🚀

External Model - Image Generation - GPT Image

🛠

Image Generation & Editing via OpenAI's GPT Image

Generate new images from text or edit existing ones with natural-language instructions inside a CNAPS Studio flow. Four tiers — from next-gen gpt-image-2.0 to cost-efficient gpt-image-1-mini — let you match quality to budget. Runs on OpenAI's servers via API.

🔑 Requires a OpenAI API key

What it does

This node connects your CNAPS Studio flows to OpenAI's GPT Image models through the OpenAI API. Use it to generate images from text prompts or to edit an input image with natural-language direction — subject, lighting, mood, style references. It works with or without an input image, and because generation runs on OpenAI's servers, you get top-tier quality without hosting any model locally.

Problem it solves

  • Generation and editing in one node — The same node handles text-to-image generation and instruction-based editing of an input image; your flow decides which by whether an image is connected.
  • Quality/cost tiers without flow changes — Swap between gpt-image-2.0 (top quality), gpt-image-1.5 (precise, fast editing), gpt-image-1 (high fidelity), and gpt-image-1-mini (high-volume, cost-efficient) as needs change.
  • Production-ready output control — Transparent backgrounds, output format (jpeg/png/webp), and quality levels are node settings, so assets drop straight into downstream steps without conversion.

Configuring the Node

Basic Settings

Model name

Model
Best For
gpt-image-2.0
Next-gen quality, top-tier generation and editing
gpt-image-1.5
Precise editing, fast production-quality images
gpt-image-1
High-fidelity generation, image editing
gpt-image-1-mini
Cost-efficient, high-volume image tasks

System prompt or instruction for image generation/editing

  • Your main instruction for what to generate or how to edit. Supports natural language including lighting, mood, and style references.
  • Works with or without an input image.

Aspect ratio of the generated image

  • auto, 1024x1024, 1536x1024, 1024x1536

Advanced Options

  • Background transparency: auto, transparent, opaque
  • Image quality: high, medium, low
  • Output file format: jpeg, png, webp
  • Content filtering: auto, low

How GPT Image compares

GPT Image is one of two external image generation options in CNAPS Studio:

GPT Image
Nano Banana
Provider
OpenAI
Google
Best for
Precise editing, production-quality generation, tiered cost control
Fast everyday images, studio-quality output, text & infographics
Size control
Pixel presets (1024x1024 …) + auto
Aspect ratios (1:1, 16:9, 9:16, 4:3, 3:4)
Transparency control
✅ (auto / transparent / opaque)
❌
Output format control
✅ (jpeg / png / webp)
❌
Sampling temperature
❌
✅ (0.0 – 2.0)

Both run inside CNAPS Studio — compare outputs side-by-side, or chain them into a larger pipeline.

Compliance & Provenance

Provider
OpenAI
Provider type
GPAI — General-Purpose AI (GPAI)
License
OpenAI Commercial Terms
EU AI Act risk class
Limited Risk
Art. 50 transparency
Required — outputs are marked. See AI Policy §2.
Region availability
Available globally
Training data summary
Provider model card / training data

For more on how we classify models and mark outputs, see our AI Policy.

Run it now