Image generation
Available now

GPT Image 1.5

by OpenAI

OpenAI's image model with best‑in‑class text rendering.
Legible signage, precise instruction following, and advanced conversational editing.

GPT Image 1.5

by OpenAI

Key features

Technical specifications

2K

Up to 2K image output

Best

Industry-leading text in images

Advanced

Full image editing capability

2

Text-to-Image, Image-to-Image

Use cases

Design with typography

Posters, signs, menus, labels, anything with text on it. GPT Image 1.5 renders typography legibly and accurately every time.

Marketing materials

Generate campaign visuals with embedded copy, social media graphics, banner ads, and promotional images with readable text overlays.

Precise compositions

When a prompt needs exact placement, specific counts, and tight spatial relationships, the model follows complex instructions faithfully.

Image editing & refinement

Edit existing images with text instructions. Modify elements, adjust composition, fix detail, or restyle, all conversationally.

Product packaging concepts

Generate packaging mockups with accurate brand names, ingredient lists, and label text, ideal for concept work and client reviews.

Educational & infographic content

Create labeled diagrams, annotated images, and infographic-style visuals with correctly rendered text annotations and clear typography.

Prompt examples

Typography design

A vintage movie poster for 'Midnight in Tokyo' with the title in elegant serif font at the top, noir style, dramatic lighting, Japanese cityscape silhouette

Edit prompt

Precise layout

A flat-lay product arrangement with exactly 5 items: coffee cup, leather notebook, fountain pen, sunglasses, and a small potted succulent, top-down view, marble surface

Edit prompt

Product label

A premium olive oil bottle with a clean label reading 'TERRA VERDE Extra Virgin' in sans-serif font, green and gold color scheme, rustic wooden background

Edit prompt

Overview

GPT Image 1.5 is OpenAI's latest image generation model, building on the DALL-E lineage with transformative improvements in text rendering, instruction following, and editing capabilities. Its standout feature is the ability to accurately render legible text within images, making it uniquely suited for design work that includes typography, labels, and embedded copy. When your image needs to include readable text, GPT Image 1.5 is the only model you can reliably trust.

Simple pricing

Get started for free today, with the option to upgrade or cancel anytime.

Basic

$9/ month
billed as $0 per year

1100 monthly credits

1 user only

All models

Workflows

Standard

$24/ month
billed as $0 per year

3625 monthly credits

1 user only

All models

Workflows

Pro

$45/ month
billed as $0 per year

6350 shared monthly credits

1 user

+ up to 4 more at extra cost

All models

Workflows

Pro Max

$170/ month
billed as $0 per year

24650 shared monthly credits

1 user

+ up to 9 more at extra cost

All models

Workflows

Enterprise

For higher limits

Custom

pricing and billing terms

High-volume credits
Custom seat limits
All models
Workflows
Pricing Gradient

Free

For playing around

$0

forever free

Up to 20 credits
1 user only
Limited models
Workflows
Compare plan details

FAQs

What is GPT Image 1.5?
GPT Image 1.5 is OpenAI's latest image generation model, the successor to DALL-E. It excels at rendering legible text within images, following complex instructions precisely, and advanced image editing.
Can GPT Image render text in images?
Yes. GPT Image 1.5 is the best model for rendering legible, accurately spelled text within generated images, ideal for signs, logos, labels, posters, and any text-heavy design work.
How does it compare to DALL-E?
GPT Image 1.5 is the successor to DALL-E with significantly improved quality, text rendering, instruction following, and editing capabilities. It represents a major generational improvement.
Can I edit existing images?
Yes. GPT Image 1.5 supports advanced image-to-image editing. Upload an image, describe changes in natural language, and iterate on modifications, from targeted edits to broad transformations.
When should I use GPT Image vs Flux or Gemini?
Use GPT Image when you need accurate text in images or precise instruction following. Use Flux for style versatility and speed. Use Gemini for multimodal understanding and contextual accuracy.
How do I use GPT Image 1.5 on Morphic?
Open Copilot, describe the image or upload a reference, and select GPT Image. It's the right pick when accurate in-image text, posters, signage, or precise instruction-following matter.

More about GPT Image 1.5

Guides, prompts, and comparisons for GPT Image 1.5.

ChatGPT Images 2.0 use cases for e-commerce, marketing, and branding

A practical guide to ChatGPT Images 2.0 use cases. Learn how to create product visuals, multilingual marketing content, brand assets, and more with GPT Image 2.

ChatGPT Images 2.0: capabilities, prompting, and use cases

What is ChatGPT Images 2.0? A complete guide to GPT Image 2 covering capabilities, prompting tips, do's and don'ts, technical specs, and use cases.

ChatGPT Images 2.0 prompt library: examples for every style

A growing collection of ChatGPT Images 2.0 prompts with example images. Copy any prompt into Morphic and learn what works best with GPT Image 2.

ChatGPT Images 2.0 by OpenAI on Morphic

Use ChatGPT Images 2.0 (GPT Image 2) by OpenAI on Morphic. Accurate multilingual text rendering, photorealistic detail, product photography, image editing, and multiple output formats.

Other models

Explore the rest of the Morphic model catalog.

See all models →

ChatGPT Images 2.5

OpenAI

OpenAI's image model, released September 2026. Sharper detail, precise edits, faster.

Lyria 3.5

Google DeepMind

Google's best-sounding music model. Full songs with structure, vocals, and lyrics.

MiniMax H3 Max Turbo

fal.ai

The fast tier of fal's post-trained H3. Twice the speed, nearly the same look.

Inworld TTS 2

Inworld

Ninety-five voices, 100+ languages. Speech that starts in under a second.