Choose Auto, TokenLab Verified, or Official for each request, with prices shown up front. See what's new

Krea: Krea 2 Large

Krea 2 Large is the higher-capacity variant in the Krea 2 family, with lighter post-training and a more textured, flexible output character. It is the stronger overall model when a workflow benefits from higher ceiling, stronger photorealism, more raw visual character, and better handling of motion blur, film grain, low dynamic range, and other less polished looks. It supports text-to-image and image-to-image generation, prompt interpretation strength through the creativity control, and up to 10 weighted reference images with both positive and negative guidance.
Compare models
krea-2-large
AvailableKreaImageSync
Price
From $0.06
Modalities
Image

About Krea 2 Large

Krea 2 Large is the higher-capacity model in the Krea 2 image family from Krea, with lighter post-training that leaves a more textured, flexible output. It aims for photorealism and raw visual character, handling motion blur, film grain, and low dynamic range better than its smaller siblings. It generates from text, edits images, and accepts up to 10 weighted reference images.

Where it works well

  • Photorealism with raw character: film grain, motion blur, and unpolished looks come out convincingly.
  • Lighter post-training leaves a higher ceiling, with more varied and textured results than Medium.
  • A creativity control sets how loosely the model interprets the prompt.
  • Up to 10 reference images can be weighted, with both positive and negative guidance.

When to choose another model

  • Its output is less uniform than Medium's, so illustration and anime sets that need strict consistency favor Medium.
  • Being the larger model, it is slower and costlier per image than Medium or the Turbo variants.
  • Fine-tuning and LoRA training are better started from Krea 2 Raw, the open base checkpoint of the family.

Getting started

  1. Create API key

    Create a key in Console, then use it with every model on the platform.

  2. Send your first request

    Copy the example for your language and run it against the endpoint.

    Image editingText to imageTokenLab endpoint
    POST/v1/images/generations
    curl -X POST "https://api.tokenlab.sh/v1/images/generations" \
      -H "Authorization: Bearer sk-xxx" \
      -H "Content-Type: application/json" \
      -d '{
      "operation": "image-to-image",
      "model": "krea-2-large",
      "prompt": "A minimalist product photo of matte black headphones on a soft blue background.",
      "image_url": "https://example.com/source.png"
    }'

Parameters

Image editing

ParameterValues and limitsDefaultNotes
heightNot provided1024Use an integer.
imageNot providedNot providedAlias of the combined images input. See input_limits.images for the total input image count.
image_urlNot providedNot providedAlias of the combined images input. See input_limits.images for the total input image count.
image_urlsNot providedNot providedAlias of the combined images input. See input_limits.images for the total input image count.
imagesInputs: ≥ 1, ≤ 10Not providedLimits apply when this input is supplied. Image aliases are combined into one input image list; the limit applies to the combined list.
n11Use an integer.
operationRequiredNot providedNot providedNot provided
output_formatjpeg, png, webpNot providedDefault encoding is shared by these equivalent values: jpg, jpeg.
promptNot providedNot providedNot provided
seed≥ 0, ≤ 9007199254740991Not providedUse an integer.
widthNot provided1024Use an integer.

Text to image

ParameterValues and limitsDefaultNotes
heightNot provided1024Use an integer.
imagesNot providedNot providedText-to-image does not accept source images. Do not send this field for that operation. Use one of this model's declared image operations for source-image requests.
n11Use an integer.
operationRequiredNot providedNot providedNot provided
output_formatjpeg, png, webpNot providedDefault encoding is shared by these equivalent values: jpg, jpeg.
promptNot providedNot providedNot provided
seed≥ 0, ≤ 9007199254740991Not providedUse an integer.
widthNot provided1024Use an integer.

Fields outside this contract are rejected.

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Image editing

per image
Official price
$0.06
Verified price
—
Discount
—

Text to image

per image
Official price
$0.06
Verified price
—
Discount
—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours
Requests
Success rate
P95 latency
Total tokens
Model performance
Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Krea 2 Large in Console with a prompt ready to edit or send.

Help me create an image with krea-2-large using image-edit at /v1/images/edits. Show the result, cost, and any limits I should know.

Use cases

Best for
  • Text to Image
  • Photographic campaigns

    Generate editorial-style images with natural grain and imperfect lighting that avoid the polished AI look.

  • Moodboard-led art direction

    Combine weighted references with negative guidance to steer toward one look and away from another.

  • Cinematic stills

    Create frames with motion blur or low dynamic range for film pitches and lookbooks.

  • Image editing

    Rework an existing photo toward a new style while using references to anchor the result.

Prompt examples

A 35mm photo of a fishing boat at dawn, heavy grain, slight motion blur, muted colors.

Street portrait of an old tailor in his shop, window light, low contrast, no retouching.

Use the three references at full weight and avoid the neon palette in the fourth: a rainy city crosswalk.

FAQ

What is Krea 2 Large best for?

Photorealistic and raw-looking images. Krea's family description gives it more capacity than Medium and lighter post-training, which suits film grain, motion blur, and low-dynamic-range looks that polished models smooth over.

How does it differ from Krea 2 Medium?

Large has more capacity and a rawer character; Medium is smaller, faster, and post-trained harder for stable, consistent results in illustration and graphic design. Choose by the look you want.

How many reference images can I use?

Up to 10 weighted reference images, with positive and negative guidance, according to the catalog description. A creativity control additionally adjusts how closely the prompt is followed.

Can it edit existing images?

Yes. The catalog lists image-to-image alongside text-to-image, so you can supply a starting image and direct the changes with a prompt and weighted references together.

How much does Krea 2 Large cost?

On TokenLab, Krea 2 Large costs $0.06 per image. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should Krea 2 Large use?

Use https://api.tokenlab.sh/v1/images/edits for Krea 2 Large. The request example below shows the matching code shape.

Which operations does Krea 2 Large support?

Krea 2 Large supports Image editing, Text to image. Select an operation above to see its endpoint and request example.

Compare Krea 2 Large

Sources

Reviewed Oct 2, 2026

More from Krea

Related models