Illustration & anime
How 20 AI image models render: “Realistic India ink illustration with crisp black lines, realistic anatomy and proportions, and watercolor fills; black ink outlines remain visible. Full-length, overhead view. A Latina woman sits on the pavement with her back against an enormous, thick round downtown pillar covered in posters for bands, art shows, burlesque, and a lost dog. One hand rests on the pavement, the other on an ankle. She tilts her head back, looking up at the viewer with a confident smile. Character: 25-year-old woman, medium-brown skin, slim build, edgy punk/goth appearance. Black asymmetrical undercut, right side shaved, longer top brushed across forehead, short messy ponytail. Sharp features, arched brows, brown almond-shaped eyes, heavy eyeliner, dark burgundy lipstick, six ear piercings. Each fingernail a different color. Loose pale-yellow graphic T-shirt, ripped blue jeans, dark red combat boots. Full left-arm sleeve tattoo of vines, leaves, and red roses. Thick black leather bracelets on both wrists.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: line quality, colour, style consistency. 144 community votes so far.
Community prompt by @dell · voting closed 2026-10-31
20 text-to-image models rendered this illustration & anime prompt with the identical text at their default settings and a fixed seed. Seedream 5.0 Pro is the community favourite so far, winning 75% of its 12 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.
- Seedream 5.0 Pro75%ByteDance69.6s · 49 cr Try
- GPT Image 2.5 Sunburst73%OpenAI27.1s · 40 cr Try
- FLUX 3 Image71%Black Forest Labs80.5s · 65 cr Try
- Qwen Image 3.070%Alibaba6.6s · 32 cr Try
- Seedream 5.0 Flash63%ByteDance20.1s · 22 cr Try
- GPT Image 2.5 Flare59%OpenAI19.4s · 40 cr Try
- Qwen Image 3.0 Pro54%Alibaba10.1s · 36 cr Try
- FLUX 3 Image Klein53%Black Forest Labs8.6s · 12 cr Try
- Ideogram v4.544%Ideogram22.4s · 80 cr Try
- Kling v3 Omni44%Kuaishou40.4s · 35 cr Try
- Krea 2 Medium43%Krea14.1s · 40 cr Try
- Nano Banana 2.140%Google20.4s · 40 cr Try
- 5.9s · 80 cr Try
- Midjourney V8.238%Midjourney34.5s · 40 cr Try
- 36%18.2s · 50 cr Try
- Ideogram v436%Ideogram17.5s · 40 cr Try
- Krea 2 Large22%Krea29.0s · 80 cr Try
- Muse Image 1.020%Meta35.3s · 12 cr Try
- Nano Banana 2 Lite0%Google8.0s · 36 cr Try
FAQ
- Which AI model renders this prompt best?
- Seedream 5.0 Pro leads this prompt in the BudgetPixel AI Image Arena, winning 75% of its 12 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.