Illustration & anime
How 22 AI image models render: “Anime-style illustration of a girl with a blue umbrella waiting at a rural train station in summer, cicadas implied by heat haze, cel shading.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: line quality, colour, style consistency. 179 community votes so far.
Core suite prompt · voting closed 2026-09-16
22 text-to-image models rendered this illustration & anime prompt with the identical text at their default settings and a fixed seed. Grok Imagine Image 2 is the community favourite so far, winning 78% of its 18 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 5.5s.
What to look for: confident line work, consistent style from edge to edge, deliberate colour and readable shapes.
- 78%18.4s · 50 cr Try
- Krea 2 Medium75%Krea27.5s · 40 cr Try
- GPT Image 2.5 Flare75%OpenAI24.5s · 40 cr Try
- Qwen Image 3.0 Pro60%Alibaba10.0s · 36 cr Try
- Nano Banana 2 Lite58%Google13.8s · 36 cr Try
- GPT Image 255%OpenAI · retired from voting57.8s · 60 cr Try
- GPT Image 2.5 Sunburst54%OpenAI24.3s · 80 cr Try
- Muse Image 1.053%Meta10.9s · 12 cr Try
- Seedream 5.0 Pro52%ByteDance60.1s · 49 cr Try
- Qwen Image 3.050%Alibaba13.5s · 32 cr Try
- Krea 2 Large50%Krea41.0s · 80 cr Try
- Recraft v4 Pro50%Recraft · retired from voting20.9s · 300 cr Try
- ImagineArt 1.5 Pro47%ImagineArt · retired from voting51.9s · 55 cr Try
- Kling v3 Omni45%Kuaishou26.8s · 35 cr Try
- Recraft v439%Recraft · retired from voting11.5s · 45 cr Try
- ImagineArt 238%ImagineArt · retired from voting31.1s · 60 cr Try
- Ideogram v418%Ideogram22.9s · 40 cr Try
- 5.5s · 80 cr Try
- Midjourney Niji 714%Midjourney · retired from voting102.2s · 160 cr Try
- Midjourney v7Midjourney · retired from voting247.2s · 160 cr Try
FAQ
- Which AI model renders this prompt best?
- Grok Imagine Image 2 leads this prompt in the BudgetPixel AI Image Arena, winning 78% of its 18 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.