Skip to content

NodeTool Cloud is in alpha. Try it →

Text-to-image · Krea

Krea 2 in a visual AI workflow

Run Krea 2 in a visual AI workflow: expressive text-to-image with style references and moodboards, at provider list price.

Krea 2 in the NodeTool canvas

Fresh Krea 2 examples are on the way. Meanwhile, here's the NodeTool canvas where you'll run it.

Krea 2 is Krea's foundation image model, in two sizes. Large is the flagship, larger and more flexible, with particular strength in photorealism and expressive artistic styles. Medium is tuned for expressive illustration, anime, and painterly styles, and stays consistent across artistic directions.

Both nodes take style reference images, a moodboard id, and a creativity setting, so a house style can travel with the graph instead of living in the prompt.

NodeTool is bring-your-own-key, so you call Krea 2 through a provider you already use and pay that provider's list price. The table below lists the providers that serve it and the model ids their `--list-models` output reports.

Modality
Text-to-image
Sizes
Large and Medium
Large strength
Photorealism and expressive artistic styles
Medium strength
Illustration, anime, and painterly styles

Where to run Krea 2

NodeTool is bring-your-own-key: you call Krea 2 through a provider you already have access to and pay their list price — no credits, no markup. These providers serve Krea 2 today.

ProviderSetting for your key
AtlasCloudATLASCLOUD_API_KEY
fal.aiFAL_API_KEY
ReplicateREPLICATE_API_TOKEN

Frequently asked questions

Should I use Krea 2 Large or Medium?
Large for photorealism and the widest stylistic range. Medium for illustration, anime, and painterly looks.
Does Krea 2 support style references?
Yes. The nodes take style reference images with a strength value, plus a moodboard id and strength.
What does Krea 2 cost in NodeTool?
NodeTool adds no per-image fee. You pay the provider that serves Krea 2 at its list price, with your own key.

Run Krea 2 your way.

Download NodeTool Studio and build across image, video, audio, and text with your own keys.