OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
烟火组成的夜空主题字样
Fireworks Spelling Out a Night Sky Theme
深蓝黑夜空中的节庆烟火展示，以火花轨迹清楚拼成用户指定的中心短句；背景烟花层次丰富但亮度较低。
提示词 / Prompt
中文提示词
创作一幅夜间烟火主题图。让 I 💗 U 作为天空中央唯一的主题字样，字形由烟火光点、火花轨迹和余烬构成，轮廓清晰、各字符容易辨认，并自然融入烟火表演。周围及后方铺展多层庆典烟花：放射状绽放、倾泻火花与不同阶段的花束形成空间纵深；背景烟花略暗，确保中央字样突出。夜空为纯净深蓝渐变至黑色，晴朗、烟雾极少。色彩以金、银、白、红、蓝为主，呈现真实的光线衰减、适度辉光、粒子运动和自然的亮度变化。整体氛围沉浸、喜庆、具有电影感；画面只呈现烟火、夜空与指定字样，不加入其他物体、人物、额外文字、标志或水印。不要承诺特定分辨率。
English prompt
Create a nighttime fireworks image. Make I 💗 U the sole central message in the sky, clearly formed from firework points, spark trails and glowing embers. Keep the contours clean and every character recognizable while integrating the lettering naturally into the show. Surround and back it with layered celebratory fireworks: radial bursts, cascading spark showers and multi-stage blooms create depth. Keep background fireworks slightly dimmer so the central message remains prominent. The sky is clear and cloudless, fading from deep navy to black with minimal smoke. Use a palette of gold, silver, white, red and blue, with natural light falloff, restrained bloom, realistic particle motion and varied brightness. The mood is immersive, festive and cinematic. Show only the fireworks, night sky and requested message; add no other objects, people, extra text, logo or watermark. Do not claim a specific output resolution.
探索更多图片和视频提示词 · 生成图片 · 生成视频 · 在 AI 画布中创作
相关作品
- 1girl
gpt image2.5生成
- 【超必杀】圣光白米大肥鱼
整体基调：东方史诗神话灾难大片质感，热血动漫爆发感融合好莱坞写实CG，UE5电影渲染，HDR光追，真实物理，强烈金色侧逆光，体积沙尘，电影景深，动态运动模糊，节奏干脆迅猛。 图1锁定角色：蓝渐变长卷发，头顶呆毛，鲸鲨鱼耳，鲸鲨长尾，女仆裙装，白色围裙，围裙印有小鲸鱼图案，Q版比例。 图2锁定巨型黑黄条纹甲壳虫王，巨口獠牙、尖刺前爪、虫群头领气质。 图3只用于冲击帧视觉语言【严格遵循Impact Frame规则】：冲击帧不是连续动画，不是撕裂米粒浪潮喷涌过程，也不是爆炸过程，而是**米粒旋风接触虫王躯干的命中顶点瞬间，强行打断正常运动、插入极短静态定格画面的视觉卡点**。冲击帧仅0.2秒，帧内无
- 法式风情地标美食海报
A premium, clean and elegant poster concept built from the source’s broad request. Eiffel Tower, Arc de Triomphe, ratatouille and Provençal bouillabaisse are curator-selected illustrative examples, not details stated by the source; they can be replaced in a future variant. The source example image i
- 梦回江户浮世绘古典人物像
A reference-led Edo-period ukiyo-e portrait transformation that preserves the supplied person’s facial identity while restyling hair, clothing and accessories in traditional Japanese fashion. The current ref-10a-v1 is the generic person preview for this workflow, not a claim about any external named
- 盛世长安万国来朝图
A text-driven historical reconstruction of the source scene: an aerial view of Kaiyuan-era Chang’an, Emperor Xuanzong and Yang Guifei looking out from Hanyuan Hall, and a distant tribute procession. The configured generic portrait is used only as a face-identity anchor for Yang Guifei in this genera
- 威震天高定西装时尚大片
A text-driven fashion-cover portrayal of Megatron, retaining the source's silver-gray mecha, haute-couture suit and cyberpunk neon setting; it does not claim an exact adaptation-specific design. / 依据文字创作的威震天时尚封面，保留银灰机甲、高定西装与赛博朋克霓虹场景；不声称复现某一改编版本的精确造型。