Krea 3
by Krea AI
Krea's fast image editing model.
Combine up to 4 images in one edit.

Key features
Technical specifications
Up to 4
Images per edit, named by number
Native 2K
1080p or 1440p on Morphic
Auto + 10
From 9:16 to 21:9, or match the source
Supported
Generates without reference images
Use cases

Group photos from selfies
Put two people who were never in the same place at one cafe table, faces and clothes carried over and the light matched.

An outfit from product shots
Style a model with a bag, sneakers and a necklace from three catalog photos, while her face, pose and the street stay the same.

Furniture in an empty room
Stage a bare room with a sofa and lamp from product photos. The window, the concrete floor and the late sun stay where they were.

A billboard for a new brand
Swap the ad on a billboard for your own product and headline. The building, the street and the dusk sky come through untouched.

One poster, three editions
Extend a screen-printed poster into three editions with new subjects, the print style, colors and type held across the set.

Next month's social post
Update a monthly social post with a new photo and a new month while the layout, the type and the small print stay put.
Prompt examples






Overview
Krea 3 is Krea's fast image editing model and the editing counterpart to Krea 2. It takes a prompt and up to 4 reference images and returns one edit: people and products combined from separate photos, one area changed while the rest holds, or a template reused for a new brand. It also generates from a prompt alone, at native 2K.
What Krea 3 does differently
Krea 3 keeps your photo. Krea 2 makes a new image in the look of its references; Krea 3 edits the image you give it and pulls people, products and styles in from the others. That makes everyday production work practical: a product placed in a room, an outfit styled from catalog shots, or next month's post from this month's.
Krea 3 on Morphic
Krea 3 is coming to Morphic soon. Until then, Nano Banana Pro and GPT Image 2.5 are live for editing, and Krea 2 for generation, on the same Canvas. The examples on this page were made with Nano Banana Pro. For prompt structure, see the Krea 3 editing guide, copy an edit from the Krea 3 prompt library, or start in the Krea 3 AI image editor.
Simple pricing
Get started for free today, with the option to upgrade or cancel anytime.
Basic
2400 monthly credits
1 user only
All models
Workflows
Standard
3625 monthly credits
1 user only
All models
Workflows
Pro
6350 shared monthly credits
1 user
All models
Workflows
Max
24650 shared monthly credits
1 user
All models
Workflows
Enterprise
For higher limits
Custom
pricing and billing terms

Free
For playing around
$0
forever free
FAQs
Vidu Q4
Shengshu Technology
Shengshu's latest video model. Up to 12 reference images and 3 voices held consistent across one clip, with native audio from 540p to 4K.
Nano Banana 2.1
Google DeepMind
Google DeepMind's new Flash image model. Better design, cleaner edits, steadier characters.
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.