How 20 AI image models render: “A three-row, six-panel sequence. Panel 1: A short-haired, nerdy man is talking to his friend Babu, another nerd with curly hair and round-frame glasses. They are both 20. Babu's room has a guitar and boxes full of things. Panel 2: Babu is exclaiming to his friend, saying something! Middle row, panel 3: Babu brings a spiky Mohican wig, pink to purple in color, out of one of his boxes. But it is oddly big. Panel 4: Babu stands in front of a wall mirror wearing the spiky wig—it is oddly very big! He looks concerned. Bottom row, panel 5: Babu's nerdy friend exclaims something to him, as if he has had an idea. Bottom row, panel 6: Babu is in a right-hand-drive sedan with a sunroof. Half of the spiky hair on his wig sticks out through the sunroof. The car is parked in front of a neighborhood hangout. Babu is looking out of the window, with one hand out of it. He wears sunglasses, trying to look cool. Several pretty adult women his age are giggling at him.”
Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: every stated element present, correct count, correct placement. 180 community votes so far.
Community prompt by @sharierkhan · voting closed 2026-10-22
Checklist: 3 rows · 6 panels · Panel 3 shows Babu bringing out an oversized pink-to-purple spiky wig · Panel 4 shows Babu wearing the wig in front of a mirror · Panel 6 shows Babu in a right-hand-drive sedan with a sunroof · Adult women Babu's age are giggling at him
20 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 Flare is the community favourite so far, winning 91% of its 11 head-to-head votes on this prompt. Grok Imagine Image Quality was the fastest at 6.0s.
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 Flare91%OpenAI32.6s · 40 cr Try
- Krea 2 Large69%Krea28.8s · 80 cr Try
- 57%22.7s · 50 cr Try
- Muse Image 1.047%Meta34.7s · 12 cr Try
- 6.0s · 80 cr Try
- FLUX 3 Image46%Black Forest Labs37.3s · 65 cr Try
- FLUX 3 Image Klein46%Black Forest Labs8.8s · 12 cr Try
- Kling v3 Omni43%Kuaishou44.4s · 35 cr Try
- Midjourney V8.243%Midjourney130.3s · 160 cr Try
- Ideogram v436%Ideogram20.8s · 40 cr Try
- Qwen Image 3.036%Alibaba7.7s · 32 cr Try
- GPT Image 2.5 Sunburst35%OpenAI40.1s · 40 cr Try
- Nano Banana 2.131%Google32.8s · 31 cr Try
- Ideogram v4.527%Ideogram18.5s · 80 cr Try
- Krea 2 Medium25%Krea16.5s · 40 cr Try
- Seedream 5.0 Flash25%ByteDance23.7s · 22 cr Try
- Nano Banana 2 Lite23%Google17.9s · 36 cr Try
- Seedream 5.0 Pro20%ByteDance91.3s · 49 cr Try
- Qwen Image 3.0 Pro18%Alibaba9.9s · 36 cr Try
FAQ
- Which AI model renders this prompt best?
- GPT Image 2.5 Flare leads this prompt in the BudgetPixel AI Image Arena, winning 91% 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.