Illustration & anime
How 23 AI image models render: “An elegant gothic woman sits sideways among oversized ivory blossoms, crimson roses, and dark teal foliage, turning toward the viewer with half-lidded amber eyes. She has a softly waved silver-white bob and a fitted black gown with lace, embroidered sleeves, and a sculpted corset. Deep-teal skirt folds reveal crimson lining and burnt-orange embroidery. Crimson ribbons with orange edging weave through the flowers, leaving breathing room around her pale face and hands. A deep-teal background fades into charcoal, with muted burnt-orange light behind her head, faint crimson haze below, and botanical shadows. Fine ordered dithering, delicate checkerboard patterns, and clustered pigment grains soften background transitions only; the woman and flowers remain smoothly painted. Crimson, deep teal, glowing orange, lacquer black, and warm ivory palette. Soft frontal fill, luminous hair, readable black fabric, subtle orange rim light, refined gothic anime, precise linework, dramatic floral framing”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: line quality, colour, style consistency. 158 community votes so far.
Community prompt by @TesaranJ · voting closed 2026-10-05
23 text-to-image models rendered this illustration & anime prompt with the identical text at their default settings and a fixed seed. Qwen Image 3.0 Pro 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 5.9s.
What to look for: confident line work, consistent style from edge to edge, deliberate colour and readable shapes.
- Qwen Image 3.0 Pro73%Alibaba10.7s · 36 cr Try
- 67%26.0s · 50 cr Try
- GPT Image 259%OpenAI58.0s · 60 cr Try
- Muse Image 1.059%Meta25.4s · 12 cr Try
- Qwen Image 3.058%Alibaba7.6s · 32 cr Try
- GPT Image 2.5 Sunburst52%OpenAI42.3s · 40 cr Try
- GPT Image 2.5 Flare50%OpenAI33.0s · 40 cr Try
- Seedream 5.0 Pro50%ByteDance58.0s · 49 cr Try
- ImagineArt 247%ImagineArt28.7s · 60 cr Try
- Ideogram v440%Ideogram13.2s · 40 cr Try
- Recraft v440%Recraft · retired from voting24.2s · 45 cr Try
- ImagineArt 1.5 Pro36%ImagineArt64.9s · 55 cr Try
- Nano Banana 2 Lite36%Google21.6s · 36 cr Try
- Recraft v4 Pro35%Recraft · retired from voting33.2s · 300 cr Try
- Krea 2 Large32%Krea49.7s · 80 cr Try
- Kling v3 Omni31%Kuaishou44.4s · 35 cr Try
- 5.9s · 80 cr Try
- Krea 2 Medium20%Krea16.9s · 40 cr Try
- Ideogram v4.517%Ideogram13.0s · 80 cr Try
- Seedream 5.0 Flash13%ByteDance30.6s · 22 cr Try
- Midjourney Niji 7Midjourney · retired from voting111.6s · 160 cr Try
- FLUX 3 ImageBlack Forest Labs25.1s · 32 cr Try
FAQ
- Which AI model renders this prompt best?
- Qwen Image 3.0 Pro leads this prompt in the BudgetPixel AI Image Arena, winning 73% of its 11 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.