Illustration & anime
How 20 AI image models render: “Energetic ink splattering + bold caricature contours + precise tonal modeling, where energetic ink splattering creates chaotic surface energy through varied line weight and ink blots, bold caricature contours produce simplified forms via thick and thin ink outlines, and precise tonal modeling infuses fine parallel line hatching. The fusion manifests as layered hatching within loose expressive marks, transforming any subject through rapid ink application over fine parallel lines. A man with glasses, messy black hair, a short beard and a dark shirt. Medium close-up at eye level, the man seated at a desk leaning forward with wide eyes and a concerned expression, holding a pencil in his right hand while resting his left hand against his cheek, an open book and papers on the desk in front of him. Scene set at a cluttered desk in a workspace, with scattered papers, an open book and mathematical equations drawn on the wall behind.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: line quality, colour, style consistency. 153 community votes so far.
Community prompt by @justrob · voting closed 2026-09-23
20 text-to-image models rendered this illustration & anime prompt with the identical text at their default settings and a fixed seed. Midjourney Niji 7 is the community favourite so far, winning 73% of its 11 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 4.9s.
What to look for: confident line work, consistent style from edge to edge, deliberate colour and readable shapes.
- Midjourney Niji 773%Midjourney123.7s · 160 cr Try
- GPT Image 2.5 Flare60%OpenAI25.9s · 28 cr Try
- 59%28.7s · 50 cr Try
- Qwen Image 3.0 Pro56%Alibaba10.9s · 36 cr Try
- Qwen Image 3.053%Alibaba8.2s · 32 cr Try
- GPT Image 2.5 Sunburst50%OpenAI37.6s · 28 cr Try
- Recraft v4 Pro47%Recraft22.9s · 300 cr Try
- GPT Image 244%OpenAI78.4s · 60 cr Try
- Krea 2 Medium44%Krea15.7s · 40 cr Try
- Seedream 5.0 Pro44%ByteDance76.2s · 49 cr Try
- Recraft v439%Recraft12.0s · 45 cr Try
- Nano Banana 2 Lite38%Google13.9s · 36 cr Try
- ImagineArt 1.5 Pro38%ImagineArt48.9s · 55 cr Try
- ImagineArt 238%ImagineArt28.4s · 60 cr Try
- Ideogram v436%Ideogram15.3s · 40 cr Try
- Kling v3 Omni33%Kuaishou27.1s · 35 cr Try
- Muse Image 1.031%Meta12.9s · 12 cr Try
- Krea 2 Large27%Krea33.9s · 80 cr Try
- 4.9s · 80 cr Try
FAQ
- Which AI model renders this prompt best?
- Midjourney Niji 7 leads with 73% of 11 blind votes on this prompt. 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.