Shotcraft
Image generation

Krea 2

Krea's first from-scratch foundation image model, a 12-billion-parameter text-to-image diffusion model released 22 June 2026 with weights published on Hugging Face.

An image model by Krea AI · read 2026-08-14 · sourcing medium

Weights
Downloadable
Commercial use
Permitted subject to conditions

It ships as Krea 2 Raw (base checkpoint, recommended for fine-tuning) and Krea 2 Turbo (post-trained and distilled for inference). Positioned around aesthetic diversity and style control rather than benchmark scores, and sold through compute-unit subscriptions.

Commercial use — Permitted subject to conditions

EXACT LICENSE: 'Krea 2 Community License'.

  • The terms restrict what you may generate. The model card states it supports creative, commercial, developer and research use cases, but obliges deployers to implement content filtering and prohibits unlawful or policy-violating use

The conditions above were extracted from the licence notes recorded during research, and each one shows the sentence it came from so you can check the reading. Read the licence before you rely on any of this. Nothing on this page is legal advice, and this site does not tell you a model is cleared for commercial use.

Specification

Vendor figures, read 2026-08-14Read from Krea AI's own documentation on 2026-08-14. Vendors change these between model versions without announcing it, so check theirs before you commit a shot to a number. Sourcing for this entry is mixed. Some fields came from pages we retrieved, others could not be confirmed and are left blank. Check the vendor's current documentation

What it takes in
text, image
What it makes
image
Maximum resolution
not established
Aspect ratios
not established
Controls
image-to-image, style-reference, editing-by-instruction
Weights
Downloadable
Pricing
subscription in compute units: Free 100 units/day, Basic $9/mo (5,000 units/mo), Pro $35/mo (20,000), Max $105/mo (60,000), Business $200/mo (80,000, up to 50 seats), Enterprise custom
Released or updated
2026-06-22

Maximum resolution and supported aspect ratios are not established here. That means no page we could retrieve stated them, not that the model lacks them.

Strengths

  • Open weights at a workable 12B size with a community license that permits commercial use
  • Separate Raw base checkpoint published explicitly for fine-tuning
  • Krea Realtime sibling targets sub-50ms interactive generation

Weaknesses

  • No documented public API for the model
  • No published resolution ceiling
  • Content-filtering obligation on deployers adds compliance work

Best for

Where the sources disagree

Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.

What to understand before using it

Explainers naming the mechanisms this model's own documentation mentions.

See it from the vendor

Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.

Nearby in the directory

Adobe Firefly Image Model 5

Adobe's current Firefly image model, announced in public beta at Adobe MAX on 28 October 2025, generating at native 4 MP resolution without an upscale

Image generation

FLUX.1 Kontext [pro] / [max]

Instruction-driven image editing models from the FLUX.1 generation (2025), still exposed as live /flux-kontext-pro and /flux-kontext-max endpoints. Th

Image generation

FLUX.2 [dev]

32-billion-parameter open-weights checkpoint that does text-to-image plus single- and multi-reference editing in one model, released 25 November 2025

Image generation

Sources

Read on 2026-08-14. A source that has changed since then will not be reflected here until the next pass.