billed separately. |
| aspect_ratioAspect Ratio | select | — | 1:1 | 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. |
| resolutionResolution | select | — | 1k | 2k | 4k | Output resolution level. Ignored if 'size' is specified. |
| sizeSize | text | auto | — | Specific image resolution. The format is [width]x[height]. If specified, aspect_ratio and resolution will be ignored. |
| qualityQuality | select | auto | auto | low | medium | high | Rendering quality. Higher quality costs more and takes longer. |
| maskMask Image | image_upload | — | image/* · 0–1 items | Reference an input image by URL. Provide exactly one. |
| backgroundBackground | select | auto | auto | transparent | opaque | Background behavior for generated image output. |
| input_fidelityInput Fidelity | select | low | low | high | Controls fidelity to the original input image(s). |
| output_formatOutput Format | select | png | png | jpeg | webp | The format of the output image. JPEG is faster for low latency. |
| output_compressionCompression | number | — | 0 ~ 100 | Compression level, only valid for JPEG/WebP (0-100). |
| moderationModeration | select | auto | auto | low | Content moderation level. |
Output fields
| Field | Type | Description |
|---|---|---|
| images | array<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
| Parameter | Type | Required | Default | Options | Description |
|---|---|---|---|---|---|
images | Array | Yes | N/A | N/A | List of URLs of input images for editing. |
prompt | String | Yes | N/A | N/A | Text description of the desired edit. |
aspect_ratio | String | No | Auto-detect | 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 | Aspect ratio of the generated image. Auto-detected from input image if not specified. |
resolution | String | No | 1k | 1k, 2k | Resolution of the output image. |
quality | String | No | Medium | Low, Medium, High | Quality 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
| Model | Modality | Input | Cached input | Output |
|---|---|---|---|---|
| gpt-image-2 | Image | $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
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.
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.
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.
Nami Z-Image T2I Spicy
Generate an image from a text prompt with configurable width, height, prompt enhancement, and seed.
Nano Banana Text to Image
Gemini 2.5 Flash Image. Lightweight and fast. The most affordable option for instant, high-volume generation.
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.
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.
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.