Krea 3 Edit

Edits and combines reference images using text instructions, with optional prompt expansion, output-size controls, and reproducible generation through a seed.

Inference$ Commercial useFrom 3 credits per run

About Krea 3 Edit

Edits and combines reference images using text instructions, with optional prompt expansion, output-size controls, and reproducible generation through a seed.

image editingmulti-referenceimage-to-imagekreakrea-3

Pricing

A run with the default settings costs 3 credits. The exact cost updates in the playground as you change settings, and you're only charged when you press Run. Failed runs are refunded automatically.

Inputs

prompttextareadefault: ""

Edit instruction. Refer to images as <image-1>, <image-2>, ... and regions as @label. May be omitted when a region has a note.

image_urlsfile-listrequired

Reference images to edit or combine (1-8). Order sets the <image-N> tags.

regionsjson

Bounding boxes on reference images, with optional labels and editing notes. Requires high or ultra reasoning.

regional_editboolean

With high or ultra reasoning, true preserves pixels outside the edit regions on the chosen canvas; false disables automatic region cropping and preservation. Omit to retain automatic preservation. With image_size=auto, keeps the canvas dimensions; an explicit image_size preserves the resized input. Billing uses the generated render dimensions. Use PNG for lossless output.

image_sizeselectdefault: "auto"

Output size, rounded up to multiples of 16, at most 4,220,160 total pixels (1680×2512). auto lets the prompt expander pick the aspect ratio at about 2048×2048.

Options: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, auto

reasoning_levelselectdefault: "medium"

How much effort the prompt expander spends reasoning about the given editing task. Higher reasoning effort means slower generation time.

Options: medium, high, ultra

negative_prompttextareadefault: ""

What to keep out of the image.

seedinteger

Latent noise seed. Use a new seed when editing a previous output again.

output_formatselectdefault: "png"

Output image format.

Options: png, jpeg

sync_modebooleandefault: false

Return images as data URIs instead of saving them in request history.

enable_safety_checkerbooleandefault: true

Check output images for unsafe content. Disabling requires account authorization.

More from Krea 3 Edit

✦ new

Krea 3 Text to Image

Generates images from text prompts with optional prompt expansion, configurable output dimensions, and seed control.

image generationprompt expansion

text-to-image

✦ new

Krea 3 Realtime

Edits an input image in a realtime session using text prompts, with seed control.

image editingrealtime

image-to-image

Related image to image models

Nano Banana Pro

Nano Banana Pro is Google's new state-of-the-art image generation and editing model

realismtypography

image-to-image

Nano Banana 2

Nano Banana 2 is Google's new state-of-the-art image generation and editing model

image-to-image

Nano Banana 2.1 Edit

Nano Banana 2.1 Edit by Google transforms reference images using text instructions, with output resolutions up to 4K and optional video or PDF context.

image editingimage to image

image-to-image

GPT Image 2.5 Sunburst Edit

Editing built for the tightest control, edits scoped precisely to the instruction, with subject and composition preserved across many rounds of revision.

stylizedtransform

image-to-image

✦ new

GPT Image 2.6 Sunburst Edit

Editing built for the tightest control, edits scoped precisely to the instruction, with subject and composition preserved across many rounds of revision.

stylizedtransform

image-to-image

GPT Image 2 API

GPT Image 2, OpenAI's latest image model, is capable of making fine-grained, detailed edits to images.

gpt-image-2openai

image-to-image

Birefnet Background Removal V2

bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)

background removalsegmentation

image-to-image

Nano Banana

Google's famous original image generation and editing model

image-editing

image-to-image

GPT Image 2.5 Flare Edit

Precise image editing that changes only what's asked, keeping subject, composition, and background intact, with reference subjects staying recognizable across styles and successive edits.

stylizedtransform

image-to-image

✦ new

GPT Image 2.6 Flare Edit

Precise image editing that changes only what's asked, keeping subject, composition, and background intact, with reference subjects staying recognizable across styles and successive edits.

stylizedtransform

image-to-image

Seedream 5.0 Pro Image Editing

Seedream 5.0 Pro is grounded, region-precise image editing model that changes one element while keeping the rest of the frame intact with layer separation, sketch completion, and up to 10 reference images.

realismtypography

image-to-image

SeedVR2

Use SeedVR2 to upscale your images

upscale

image-to-image