- 🖼️ Text-to-image generation from Krea.ai
- 🎨 Mid-tier model balancing quality and speed
- 🏢 Part of the Krea v2 image lineup
- 🎯 Step between lightweight and large variants
- ⚡ Released May 2026
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.
Explore 2 more models by Krea →Krea v2 Medium is the balanced, mid-tier entry in Krea.ai's v2 image-generation family, released in May 2026 alongside its higher-fidelity counterpart Krea v2 Large. Built by the generative-AI studio behind Krea.ai, it produces images from text prompts and is positioned as the middle option in the lineup — trading some of the Large model's raw detail for faster turnaround and lighter compute, while offering more headroom than the lineup's speed-focused tiers.
Within Krea's current catalogue, the v2 line is joined by Krea 2 Turbo (released June 2026), a latency-optimized variant aimed at rapid iteration. Krea v2 Medium remains the standalone medium-weight choice in its family, well suited to users who want dependable image quality without committing to the heaviest model.
In practice, Krea v2 Medium is a sensible default for everyday creative work — concept art, illustration, marketing visuals, and exploratory prompt iteration — where you want strong output without paying the cost or wait of the largest model. Reach for the Large variant when maximum fidelity matters, or Turbo when speed is the priority.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
| Seller | Reputation↓ | Routing | $ / img | Categories | API |
|---|---|---|---|---|---|
| Venice.ai Proxy 0x1f22…18c9 | 100.00 | #1 | $0.02 | image,creative | openai-images |
| ▲ Apex Ant 0x73b4…e736 | 91.01 | #2 | $0.02 | image,media | openai-images |
| D5V1N2 0xd5e7…7be0 | 33.17 | gated | $0.0465 | image,creative,router,fallback | openai-images |
"Best price" and the seller table are live AntSeed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = on-chain trust (0-100). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on AntSeed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.