Concept art & fantasy
How 21 AI image models render: “A majestic dragon made of pure starlight and frozen cosmic dust, soaring through a celestial winter landscape. Its scales shimmer with the light of a thousand galaxies, and its breath is a trail of icy comets. The background features swirling aurora borealis over a frozen, mountainous terrain. The style is a blend of painterly fantasy art and surrealism.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: design originality, readable silhouette, lighting drama. 58 community votes so far.
Community prompt by @anyafoxx · voting closed 2026-10-20
21 text-to-image models rendered this concept art & fantasy prompt with the identical text at their default settings and a fixed seed. Ideogram v4.5 is the community favourite so far, winning 71% of its 7 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 4.8s.
What to look for: sense of scale, atmosphere and light, and designs that read clearly at a glance.
- Ideogram v4.571%Ideogram11.6s · 80 cr Try
- Kling v3 Omni71%Kuaishou148.7s · 35 cr Try
- Nano Banana 2.171%Google16.1s · 31 cr Try
- Muse Image 1.067%Meta11.2s · 12 cr Try
- 63%16.4s · 50 cr Try
- 4.8s · 80 cr Try
- Ideogram v460%Ideogram13.5s · 40 cr Try
- Seedream 5.0 Pro60%ByteDance67.8s · 49 cr Try
- GPT Image 2.5 Flare50%OpenAI29.8s · 40 cr Try
- Qwen Image 3.033%Alibaba7.8s · 32 cr Try
- Krea 2 Large29%Krea35.7s · 80 cr Try
- Qwen Image 3.0 Pro22%Alibaba12.1s · 36 cr Try
- Midjourney V8.220%Midjourney113.7s · 160 cr Try
- Seedream 5.0 Flash17%ByteDance18.3s · 22 cr Try
- Nano Banana 2 Lite0%Google13.2s · 36 cr Try
- GPT Image 2.5 SunburstOpenAI30.8s · 40 cr Try
- Krea 2 MediumKrea14.6s · 40 cr Try
- FLUX 3 Image KleinBlack Forest Labs15.4s · 12 cr Try
- FLUX 3 ImageBlack Forest Labs20.8s · 65 cr Try
- ImagineArt 2ImagineArt · retired from voting28.3s · 60 cr Try
FAQ
- Which AI model renders this prompt best?
- Ideogram v4.5 leads this prompt in the BudgetPixel AI Image Arena, winning 71% of its 7 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.