How 22 AI image models render: “A pretty K-pop idol who is 19–21 years old at a music video shoot. The music video is for her hit song "돈 벌기" (Make Money). The setting of the music video relates to the song name. At least 4 scenes and many angles.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: every stated element present, correct count, correct placement. 239 community votes so far.
Community prompt by @blanknamebp · voting closed 2026-10-01
Checklist: adult K-pop idol aged 19–21 · music video shoot setting · song title "돈 벌기" (Make Money) · at least 4 scenes · many camera angles
22 text-to-image models rendered this prompt adherence 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 78% of its 27 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 6.4s.
What to look for: the right count of objects, the right spatial relationships, the stated colours and attributes, and nothing added.
- GPT Image 2.5 Sunburst78%OpenAI36.9s · 40 cr Try
- Ideogram v477%Ideogram19.2s · 40 cr Try
- GPT Image 2.5 Flare63%OpenAI27.2s · 40 cr Try
- Krea 2 Large61%Krea34.3s · 80 cr Try
- GPT Image 252%OpenAI77.4s · 60 cr Try
- Muse Image 1.052%Meta14.4s · 12 cr Try
- Seedream 5.0 Pro50%ByteDance81.0s · 49 cr Try
- Nano Banana 2 Lite46%Google21.9s · 36 cr Try
- Qwen Image 3.045%Alibaba6.8s · 32 cr Try
- 44%20.5s · 50 cr Try
- Kling v3 Omni44%Kuaishou31.4s · 35 cr Try
- 6.4s · 80 cr Try
- ImagineArt 1.5 Pro41%ImagineArt69.0s · 55 cr Try
- Seedream 5.0 Flash38%ByteDance41.4s · 22 cr Try
- Recraft v437%Recraft · retired from voting12.7s · 45 cr Try
- ImagineArt 236%ImagineArt32.0s · 60 cr Try
- Qwen Image 3.0 Pro36%Alibaba13.7s · 36 cr Try
- Recraft v4 Pro36%Recraft15.8s · 300 cr Try
- Krea 2 Medium23%Krea23.0s · 40 cr Try
- Midjourney Niji 710%Midjourney · retired from voting188.9s · 160 cr Try
- Ideogram v4.5Ideogram19.7s · 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 78% of its 27 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.