Open BudgetPixel
Illustration & anime

How 20 AI image models render: “Character exploration sheet of the same woman: several bust and waist-up studies with varied expressions and 3/4 views, including one from behind, glancing over her shoulder at the viewer; one larger central portrait; and one full-length figure at the side, spanning the image height. Plain light-gray background with irregular painted edges. Character: 25-year-old Korean woman with long straight black hair and two platinum face-framing streaks from roots to ends, glasses, tipped almond eyes, Asian skin tone, plaid button-up tied at the waist, cuffed denim shorts, chunky red sneakers. Style: stylized semi-realistic digital painting; animation-inspired proportions, large eyes, strong brows, simplified but solid anatomy, painterly shape-based rendering, minimal linework, soft facial shading, angular clothing brushwork, warm luminous skin with peach/terracotta undertones and rosy cheeks/nose, sculpted hair, muted charcoal/earth palette, soft studio light, loose unfinished edges.”

Same prompt, sent verbatim, at each model's default settings and a fixed seed. Judge: line quality, colour, style consistency. 38 community votes so far.

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

20 text-to-image models have rendered this illustration & anime 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. 38 votes so far.

What voters look for: confident line work, consistent style from edge to edge, deliberate colour and readable shapes.

  • Model 1
    Revealed when voting closes
    Voting in progress
  • Model 2
    Revealed when voting closes
    Voting in progress
  • Model 3
    Revealed when voting closes
    Voting in progress
  • Model 4
    Revealed when voting closes
    Voting in progress
  • Model 5
    Revealed when voting closes
    Voting in progress
  • Model 6
    Revealed when voting closes
    Voting in progress
  • Model 7
    Revealed when voting closes
    Voting in progress
  • Model 8
    Revealed when voting closes
    Voting in progress
  • Model 9
    Revealed when voting closes
    Voting in progress
  • Model 10
    Revealed when voting closes
    Voting in progress
  • Model 11
    Revealed when voting closes
    Voting in progress
  • Model 12
    Revealed when voting closes
    Voting in progress
  • Model 13
    Revealed when voting closes
    Voting in progress
  • Model 14
    Revealed when voting closes
    Voting in progress
  • Model 15
    Revealed when voting closes
    Voting in progress
  • Model 16
    Revealed when voting closes
    Voting in progress
  • Model 17
    Revealed when voting closes
    Voting in progress
  • Model 18
    Revealed when voting closes
    Voting in progress
  • Model 19
    Revealed when voting closes
    Voting in progress
  • Model 20
    Revealed when voting closes
    Voting in progress

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.
Vote on pairs like thisIllustration & anime leaderboardAll prompts and the rules