KreaKrea·🖼️ Image Generation·New

Krea v2 Large

anonymized
Try on Venice.ai ↗
Quick reference
Krea v2 Large — TLDR
  • - 🆕 Krea's first foundation image model built completely from scratch.
  • - 🎯 Tuned for aesthetics, style transfer, and creative control.
  • - 🔧 Supports style references, moodboards, and image prompts.
  • - 📏 Krea states its platform offers native 4K generation across models.
  • - 🌐 API access available through Krea's developer documentation.
  • - 🏢 Part of Krea's broader image, video, and 3D suite.
💰 Pricing
$0.070
per image
📅 On Venice since
May 22, 2026
12 days ago
Provider

Krea is a company building generative artificial intelligence products, with a focus on image generation and creative visual tooling. Its work centers on producing high-quality AI imagery through models designed for both fidelity and speed.

Read full profile →
2 models on Venice
2 image
Added May 22, 2026

About this model

Krea v2 Large (also called K2) is an image-generation model from Krea AI, which the company positions as its first in-house foundation image model built entirely from scratch. Released in 2026, Krea describes it as focused specifically on aesthetics, style transfer, and creative control rather than raw prompt-matching alone.

According to Krea, the model supports style references, moodboards, and image prompts, letting users curate a collection of images and generate in a matching look. Krea also states its platform offers native 4K generation across its models.

Because Krea presents this as its first ground-up foundation model, there is no earlier same-family foundation model to compare it against, so generational comparisons cannot be drawn.

The model is part of Krea's wider creative suite, which spans images, video, and 3D, and is accessible through the platform's interface and its developer API documentation.

This About section is AI-generated from public sources (Claude Opus 4.8), with no human editing. It may contain inaccuracies — verify critical details against the sources listed above.

Data sources: Venice API · HuggingFace · Wikipedia — enrichment updated 4h ago