Illustration & anime
How 21 AI image models render: “Watercolour illustration of an adult ceramicist shaping a blue-glazed vessel in a sunlit workshop, shelves of unfinished pottery and leafy plants softened by loose brushwork. Palette of terracotta, indigo, warm cream, and sage.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: line quality, colour, style consistency. 215 community votes so far.
Fresh prompt from the daily stream · voting closed 2026-10-15
21 text-to-image models rendered this illustration & anime prompt with the identical text at their default settings and a fixed seed. GPT Image 2.5 Sunburst is the community favourite so far, winning 70% of its 20 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 5.1s.
What to look for: confident line work, consistent style from edge to edge, deliberate colour and readable shapes.
- GPT Image 2.5 Sunburst70%OpenAI40.7s · 40 cr Try
- GPT Image 263%OpenAI · retired from voting92.1s · 60 cr Try
- 5.1s · 80 cr Try
- Qwen Image 3.061%Alibaba7.4s · 32 cr Try
- Nano Banana 2 Lite60%Google12.1s · 36 cr Try
- 56%19.3s · 50 cr Try
- GPT Image 2.5 Flare55%OpenAI30.5s · 40 cr Try
- FLUX 3 Image50%Black Forest Labs28.0s · 65 cr Try
- Seedream 5.0 Pro50%ByteDance71.9s · 49 cr Try
- Midjourney V8.250%Midjourney113.1s · 160 cr Try
- Seedream 5.0 Flash42%ByteDance25.6s · 22 cr Try
- Muse Image 1.040%Meta9.4s · 12 cr Try
- Qwen Image 3.0 Pro35%Alibaba9.7s · 36 cr Try
- Ideogram v4.531%Ideogram12.8s · 80 cr Try
- Kling v3 Omni31%Kuaishou31.7s · 35 cr Try
- ImagineArt 229%ImagineArt29.4s · 60 cr Try
- Krea 2 Medium29%Krea22.2s · 40 cr Try
- Ideogram v424%Ideogram14.4s · 40 cr Try
- Nano Banana 2.115%Google10.1s · 31 cr Try
- Krea 2 Large7%Krea30.3s · 80 cr Try
FAQ
- Which AI model renders this prompt best?
- GPT Image 2.5 Sunburst leads this prompt in the BudgetPixel AI Image Arena, winning 70% of its 20 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.