Image - 2026-05-22 08:43

Art style: Disney 3D Animation. Comic wide shot on a sunny town square: on the cobblestones in front of a fountain stands a goofy cartoon villain — a short pudgy man in a tight purple costume with a big "Z" on the chest, a green eye-mask, droopy moustache. Beside him: a huge ridiculous contraption of welded pipes, hoses, dials, blinking bulbs and a large extraction nozzle through which a thin trickle of golden oil flows (the "butter-stealer"). The villain gleefully rubs his hands and laughs "ha-ha-ha," head thrown back, mouth in a villain-grin. Around the square: astonished townsfolk — an old lady with her dog frozen mid-step, a paperboy who has dropped his papers, a grandmother from a second-floor window pointing a finger. The fountain in the middle, pigeons scattered. Lighting: bright midday sun, crisp shadows, an overall bright comic palette. Composition: villain and machine as the central focus, townsfolk as edge framing, fountain in the lower-central. Palette: purple costume, green mask, copper machine, gold-oil accents. Mood: light comic horror. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FINAL STYLE ENFORCEMENT (this is the authoritative rendering directive — it overrides any style wording elsewhere in the prompt): Render this image entirely in "Disney 3D Animation" style. Match the lighting grammar, material response, colour science, level of realism / stylisation, line weight, and shading model typical of "Disney 3D Animation". Keep the subject, composition, camera angle, lighting direction, and colour palette from the description above — but EVERY surface, skin, fabric, material, and environmental element must be rendered in the "Disney 3D Animation" idiom, not in any other medium. Character appearance reference (MUST match exactly): - Главный герой: A child stylized as a modern Disney 3D animated character (Tangled / Frozen / Moana look) — polished 3D rendering, big sparkly eyes, soft idealized features, magical warm lighting, rich saturated palette. Use the reference image as the canonical visual identity across every scene.