Concept art & fantasy
How 21 AI image models render: “A majestic winged horse, with iridescent feathers and a coat like polished obsidian, is soaring through a celestial realm filled with nebulae and shimmering stardust. Around its hooves, tiny galaxies spiral outwards. The style is reminiscent of intricate fantasy illustration, with glowing, ethereal colors and a sense of deep cosmic wonder”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: design originality, readable silhouette, lighting drama. 75 community votes so far.
Community prompt by @anyafoxx · voting closed 2026-10-15
21 text-to-image models rendered this concept art & fantasy prompt with the identical text at their default settings and a fixed seed. Krea 2 Large is the community favourite so far, winning 80% of its 5 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 5.2s.
What to look for: sense of scale, atmosphere and light, and designs that read clearly at a glance.
- Krea 2 Large80%Krea35.1s · 80 cr Try
- 73%20.2s · 50 cr Try
- GPT Image 2.5 Sunburst63%OpenAI46.7s · 40 cr Try
- Nano Banana 2 Lite56%Google29.4s · 36 cr Try
- Seedream 5.0 Pro55%ByteDance67.5s · 49 cr Try
- Kling v3 Omni50%Kuaishou27.1s · 35 cr Try
- Muse Image 1.050%Meta11.1s · 12 cr Try
- Nano Banana 2.144%Google9.8s · 31 cr Try
- Qwen Image 3.044%Alibaba7.2s · 32 cr Try
- Qwen Image 3.0 Pro44%Alibaba10.5s · 36 cr Try
- Seedream 5.0 Flash33%ByteDance26.9s · 22 cr Try
- 5.2s · 80 cr Try
- ImagineArt 220%ImagineArt28.1s · 60 cr Try
- FLUX 3 Image17%Black Forest Labs21.6s · 65 cr Try
- Ideogram v4.511%Ideogram13.7s · 80 cr Try
- GPT Image 2.5 Flare0%OpenAI46.0s · 40 cr Try
- GPT Image 2OpenAI · retired from voting53.7s · 60 cr Try
- Ideogram v4Ideogram13.6s · 40 cr Try
- Krea 2 MediumKrea28.0s · 40 cr Try
- Midjourney V8.2Midjourney101.5s · 160 cr Try
FAQ
- Which AI model renders this prompt best?
- Krea 2 Large leads this prompt in the BudgetPixel AI Image Arena, winning 80% of its 5 blind head-to-head votes. Vote on the arena page to add your judgement.
- Were the prompts adjusted per model?
- No. Every model received the exact same prompt, unmodified, at its default settings, with no negative prompt or style suffix. Some models rewrite prompts internally, and that is part of what is being compared.
- Can I run this prompt myself?
- Yes. Each tile’s “Try” link opens the BudgetPixel workshop with this prompt and that model preselected.