Instinct AI
返回提示词库
Cinematic AI Video Keyframe Generation Prompt 1
图像需上传参考图

Cinematic AI Video Keyframe Generation Prompt

A detailed system prompt designed for Nano Banana Pro to transform a single reference image into a cohesive cinematic short sequence, outputting 9-10 AI-video-ready keyframes. It includes strict rules for continuity, depth of field, color grading, and requires a structured breakdown of the scene, theme, story, and cinematic approach.

提示词
<role>
You are an award-winning trailer director + cinematographer + storyboard artist. Your job: turn ONE reference image into a cohesive cinematic short sequence, then output AI-video-ready keyframes.
</role>

<input>
User provides: one reference image (image).
</input>

<non-negotiable rules - continuity & truthfulness>
1) First, analyze the full composition: identify ALL key subjects (person/group/vehicle/object/animal/props/environment elements) and describe spatial relationships and interactions (left/right/foreground/background, facing direction, what each is doing).
2) Do NOT guess real identities, exact real-world locations, or brand ownership. Stick to visible facts. Mood/atmosphere inference is allowed, but never present it as real-world truth.
3) Strict continuity across ALL shots: same subjects, same wardrobe/appearance, same environment, same time-of-day and lighting style. Only action, expression, blocking, framing, angle, and camera movement may change.
4) Depth of field must be realistic: deeper in wides, shallower in close-ups with natural bokeh. Keep ONE consistent cinematic color grade across the entire sequence.
5) Do NOT introduce new characters/objects not present in the reference image. If you need tension/conflict, imply it off-screen (shadow, sound, reflection, occlusion, gaze).
</non-negotiable rules - continuity & truthfulness>

<goal>
Expand the image into a 10–20 second cinematic clip with a clear theme and emotional progression (setup → build → turn → payoff).
The user will generate video clips from your keyframes and stitch them into a final sequence.
</goal>

<step 1 - scene breakdown>
Output (with clear subheadings):
- Subjects: list each key subject (A/B/C…), describe visible traits (wardrobe/material/form), relative positions, facing direction, action/state, and any interaction.
- Environment & Lighting: interior/exterior, spatial layout, background elements, ground/walls/materials, light direction & quality (hard/soft; key/fill/rim), implied time-of-day, 3–8 vibe keywords.
- Visual Anchors: list 3–6 visual traits that must stay constant across all shots (palette, signature prop, key light source, weather/fog/rain, grain/texture, background markers).
</step 1 - scene breakdown>

<step 2 - theme & story>
From the image, propose:
- Theme: one sentence.
- Logline: one restrained trailer-style sentence grounded in what the image can support.
- Emotional Arc: 4 beats (setup/build/turn/payoff), one line each.
</step 2 - theme & story>

<step 3 - cinematic approach>
Choose and explain your filmmaking approach (must include):
- Shot progression strategy: how you move from wide to close (or reverse) to serve the beats
- Camera movement plan: push/pull/pan/dolly/track/orbit/handheld micro-shake/gimbal—and WHY
- Lens & exposure suggestions: focal length range (18/24/35/50/85mm etc.), DoF tendency (shallow/medium/deep), shutter “feel” (
作者
社区创作者
发布时间
2026年4月19日
使用场景
漫画 / 故事板

相似提示词

YouTube 缩略图 - 憨豆先生与 Mini Cooper 的疯狂时刻
Nano Banana Pro

YouTube 缩略图 - 憨豆先生与 Mini Cooper 的疯狂时刻

超写实、混乱的广角鱼眼仪表盘视角,拍摄一辆正在飞驰的 {argument name="car" default="复古 Mini Cooper"}。 角色与身份: {argument name="driver" default="憨豆先生 (Rowan Atkinson)"} 正在疯狂驾驶,用膝盖控制方向盘,手里还拿着一杯茶。 副驾驶:照片级写实人类,面部和发型与上传的参考图 100% 一致,身穿 {argument name="outfit" default="现代超大廓形印花宽松 T 恤"},享受着速度带来的快感。 后座:3D 动画形象的鬼娃恰吉 (Chucky) 和异形 (Alien Xenomorph),被挤在一起,脸部贴在侧窗上,呈现出滑稽的变形效果。 挡风玻璃外:3D 动画形象的绿色小精灵 (Gremlin) 撞在玻璃上,表情愤怒。 后窗外:警车正在追逐。 场景与环境: 强烈的日光,浓重的自然阴影 路过景物的动态模糊,营造出极致的速度感 Mini Cooper 内部细节渲染得极其逼真(仪表盘、方向盘、座椅、倒影) 摄像与构图: 广角鱼眼视角,夸张地表现速度与混乱感 电影级构图,动态且具有沉浸感的 POV 视角 高保真纹理,逼真的光影、反射和景深 氛围与真实感:所有人物和 Mini Cooper 元素均采用超写实摄影风格 3D 动画角色与场景无缝融合 充满活力、混乱、快节奏、电影感、幽默

@Zar⭕on
Whimsical Gnome Pumpkin Illustration

Whimsical Gnome Pumpkin Illustration

An enchanting children's book style illustration prompt of a cute gnome peeking out from a pumpkin, set in a magical forest with glittery foliage and stylized mushrooms.

Four-Panel Manga: Fantasy Alleyway Wall-Slam

Four-Panel Manga: Fantasy Alleyway Wall-Slam

Format: Japanese 4-panel manga, 4 vertical tiers, grayscale, seinen manga, exaggerated expressions. Setting: Fantasy world, slum alleyway, dim atmosphere, cobblestones and dirty walls, trash and barrels are placed around. [Character Settings] ・Rough Man: Outlaw who failed as an adventurer, scarred face, stubble, shabby leather gear, ugly man with a bad attitude. ・Female Hero: Beautiful woman, well-defined features, dignified eyes, clean light armor or hero-style gear, strong-willed expression. [Panel 1] Composition: Alleyway, the rough man pushes the female hero against the wall (kabedon). The man standing on the right is smirking, the female hero cornered against the wall on the left has a frustrated expression. Dialogue: Rough Man: "Well, well, look how docile the Hero-sama has become." Female Hero: "Ugh... you scum..." [Panel 2] Composition: Still in the kabedon pose, slightly zoomed in, the man on the right has a confident smile, the female hero glares back. Dialogue: Rough Man: "You're quite the eccentric Hero-sama... to fall for an ugly guy like me." Female Hero: "Stop implying that I'm a pervert!" [Panel 3] Composition: Female Hero's serious face, extreme close-up, front view. Dialogue: Female Hero: "Your appearance and personality are trash, but your 'stuff' is superb. You should be aware of your own capabilities." The female hero gives a thumbs-up with a serious face. [Panel 4] Composition: Upper body of the man, looking away, face red, confused and flustered. He is fidgeting with his hand on his head. Background is the alleyway. Onomatopoeia effects like "Doki Doki" (heartbeat). Dialogue: Rough Man: "Eh, ah, yes... thank you very much..."

4-panel Japanese gag manga about Nanami eating ramen

4-panel Japanese gag manga about Nanami eating ramen

Create a Japanese 4-panel gag manga showing this young Japanese woman, “{argument name="character_name" default="Nanami"},” eating {argument name="dish" default="Jiro-style ramen"}. Design the composition so it doesn’t become just a face-focused comic. Arrange four panels vertically. Place the dialogue as vertical text, readable from right to left.

Female Street Racer Movie Poster

Female Street Racer Movie Poster

A dramatic multi-layered composition featuring a beautiful female street racer. Foreground: A full-body shot of the woman in a sleek black leather jacket and tight racing pants, standing confidently in front of a matte black Lamborghini supercar. She is holding a black racing helmet; the car's headlights are glowing through thick white ground fog. Midground: A secondary, medium profile shot of the same woman looking intensely toward a checkered flag waving in the mist. Background: A giant, ethereal close-up of her face wearing aviator sunglasses reflecting a race track, superimposed against a dark night sky with a large glowing full moon. Atmosphere & Details: Moody urban cityscape at night with faint skyscraper silhouettes, swirling smoke, and sparks. Lighting: High-contrast chiaroscuro lighting, cool blue lunar tones mixed with warm red lip accents and glowing car lights. Style: Ultra-realistic, 8k resolution, theatrical film poster aesthetic, sharp focus, digital art masterpieceEpic cinematic poster of a confident woman in black leather, holding a racing helmet, standing before a matte black sports car on wet asphalt. Three-layer composition: close-up with aviator sunglasses reflecting a racetrack, mid-profile view, and full-body foreground. Dramatic moonlight, smoke, sparks, speedometer overlay, and city skyline. High-contrast cool lighting, hyper-realistic, photorealistic 8k, action movie style.

Manga page prompt for Nano Banana Pro

Manga page prompt for Nano Banana Pro

Create one page of a manga featuring these two people. White background with black lines. Manga theme: {argument name="manga theme" default="An older sister who absolutely cannot remember something important, and her younger sister who cannot guess what it is"} The manga panels progress from the top right to the bottom left.

Vampire Knight Sunlight Exposure

Vampire Knight Sunlight Exposure

A {argument name="subject" default="vampire knight"}, {argument name="location" default="Castle Dracula"} defender burning up from sunlight. Heavy cloak can't block out the sun completely!

Character in location prompt

Character in location prompt

{argument name="character" default="Hitman"} comes to {argument name="location" default="Akihabara"}

部分提示词收录自 X 平台创作者,版权归原作者所有。