GPT Image Prompt
VISUAL ATTACK:
Background: Matte charcoal-black background covers 76%, with one giant cold white moon-disc / spotlight circle covering the upper-center 24%.
Color blocks: Charcoal black 52%, cold white 24%, deep blue-gray 18%, blood red 6%.
Accent: Blood red under 6%, used only on occult seals, title marks, and tiny warning glyphs.
Subject scale: Full-body subject, 92% image height, placed slightly center-right.
Hero hook: Wide-legged power stance plus the huge shadow silhouette of a heavy axe cast across the wall; face reads first, shadow weapon reads second, white shirt reads third.
Typography: Giant vertical title spine occupies the left 18%; small faction labels and episode-code style text stay bottom-right.
Layout grammar: L05 Center Emblem Hero + L12 Vertical Title Spine; negative space stays top-left around the title; eye path goes title → face → white shirt torso → shadow axe.
Contrast: Cinematic contrast.
Surface: Glossy anime-cinematic poster surface.
Text role: Branding + caption system.
PROMPT:
Create a high-impact Demon Hunter / Urban Fantasy Poster featuring a beautiful adult Asian woman with a strong model-like presence, a sleek black chin-length bob haircut with straight bangs, a visible confident face, and a cool, dangerous expression. She stands in a powerful wide-leg stance, full body visible, with one hand holding the handle of a heavy axe-like weapon so that the weapon itself reads mainly through its oversized shadow projected onto the wall. Her outfit keeps the sharp office-assassin energy: a crisp cropped white button-up shirt, a loose black tie, fitted black shorts, sheer dark thigh-high stockings, and towering black platform thigh-high boots. The body language must feel dominant, seductive, and lethal without becoming generic glamour.
Build the composition as a franchise-grade urban fantasy character poster. Place her slightly center-right at 92% image height. Behind her, a giant cold white moon-disc / spotlight circle should occupy the upper center and frame her head and torso like an emblem. The left side of the image carries a giant vertical title spine in bold pseudo-typography, while small clean occult labels, faction tags, and episode-code style text sit near the lower-right edge. The background is matte charcoal black with deep blue-gray shadow falloff, keeping the scene minimal but theatrical.
Color identity must be strict: charcoal black 52%, cold white 24%, deep blue-gray 18%, blood red 6% maximum. Use blood red only for curse seals, small warning marks, and tiny ritual accents. Add subtle occult sigils and a few restrained red glyph fragments around the moon-disc, but keep the image clean and poster-driven. The hero hook is the immediate one-second read: powerful female stance inside a moon circle, with the giant shadow of the axe cutting across the wall. Surface should feel like a glossy anime-cinematic key poster with crisp silhouette control, premium shadow rendering, strong hierarchy, and no clutter. This must feel like official promotional key art for a dark urban fantasy series.
NEGATIVE PROMPT:
generic fantasy pin-up, default action poster, weak silhouette, boring realistic studio photo, muddy colors, random neon overload, cyberpunk city clutter, ornate medieval armor, giant monster crowd, soft low-contrast lighting, unreadable text, dense paragraph text, bad poster hierarchy, stock-photo glamour, comedy vibe, cute idol vibe, flat centered layout, overdecorated background, excessive magical particles, low-detail weapon shadow, bad anatomy, short legs, distorted boots, broken hands, face distortion, eyepatch
How to use: Copy and paste this prompt into ChatGPT, Gemini, Nano Banana, or your favorite AI image tool. If it mentions LoRA, reference image, uploaded photo, or identity reference, upload your own photo first. No reference photo? Replace the character with a clear age, gender, and nationality, such as “25-year-old Japanese woman” or “30-year-old American man”.
Nanobanana Prompt
How to use: Copy and paste this prompt into ChatGPT, Gemini, Nano Banana, or your favorite AI image tool. If it mentions LoRA, reference image, uploaded photo, or identity reference, upload your own photo first. No reference photo? Replace the character with a clear age, gender, and nationality, such as “25-year-old Japanese woman” or “30-year-old American man”.