Illustration & anime
How 22 AI image models render: “Cel-shaded anime illustration of an adult kite maker testing a vast translucent dragon-shaped kite on a windy coastal bluff, ribbons streaming above wild grasses and distant cliffs. Palette of coral, turquoise, butter yellow, and deep blue, with clean contours and a luminous sky.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: line quality, colour, style consistency. 128 community votes so far.
Fresh prompt from the daily stream · voting closed 2026-10-09
22 text-to-image models rendered this illustration & anime prompt with the identical text at their default settings and a fixed seed. Seedream 5.0 Flash is the community favourite so far, winning 69% of its 13 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 6.2s.
What to look for: confident line work, consistent style from edge to edge, deliberate colour and readable shapes.
- Seedream 5.0 Flash69%ByteDance25.8s · 22 cr Try
- Seedream 5.0 Pro69%ByteDance72.4s · 49 cr Try
- Qwen Image 3.0 Pro67%Alibaba10.8s · 36 cr Try
- GPT Image 262%OpenAI58.8s · 42 cr Try
- FLUX 3 Image57%Black Forest Labs21.3s · 32 cr Try
- Ideogram v457%Ideogram11.7s · 40 cr Try
- ImagineArt 1.5 Pro54%ImagineArt · retired from voting52.1s · 55 cr Try
- GPT Image 2.5 Sunburst53%OpenAI41.0s · 40 cr Try
- Krea 2 Large53%Krea29.8s · 80 cr Try
- Ideogram v4.546%Ideogram19.4s · 80 cr Try
- Muse Image 1.045%Meta22.4s · 12 cr Try
- GPT Image 2.5 Flare42%OpenAI31.8s · 40 cr Try
- 6.2s · 80 cr Try
- 33%15.2s · 50 cr Try
- ImagineArt 233%ImagineArt57.9s · 60 cr Try
- Kling v3 Omni29%Kuaishou96.3s · 35 cr Try
- Qwen Image 3.029%Alibaba6.6s · 32 cr Try
- Krea 2 Medium25%Krea27.9s · 40 cr Try
- Nano Banana 2 Lite19%Google19.3s · 36 cr Try
- Recraft v4 Pro17%Recraft · retired from voting15.1s · 300 cr Try
- Nano Banana 2.1Google12.0s · 40 cr Try
FAQ
- Which AI model renders this prompt best?
- Seedream 5.0 Flash leads this prompt in the BudgetPixel AI Image Arena, winning 69% of its 13 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.