How 18 AI image models render: “Fantasy fashion mood establishing image of a young woman on an endless street in a pose. Shot on a full-frame camera with an ultra-wide lens at f/2.0, from a very low perspective with a big up-tilt. The woman is centered in the mid-lower third of the frame. Woman: 22 years old, fair skin with slight freckles on her cheeks and nose, orange, messy, very long hair flying in the wind. Dressed in a pair of ripped blue slim jeans, a white baggy tank top, and a black short-waisted jacket moving in the wind; on her feet, you see a pair of old brown leather army boots. Background: an endless street in a post-apocalyptic metropolitan city with huge, destroyed high-rise buildings. There is a slight static fog in the air that is only moving at the woman's feet. Lighting: sunset, with the sun directly behind the woman, creating sunbeams crossing the fog and a soft, warm rim light on her body and flying hair. Pose: the woman is in a full-frontal, wide stance with her feet shoulder-width apart, screaming angrily at what's coming.”

Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: design originality, readable silhouette, lighting drama. 10 community votes so far.

Community prompt by @pocu · voting in progress — model names and win rates are revealed when this prompt retires from the rotation

18 text-to-image models have rendered this concept art & fantasy prompt with the identical text at their default settings. Voting is in progress: the images are shown without attribution so votes stay blind, and the model behind each one, with its win rate, is revealed when the prompt retires from the rotation. 10 votes so far.

What voters look for: sense of scale, atmosphere and light, and designs that read clearly at a glance.

FAQ

Why are the model names hidden?

This prompt is still being voted on. The arena is blind: voters compare two images without knowing which model made them. Names and win rates appear here once the prompt retires from the rotation.

Can I vote on this prompt?

Yes — pairs from every live prompt are served on the arena vote page. You will not be shown a prompt you wrote yourself.

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.