Reve 2.0 builds an image as a structured layout, every element with its own position, size, and description. You direct what goes where instead of hoping a sentence lands it.

Native 4K resolution

Renders at 2048 by 2048 and upscales to 4096 by 4096 with most fine detail intact. Output holds up for print, large format, and close client review.

Professional text rendering

A dedicated typography step places legible, correctly spelled text inside the image. Headlines, packaging copy, and labels sit in the right perspective.

Multi-reference composition

Feed several reference images as visual ingredients. Reve 2.0 borrows character, lighting, material, or environment from each and merges them into one coherent scene.

Region-level editing

Change one element without disturbing the rest. Swap an object, relight a corner, or rewrite a caption while composition, proportion, and perspective stay put.

Spatial consistency

Proportion, perspective, and material hold together across the frame. Floor plans, product shots, and multi-panel layouts line up the way a brief expects instead of warping.

Design a poster with bold, readable title textStart creating

Technical specifications

Generate, edit, reference

Text-to-image, image editing, and multi-reference generation

Up to 4K

2048 × 2048 native, upscaled to 4096 × 4096 with most fine detail kept

Widescreen to square

Seven ratios from 16:9 and 9:16 down to a square 1:1

Editable layout

An element tree you can edit, like HTML is to a web page

Use cases

Editable layout files

Treat a generated image like a design document. Reposition, resize, or rewrite any element and re-render, instead of rerolling the whole prompt and losing what already worked.

Posters and packaging

Movie posters, product packaging, and event graphics where the title, the price, and the small print all have to read correctly in the right place.

Multi-panel layouts

Comic pages, storyboards, and explainer grids. The layout hierarchy keeps panels, gutters, and speech balloons ordered instead of merging into one busy frame.

Product and architectural comps

Spatial intelligence keeps proportion and perspective honest, so floor plans, product shots, and interior comps line up the way a brief expects.

Brand-consistent sets

Carry one character, product, or material across a full set through multiple references, so a campaign looks like it came from a single shoot.

4K print-ready art

Editorial spreads, gallery prints, and large-format display work that has to survive being blown up and inspected up close.

Prompt examples

Movie poster

Movie poster, bold title text at the bottom, lone figure on a ridge at dusk

Edit prompt

Packaging

Cereal box front panel, clear product name, friendly mascot, morning kitchen light

Edit prompt

Comic layout

Three-panel comic strip, same detective in each panel, readable speech bubbles

Edit prompt

Floor plan

Isometric office floor plan, labeled rooms, clean flat-vector look

Edit prompt

Magazine cover

Fashion magazine cover, masthead at top, coverlines aligned down the left edge

Edit prompt

App UI mockup

Mobile app home screen, top nav bar, three feature cards, bottom tab bar

Edit prompt

Overview

Reve 2.0, also called Reve Image 2, is a layout-first image model from Reve AI, released on June 3, 2026. Rather than turning a single prompt into pixels in one pass, it builds the image as a structured layout, an editable tree where every element carries its own position, size, and description. It covers text-to-image, image editing, multi-reference composition, and in-image text, with output up to 4K, and debuted second on the public Text-to-Image Arena leaderboard on launch day.

What Reve 2.0 does differently

Most image models compress your intent straight into pixels, so a small wording change can shift the whole picture and there is no clean way to nudge one element. Reve 2.0 puts an editable layout in between, much like HTML sits between intent and a rendered web page. Every region has a location, a size, and a local description you can rewrite, and you refine results either by talking to the model or by editing the layout directly. The image stops being a one-shot output and starts behaving like a design file you can revise.

Reve 2.0 and Morphic

Reve 2.0 is not in the Morphic model catalog today. If you want to start creating right now, Morphic runs image models like Nano Banana Pro, GPT Image 2, and Seedream, plus video, speech, and music, all in one Canvas. This page tracks Reve 2.0 as a model to know about; if it lands on Morphic, the page will say so.

Simple pricing

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

Basic

/ month

billed as $0 per year

2400 monthly credits

1 user only

All models

Workflows

Standard

/ month

billed as $0 per year

3625 monthly credits

1 user only

All models

Workflows

Pro

/ month

billed as $0 per year

6350 shared monthly credits

1 user

+ up to 4 more at extra cost

All models

Workflows

Max

/ 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

Free

For playing around

forever free

Up to 20 credits

1 user only

Limited models

Workflows

Compare plan details

FAQs

What is Reve 2.0?

Reve 2.0 is a layout-first AI image model from Reve AI, released on June 3, 2026. Instead of turning a single sentence into pixels, it builds the image as a structured layout where every element has its own position, size, and description, which you can edit before and after rendering. It handles text-to-image, image editing, multi-reference composition, in-image text, and output up to 4K.

Is Reve 2.0 the same as Reve Image 2?

Yes. Reve 2.0 and Reve Image 2 refer to the same model, the second generation of Reve AI's image model. Reve labels the family Reve Image 2.0; most people shorten it to Reve 2.0.

What makes Reve 2.0's layout control different?

Most image models go straight from a prompt to pixels, so a small change can ripple across the whole picture. Reve 2.0 inserts an editable layout in between, similar to how HTML sits between intent and a rendered web page. You can move, resize, or rewrite a single element and re-render just that, which makes results predictable and editable rather than one-shot.

What resolution does Reve 2.0 output?

Reve 2.0 renders natively at 2048 by 2048 and can upscale to 4096 by 4096, keeping most fine detail through the upscale. It supports seven aspect ratios, from 16:9 and 9:16 to 1:1, and exports as PNG, JPEG, or WebP.

Can Reve 2.0 render text inside images?

Yes. Reve 2.0 runs a dedicated typography step so headlines, packaging copy, and labels come out legible, correctly spelled, and placed in the right perspective. That makes it well suited to posters, packaging, and UI mockups where text accuracy matters.

How does Reve 2.0 compare to GPT Image 2?

On launch day Reve 2.0 debuted second on the public Text-to-Image Arena leaderboard, just behind GPT Image 2. The practical difference is control: GPT Image 2 leads on raw prompt-to-image quality and reasoning, while Reve 2.0's edge is the editable layout, so you place and adjust elements directly rather than re-describing the whole scene.

Who makes Reve 2.0?

Reve 2.0 is built by Reve AI, an independent image-AI lab based in Palo Alto. The model is available through Reve's own app and API and through hosting partners.

Other models

Explore the rest of the Morphic model catalog.

See all models →

Flux 3 Image

Black Forest Labs

Black Forest Labs' control-first image model. Place every element, edit one box at a time.

Ideogram 4.5

Ideogram

Ideogram's precision edit model. Stack edit on edit, with no drift or artifacts.

Eleven v4

ElevenLabs

ElevenLabs' most expressive voice model. Audio tags, 90+ languages, and a faster Turbo tier.

Kling 4.0 Flash

Kling

Kuaishou's speed-tuned Kling 4.0 for high-volume video. Fast 3 to 20 second clips at 720p.