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

Krea: Krea 2 Turbo

Krea 2 Turbo is the open-source Krea image model for fast, low-cost text-to-image generation. It focuses on prompt-driven generation rather than the richer Krea 2 reference workflow, making it a better fit for simple production pipelines, accelerated runtimes, and workflows that benefit from open-model compatibility such as LoRA-based customization.
Compare models
krea-2-turbo
AvailableKreaImageSync
Price
From $0.015
Modalities
Image

About Krea 2 Turbo

Krea 2 Turbo is the distilled open-weight model of the Krea 2 family, made for fast few-step image generation. Krea describes it as guidance- and timestep-distilled, with a wide aesthetic range, and it works from prompts rather than the full Krea 2 reference workflow. It fits simple production pipelines and open-model setups such as LoRA customization.

Where it works well

  • Few-step generation produces images quickly, which helps in high-volume pipelines.
  • Distillation keeps a wide aesthetic diversity rather than one house look.
  • Open weights allow LoRA-based customization on the model family.
  • The prompt-driven interface is straightforward to integrate.

When to choose another model

  • It lacks the moodboard and reference tooling of the managed Krea 2 models, which Medium and Large offer.
  • Krea describes it as a distilled variant of Raw, so deep fine-tuning belongs on the Raw checkpoint.
  • The technical report notes the family is undertrained and lists native 2K to 4K output as future work.

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-turbo",
      "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
height≥ 64, ≤ 20481024Use an integer. Use multiples of 16.
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, ≤ 4Not 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 providedMinimum length: 2 characters. Maximum length: 10000 characters.
seed≥ 0, ≤ 9007199254740991Not providedUse an integer.
steps≥ 1, ≤ 1008Use an integer.
width≥ 64, ≤ 20481024Use an integer. Use multiples of 16.

Text to image

ParameterValues and limitsDefaultNotes
height≥ 64, ≤ 20481024height is an integer pixel dimension from 64 to 2048 in multiples of 16; default 1024. Explicit width or height requires a delivery path that exposes pixel dimensions. Use size=WIDTHxHEIGHT when a size string is preferred.
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_formatpng, jpeg, webpNot providedUse png, jpeg, or webp. PNG and JPEG are available on both delivery paths; WebP requires a compatible path. Omitted output_format has no shared encoding default: it can be PNG or JPEG. Set it explicitly when the encoding matters. The public endpoint does not accept jpg.
promptNot providedNot providedRequired prompt, 1 to 10000 characters. A one-character prompt requires the text-only delivery path with a 5000-character limit. Explicit steps, WebP, or direct width/height require a compatible path and a prompt of at least 2 characters. Source images are rejected for operation=text-to-image; use operation=image-edit for source-image requests.
seedNot providedNot providedOptional safe integer seed. The shared declared range is 0 to 9007199254740991; a compatible path also accepts negative safe integers. Omit seed for a random result. The same seed does not guarantee an identical image across delivery paths.
sizeNot provided1024x1024Use WIDTHxHEIGHT in pixels. The width and height constraints also apply to size.
steps≥ 1, ≤ 100Not providedUse an integer from 1 to 100. Explicit steps require a delivery path that exposes this control. That path uses 8 when steps is omitted; other paths fix their own step count.
width≥ 64, ≤ 20481024width is an integer pixel dimension from 64 to 2048 in multiples of 16; default 1024. Explicit width or height requires a delivery path that exposes pixel dimensions. Use size=WIDTHxHEIGHT when a size string is preferred.

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
$0.015
Verified price
—
Discount
—

Text to image

per image
Official price
$0.015
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 Turbo in Console with a prompt ready to edit or send.

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

Use cases

Best for
  • Text to Image
  • Bulk image pipelines

    Generate thumbnails, placeholders, or product images from text at low cost per image.

  • LoRA-customized output

    Apply a style or character LoRA trained from Krea 2 Raw for brand-specific generation.

  • Rapid concepting

    Test many prompts in seconds and settle on a direction before choosing whether a larger model is needed for the final render.

  • Editing workflows

    Run image-to-image changes on existing pictures with short prompts when the job is a quick adjustment rather than a polished rebuild.

Prompt examples

A paper-cut diorama of a forest at dusk, layered depth, soft shadows.

Close-up of hands kneading dough on a floured table, natural window light.

Retro travel poster of a mountain railway, limited palette, bold shapes.

FAQ

What is Krea 2 Turbo?

A guidance- and timestep-distilled model released with open weights for fast few-step generation. It is the fast sibling of Krea 2 Raw and shares the 12B Diffusion Transformer design.

How does it differ from Krea 2 Raw?

Raw is the undistilled base for fine-tuning, while Turbo is distilled for quick generation. Krea's rule of thumb in its announcement is to train on Raw and generate with Turbo.

How does it differ from Krea 2 Medium Turbo?

Medium Turbo keeps the richer Krea 2 controls such as moodboards and style references. This model is the open-weight option driven mainly by the text prompt itself.

Can I use LoRAs?

Yes. Open-model compatibility such as LoRA customization is a stated advantage of this model, and LoRAs are typically trained from the Raw checkpoint and applied here.

Does it edit images?

Yes. It handles image-to-image next to text-to-image, so an input picture can serve as the starting point and a short prompt describes the change you want.

How much does Krea 2 Turbo cost?

On TokenLab, Krea 2 Turbo costs $0.015 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 Turbo use?

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

Which operations does Krea 2 Turbo support?

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

Compare Krea 2 Turbo

Sources

Reviewed Oct 2, 2026

More from Krea

Related models