Image generation

Available now

ChatGPT Images 2.0

by OpenAI

OpenAI's image model for design work where the text matters.
Posters, packaging, and storyboards with legible type and consistent characters.

ChatGPT Images 2.0

by OpenAI

Key features

Native reasoning before drawing

Thinking mode plans composition, verifies text, and self-corrects before finalizing. It handles complex prompts more reliably.

Multi-image batches with continuity

Generate up to 8 images from one prompt with shared characters, props, and style. Fits storyboards, ad variants, and sequential scenes.

Up to 2K across aspect ratios

Output up to 2K with flexible aspect ratios, from wide cinematic frames to tall verticals. Ready for print, social, and product use.

Multilingual text in images

Renders legible, correctly spelled text across multiple languages. Fits diagrams, infographics, posters, comics, and packaging.

Stronger instruction following

Honors specific counts, spatial relationships, and multi-element layouts with the precision design briefs and client mockups need.

Conversational editing

Edit existing images by describing changes. Iterate on details, fix elements, or restyle, all without leaving the chat.

Movie poster reading "Echoes of the Tide" in elegant serif, stormy coastline, moonlightTry now

Technical specifications

Up to 2K

High-resolution output across aspect ratios

Up to 8

Multi-image generation with character continuity

Instant + Thinking

Fast generation or reasoning-augmented quality

Image Arena leaderboard at launch (April 2026)

Use cases

Storyboards and sequential scenes

Generate consistent characters and locations across up to 8 frames, suited for ad storyboards, comics, and narrative sequences.

Diagrams, infographics, and charts

Text-heavy visuals with structured layouts and legible labels, suited for educational content and presentations.

Posters and marketing visuals

Campaign posters with embedded copy, multilingual signage, and product imagery that needs accurate typography.

UI mockups and web screenshots

Interface mockups with readable text, button labels, and structured layouts for design exploration.

Product packaging concepts

Packaging with accurate brand names, ingredient lists, and label copy for concept development and client review.

Multilingual localization

Generate the same visual with text translated and adapted across languages, useful for international campaign work.

Prompt examples

Poster with title text

Movie poster reading 'Midnight in Tokyo', neon alley, rim light

Edit prompt

Infographic

Infographic of 4 espresso brewing steps, line icons, clean layout

Edit prompt

Packaging mockup

Coffee bag label 'Bean Street Roast', kraft paper, soft daylight

Edit prompt

Simple pricing

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

Basic

/ month

billed as $0 per year

900 monthly credits

1 user only

All models

Workflows

Standard

/ month

billed as $0 per year

3200 monthly credits

1 user only

All models

Workflows

Pro

/ month

billed as $0 per year

6200 shared monthly credits

1 user

+ up to 4 more at extra cost

All models

Workflows

Pro Max

/ month

billed as $0 per year

24000 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

Free

For playing around

forever free

Up to 20 credits

1 user only

Limited models

Workflows

Compare plan details

FAQs

What is ChatGPT Images 2.0?

ChatGPT Images 2.0 (API model name gpt-image-2) is OpenAI's image generation model released April 2026. It adds native reasoning, output up to 2K, and multi-image batches with character continuity.

What is thinking mode?

Thinking mode lets the model plan composition, verify text accuracy, and self-correct before producing the final image. It is suited for complex prompts where instant mode struggles.

How is it different from GPT Image 1.5?

ChatGPT Images 2.0 adds native reasoning, multi-image batches of up to 8 frames with consistent characters, output up to 2K, and stronger multilingual text rendering.

Can it generate multiple consistent images at once?

Yes. ChatGPT Images 2.0 produces up to 8 images from a single prompt with the same characters, objects, and style preserved across the set.

When should I use ChatGPT Images 2.0 vs Nano Banana or Flux?

Use ChatGPT Images 2.0 for text-heavy work, multi-image continuity, and complex compositions. Use Nano Banana for fast iteration with real-world grounding. Use Flux for style versatility and photorealistic range.

How do I use ChatGPT Images 2.0 on Morphic?

Open Copilot, describe the image or upload reference shots, and select ChatGPT Images 2.0. It's the right pick when in-image text, multi-image continuity, or complex instructions are central to the brief, and it stays in the same workflow as every other image and video model on Morphic.

ChatGPT Images 2.0

Key features

Native reasoning before drawing

Multi-image batches with continuity

Up to 2K across aspect ratios

Multilingual text in images

Stronger instruction following

Conversational editing

Technical specifications

Use cases

Storyboards and sequential scenes

Diagrams, infographics, and charts

Posters and marketing visuals

UI mockups and web screenshots

Product packaging concepts

Multilingual localization

Prompt examples

Poster with title text

Infographic

Packaging mockup

Simple pricing

FAQs

Other models