GPT Image 2AI-промпт
Kessoku Band Anime Rock Poster — Gritty Concert Aesthetic
Generate a dramatic, high-energy anime concert poster for Kessoku Band with ink-splatter effects, vibrant stage lighting, and bold hand-drawn typography.
1 / 4
ПРОМПТ · EN
一张极具戏剧性的动漫摇滚乐队海报，采用粗粝的泼墨宣传风格，画面呈现结束乐队 (Kessoku Band) 的四位女孩在舞台上的宽幅构图，展现动态的演唱会氛围。背景为混乱的黑色演唱会幕布，布满油漆飞溅、火花、烟雾、霓虹般的色彩线条，顶部横跨巨大的粗犷白色毛笔字样，显示乐队名称 argband name: KESSOKU BAND。在左上方添加一个巨大的漫画对话框，内含粗体手绘英文文本 argspeech bubble text: KESSOKU BAND WERE CRUSHING IT。画面中精准呈现 4 名乐队成员肩并肩站立的表演姿态，每人都穿着深色乐队 T 恤和休闲舞台装，周围环绕着风格化的彩色灯光。最左侧是山田凉 (Yamada Ryo)，留着深蓝色短发，手持奶油色贝斯，表情冷静，身后有蓝色油漆飞溅，并显示其日文和英文名："山田リョウ" 和 "YAMADA RYO"。左二为伊地知虹夏 (Ijichi Nijika)，留着金色双马尾，姿态充满活力，一只手比出胜利手势，身后有温暖的黄色飞溅，领口系着大红丝带，并显示其名称为 "伊地知虹夏" 和 "IJICHI NIJIKA"。中心区域后方放置一套红色鼓组，大鼓上印有乐队标志。右二为喜多郁代 (Kita Ikuyo)，留着鲜艳的红色长发，弹奏蓝色电吉他，身后有红色飞溅，并显示其名称为 "喜多郁代" 和 "KITA IKUYO"。最右侧是后藤一里 (Gotoh Hitori)，留着飘逸的粉色长发，弹奏黑色电吉他，身后有粉色飞溅，并显示其名称为 "後藤ひとり" 和 "Gotoh Hitori"。左下角放置巨大的亮粉色日文标题，采用充满张力的毛笔字书写 "结束バンド"，下方配有较小的白色日文标语。右下角添加一条对角线亮粉色油漆笔触横幅，内含粗体黑色手写英文标语 argbottom slogan: LIVE IS OUR LIFE, LOUDER THAN YESTERDAY. STRONGER TOGETHER.。采用高对比度的漫画海报美学，每位女孩对应饱和的蓝、黄、红、粉色调，带有粗糙的网点纹理、做旧的画笔字体、爆炸性的舞台灯光氛围以及精致的动漫角色渲染。保持构图紧凑、前卫且具有海报质感，如同官方电影或演唱会的主视觉图。
О промпте
Generate a dramatic, high-energy anime concert poster for Kessoku Band with ink-splatter effects, vibrant stage lighting, and bold hand-drawn typography. Use it as a Концепт-арт starting point for GPT Image 2: keep the visual structure and style constraints intact, then swap in your own subject, brand, or scene.
Start by replacing band name, speech bubble text, and bottom slogan, then keep the camera, composition, and material cues in the same order. This makes the output easier to compare across variations.
Как использовать этот промпт
- Copy the entire prompt text above.
- Choose a high-quality AI image model (like Midjourney, DALL-E 3, or Stable Diffusion XL) that excels in anime or illustration styles.
- Optionally tweak the variables
{band name},{speech bubble text}, and{bottom slogan}to customize the poster. - Paste the prompt into your chosen model's interface and generate the image.
