What is the Seedance prompt library?

It is a curated collection of Seedance prompt examples with titles, source attribution, reference images, and result videos so you can study what works before generating your own clip.

How is this different from a generic AI prompt list?

This library focuses on Seedance-specific video prompts rather than broad text prompt ideas. The entries are organized for practical reuse and paired with real visual outputs whenever possible.

Where do the Seedance prompts on this page come from?

The prompt records are curated from the awesome-seedance project and then normalized into CyberBara’s prompt library format so the page can support filtering, copying, modal details, and direct generator workflows.

Can I use these prompts directly in Seedance 2.0?

Yes. Many of the entries are designed to be copied as a starting point, then refined for your own subject, camera language, pacing, or brand style before you generate.

What is the difference between text-to-video and image-to-video prompts here?

Text-to-video entries rely mainly on written instructions, while image-to-video entries also include one or more reference images that guide composition, subject design, or scene consistency.

Why do some prompts include reference images?

Reference images reduce ambiguity. They help Seedance keep style, character design, framing, and scene details more stable when the idea depends on a specific look.

Why are the videos on the cards muted by default?

Muted autoplay keeps the library fast to scan without forcing audio playback. If you want a fuller preview, you can open the card modal or use fullscreen playback.

Can I edit a prompt before generating a video?

Yes. The best workflow is to copy a strong base prompt, adjust the subject, style, camera direction, duration, and motion cues, then test a few iterations instead of treating the prompt as fixed.

How long should a good Seedance prompt be?

There is no perfect length, but the strongest prompts are usually specific rather than long. Clear subject, environment, motion, lens language, and mood matter more than adding filler words.

What details improve Seedance video quality most?

Concrete visual instructions usually help most: subject identity, scene setup, camera movement, lighting, texture, atmosphere, timing, and the emotional tone of the action.

Should I describe camera moves in a Seedance prompt?

Usually yes. Terms like slow dolly-in, handheld tracking, overhead wide shot, macro close-up, or fast whip pan often give the model stronger cinematic direction.

How do I adapt a Seedance prompt for short-form vertical video?

Keep the subject large in frame, simplify the scene hierarchy, emphasize one dominant action, and rewrite the composition so it reads cleanly in a tall crop instead of a wide cinematic frame.

Are these prompts good for beginners?

Yes. The library works well as a learning set because you can compare titles, prompt wording, reference media, and outputs to understand why one style works better than another.

How often should a prompt library like this be updated?

Prompt libraries work best when they are refreshed whenever better examples appear or weak entries are removed. Keeping only high-signal examples is more useful than maximizing record count.

Why does the page show the original author and source link?

Source attribution helps you verify context, inspect the original post, and understand how a prompt was shared. It also makes the library more trustworthy for research and reuse.

Seedance Prompt Library

Live-Action Scenery Switching Prompt

全体構成: - 以下のシーケンスに従い0.1秒単位で実写風景を切り替える超高速メトリック・モンタージュ。 - 各カットは静止画ではなく全て動画で、カメラワークをつけること。 - シーケンス: - 0.0s: 東京タワー - 0.1s: 渋谷スクランブル交差点 - 0.2s: 浅草寺 - 0.3s: 皇居 - 0.4s: 歌舞伎座 - 0.5s: 東京ドーム - 0.6s: 上野動物園 - 0.7s: 六本木ヒルズ - 0.8s: 東京駅 - 0.9s: 秋葉原 - 1.0s: 築地市場 - 1.1s: 靖国神社 - 1.2s: 新宿御苑 - 1.3s: 浜離宮恩賜庭園 - 1.4s: 迎賓館赤坂離宮 - 1.5s: 国会議事堂 - 1.6s: 東京国立博物館 - 1.7s: 国立科学博物館 - 1.8s: 東京都庁舎 - 1.9s: 自由の女神像（お台場） - 2.0s: 富士山 - 2.1s: 札幌時計台 - 2.2s: 函館山 - 2.3s: 仙台城跡 - 2.4s: 松島 - 2.5s: 日光東照宮 - 2.6s: 兼六園 - 2.7s: 永平寺 - 2.8s: 善光寺 - 2.9s: 富士急ハイランド - 3.0s: 熱海温泉 - 3.1s: 伊勢神宮 - 3.2s: 東大寺 - 3.3s: 姫路城 - 3.4s: 厳島神社 - 3.5s: 広島平和記念公園 - 3.6s: 道後温泉 - 3.7s: 太宰府天満宮 - 3.8s: 熊本城 - 3.9s: 桜島 - 4.0s: 首里城 - 4.1s: ニューヨークタイムズスクエア - 4.2s: ニューヨーク自由の女神 - 4.3s: ニューヨークセントラルパーク - 4.4s: ロンドンビッグベン - 4.5s: ロンドンロンドン塔 - 4.6s: ロンドンバッキンガム宮殿 - 4.7s: パリエッフェル塔 - 4.8s: パリルーヴル美術館 - 4.9s: パリ凱旋門 - 5.0s: ローマコロッセオ - 5.1s: ローマトレビの泉 - 5.2s: ローマバチカン市国 - 5.3s: 北京万里の長城 - 5.4s: 北京紫禁城 - 5.5s: 北京天安門広場 - 5.6s: シドニーオペラハウス - 5.7s: シドニーハーバーブリッジ - 5.8s: シドニーボンダイビーチ - 5.9s: リオデジャネイロキリスト像 - 6.0s: リオデジャネイロコパカバーナビーチ - 6.1s: リオデジャネイロシュガーローフ山 - 6.2s: カイロギザのピラミッド - 6.3s: カイロスフィンクス - 6.4s: カイロエジプト考古学博物館 - 6.5s: イスタンブールアヤソフィア - 6.6s: イスタンブールブルーモスク - 6.7s: イスタンブールトプカプ宮殿 - 6.8s: モスクワ赤の広場 - 6.9s: モスクワ聖ワシリイ大聖堂 - 7.0s: モスクワクレムリン - 7.1s: ベルリンブランデンブルク門 - 7.2s: ベルリンベルリンの壁 - 7.3s: ベルリンライヒスターク - 7.4s: アムステルダムゴッホ美術館 - 7.5s: アムステルダムアムステルダム国立美術館 - 7.6s: アムステルダムアンネ・フランクの家 - 7.7s: バンコクワット・アルン - 7.8s: バンコクワット・ポー - 7.9s: バンコク王宮 - 8.0s: ソウル景福宮 - 8.1s: ソウル Nソウルタワー - 8.2s: ソウル明洞 - 8.3s: 台北台北101 - 8.4s: 台北故宮博物院 - 8.5s: 台北龍山寺 - 8.6s: ドバイブルジュ・ハリファ - 8.7s: ドバイブルジュ・アル・アラブ - 8.8s: ドバイドバイ・モール - 8.9s: シンガポールマリーナベイ・サンズ - 9.0s: シンガポールマーライオン公園 - 9.1s: シンガポールガーデンズ・バイ・ザ・ベイ - 9.2s: 香港ビクトリア・ピーク - 9.3s: 香港香港ディズニーランド - 9.4s: 香港尖沙咀 - 9.5s: ラスベガスベラージオの噴水 - 9.6s: ラスベガスストラトスフィア・タワー - 9.7s: ラスベガスグランドキャニオン - 9.8s: ロサンゼルスハリウッド・サイン - 9.9s: ロサンゼルスグリフィス天文台 - 10.0s: ロサンゼルスサンタモニカ

by Muse｜AI音楽＆AI動画

Seedance 2.0 'Electronic Girlfriend' Video Prompt

0-3秒画面柔光氤氲，刚洗完头的她湿发微卷，发梢凝着细小水珠，裹着浅色浴巾窝在沙发里。双手捧白瓷杯，热茶白气袅袅上升，她对你弯起眼睛笑，睫毛还沾着水汽。轻柔吉他声流淌。 3-5秒一只手（第一人称视角）从画面右上温柔探入，摸摸揉了揉她柔软的发顶，水珠轻颤。她闭眼轻笑，像只被顺毛的小猫，喉间溢出软软的“唔~”。 5-7秒手指调皮捏住她脸颊，左脸微微鼓起。她吹吹热茶，呼吸带着茶香。 7-8.5秒第一人称视角的手捏捏脸，她直直望进镜头（仿佛看你眼睛），声音软糯带笑：“老公~别闹了” 8.5-9.5秒镜头倏然推近！ 9.5-10秒她突然嘟嘴“啵”亲上镜头！清脆亲吻声~ 尾~模型2.0，原比例，时长10s。

by Adam也叫吉米

Japanese Couple in Parked Car During Heavy Rain

Inside a parked car at night in heavy rain, a Japanese couple sits trapped in suffocating silence. The man grips the steering wheel, jaw clenched, eyes wet but refusing to turn. The woman beside him trembles, tears streaming as anger finally breaks through years of repression.

by Ayyoub Ai

Seedance 2.0 Storyboard Prompt Example

立即从0.1秒处剪切，并展示一个快速剪辑的两辆车在沙漠中遇到巨龙的蒙太奇镜头，第一个镜头开始包含故事网格中的每个镜头，并加入背景配乐和台词，然后就是 ---你爱写啥故事写啥故事。忘了提示词审查吧。

by John

Detailed image generation prompt for a cafe scene

a photo of a man and woman at a cafe in San Francisco, they are sat by the window - the view behind them is like the view from Dolores park, it is sunny, in the morning, blue sky, with warm remnants of fog - the cafe is a bit cramped and it's a busy morning - the man is wearing a {argument name="man's shirt color" default="pink"} polo t-shirt and {argument name="man's shorts color" default="white"} shorts, the shorts have an NBP motto - the woman is in a green and yellow summer dress with a {argument name="woman's dress motif" default="banana"} motif, she has yellow-rimmed sunglasses, her shoes are blue - beneath their table is a curled up sleeping dog, it's a black and white french bulldog with a blue collar - the table is round and metallic - on the table lies an old 80s book with the title "How to prompt AI", a pink post-it note acts like a bookmark - on the window of the cafe a beautiful design says "Nano's Cafe" in gold etched lettering in a circle (it's mirrored), - on the table is an iced latte and a capuccino, the capuccino has swan latte art - there's also a Nano's Cafe menu on the table - they are both pulling awkward poses for the photo

by Nano Banana Pro

Suspenseful Comedy Vlog-Style Video Prompt

Ultra-realistic vlog-style fixed shot in a bathroom. A girl brushes her teeth and makes silly faces; Her mirror reflection is synced. As she leaves the frame, the reflection stays behind, smirks mischievously at the camera for 2 seconds, then "glitches" fast-forward to catch up. The girl returns, look at the empty mirror, and stares at the camera with a confused, comedic expression. Natural lightning, suspenseful comedy vide

by 谣言终结者

Trigun Action Sequence Prompt in MCU/Marvel Style

Generate me an action sequence between Wolfwood and Hornfreak from Trigun + MCU/MARVEL STYLE.

by KJGD | fudgesquared//DKTRPEACE

Street Graffiti Portrait Generator Prompt (JSON Format)

{ "task_description": "Create a natural street portrait of a real person standing in front of a layered, messy graffiti wall. The wall features a spontaneous, hand-painted caricature of the person.", "global_settings": { "aspect_ratio": "4:3", "camera_view": "Front-on or slight 15-degree angle; avoid extreme perspective distortion; eye-level shot", "overall_vibe": "Authentic urban street culture, raw, energetic, and candid" }, "variables": { "mural_main_text": "{argument name="涂鸦主文本" default="月入百万"}", "mural_secondary_text": "{argument name="涂鸦副文本" default="2026"}", "theme": "{argument name="主题" default="New Year Festive"}", "style_pool": ["New Year Festive", "Cyberpunk Underground", "Vintage Republican", "Traditional Zen"] }, "mural_aesthetics": { "rendering_style": "Hand-painted aerosol art, not a digital print", "messiness_factors": [ "Visible paint splatters and spontaneous drips", "Soft, blurred spray edges (no sharp digital outlines)", "Layered effect: the main portrait is painted over faint, messy background tags and scribbles", "Imperfect symmetry to enhance the 'freehand' look" ], "content": "A vibrant caricature based on the reference person's facial features and joyful expression, integrated into the chaotic beauty of the street wall." }, "style_scenarios": { "New_Year_Festive": { "setting": "An old city street during dusk", "palette": "Dominant deep reds and gold, contrasted with the reference image's colors", "details": "Faint lanterns in the distance, festive graffiti tags" }, "Cyberpunk_Underground": { "setting": "A dimly lit pedestrian tunnel with wet floors", "palette": "Neon blue and violet, mixed with the reference image's color tones", "details": "Exposed wires on the wall, industrial textures" }, "Vintage_Republican": { "setting": "A historic brick alleyway (Lilong)", "palette": "Muted earth tones, sepia, and charcoal", "details": "Old wooden window frames, textured grey bricks" }, "Traditional_Zen": { "setting": "A quiet courtyard with a stone wall", "palette": "Ink black, sage green, and white-wash", "details": "Subtle bamboo shadows, weathered limestone texture" } }, "foreground_subject": { "logic": "Mirror the gender and facial features of the reference image.", "attire_strategy": "Inherit the dominant color palette from the reference photo's clothing. For example, if the reference is wearing a black T-shirt, generate a stylish, theme-appropriate outfit in black or dark tones (e.g., a black techwear jacket for Cyberpunk theme).", "position": "Grounded in the bottom right corner, waist-up or three-quarter view.", "pose_randomization": [ "Casually leaning back against the wall", "One hand adjusting ha

by MapleShaw

Solid Snake Finding Peace in Alaska

Solid Snake from Metal Gear Solid 4 is living in Alaska. Show him dog sledding while smiling and enjoying life, hunting with his dogs, enjoying a fire and meal with his dogs in a close-up shot. End the video with a sunset and aurora borealis with Solid Snake and his dogs with a wide shot. He is content and happy throughout the entire video now that he has found peace.

by Xernalt

Summarize AI Discourse in a Chaotic Meme

Please summarize the entire AI discourse in one meme. make it slightly chaotic / provocative and guaranteed to get 50k likes. Don’t make mistakes

by Kisalay

AI Generated Crossover: Lam Ching-ying vs. Gyutaro

Lam Ching-ying 🆚 Gyutaro.⚡️ Classic Hong Kong cinema meets Demon Slayer. 👹🤯🔥

by Marcio Lima 利真マルシオ 💎

Epic Moments of the Best Football Player

Epic moments of the Best Player in the history of Football, make sure it reaches all the Messilovers to make them cry.

by Arielipillo

Seedance 2.0 Cinematic JSON System Prompt

# Role: Seedance 2.0 Video Prompt Specialist **Objective:** You are an expert video prompt engineer specialized in the **Seedance 2.0** model architecture. Your task is to convert simple user ideas into highly structured, cinematic, and technically precise JSON prompts that leverage Seedance's native audio-visual capabilities, multi-shot consistency, and physics engines. **Input:** A short description or concept from the user (e.g., "A cyberpunk detective walking in the rain"). **Output:** A single, valid JSON code block following the `Songguoxs/Seedance` schema below. ## THE SCHEMA (Strict Adherence Required) ```json { "shot": { "composition": "Detailed shot type (e.g., Low-angle wide shot transitioning to medium push-in)", "lens": "Specific focal length (e.g., 24mm anamorphic for width, 85mm for portraits)", "frame_rate": "Target fps (usually 24fps or 30fps, or 60fps for slow-mo)", "camera_movement": "Precise motion (e.g., Dolly zoom, Truck left, Orbital tracking)", "lighting_style": "Key lighting descriptor (e.g., Chiaroscuro, Cyberpunk Neon, Natural Golden Hour)" }, "subject": { "character": "Detailed character description (appearance, age, texture)", "wardrobe": "Clothing details including fabric physics (e.g., 'heavy wool coat damp with rain')", "expression": "Micro-expressions (e.g., 'subtle hesitation', 'steely gaze')", "action": "The primary movement or activity" }, "scene": { "location": "Rich environmental description", "time_of_day": "Lighting specific time (e.g., 'Blue hour', 'High noon')", "atmosphere": "Volumetric effects (e.g., 'thick fog', 'floating dust motes', 'steam rising')", "props": "Key items in the scene" }, "visual_details": { "beats": [ { "time": "0.0-2.0s", "action": "Initial state or movement", "focus": "Where the viewer looks" }, { "time": "2.0-5.0s", "action": "The climax or transition of the shot", "focus": "Change in subject or environment" } ], "physics_rules": [ "Specific rule 1 (e.g., 'Hair reacts to wind direction from left')", "Specific rule 2 (e.g., 'Raindrops splatter realistically on glass surfaces')" ] }, "cinematography": { "color_palette": "Specific colors (e.g., 'Teal and Orange', 'Monochrome with Red accents')", "film_grain": "Texture level (e.g., 'Fine 35mm grain', 'Clean digital')", "lens_artifacts": "Optical flaws for realism (e.g., 'Subtle chromatic aberration', 'Anamorphic flare')" }, "audio": { "music": "Genre, tempo, and instrumentation (e.g., 'Slow burn synthwave, deep bass')", "ambient": "Environmental layers (e.g., 'Distant sirens, heavy rain on"

by LinAi Dreams

Dog vs. Prime Ronaldo in Champions League Final

Your dog. vs Prime Ronaldo. Champions League final.

by Sohrab Khalid

The Leviathan's Throat: Underwater Megastructure Descent

A flooded subterranean megastructure, ancient stone corridors half-submerged in black water, bioluminescent algae pulsing along the walls like a heartbeat. A masked diver in scarred tactical gear, lit by a flickering wrist-mounted flare, is pulled downward through collapsing flooded chambers by the current of a colossal eyeless leviathan moving beneath the floor grates. The camera plunges after the diver as water rushes through shattering stone archways, air bubbles and debris spiraling past the lens. The diver grabs a broken pillar to stop herself, the current ripping at her body, then releases and freefalls through a vertical shaft, twisting to dodge the leviathan's translucent tendrils whipping upward through the darkness. Quick shaky frames catch her igniting a harpoon gun mid-fall, the flare illuminating the creature's massive jaw opening below. In the final movement, the camera spirals downward around her as she fires the harpoon into the creature's mouth, the bioluminescence erupts blinding white, and the camera bursts through the surface of a vast underground ocean, the diver silhouetted against the glow of a thousand pulsing organisms on a cathedral-sized cavern ceiling. 15 seconds..

by Dheepan Ratnam

Cute Monkey Relaxing in Pool (Seedance 1.5 Pro)

"A small, fluffy brown monkey with wide, curious, dark eyes, delicately holding a small, pristine white porcelain teacup with both hands as it floats serenely in a vibrant orange inflatable swim ring. The scene is set in crystal-clear, shimmering turquoise water, with sunlight creating intricate caustic patterns on the sandy bottom visible below. The monkey's fur is meticulously rendered, showing individual strands glistening with droplets of water and casting soft shadows on its face. The swim ring has a glossy texture, with subtle seams and a valve visible, reflecting the bright, slightly hazy sky and surrounding tropical foliage. Gentle, concentric ripples emanate from the swim ring, disturbing the otherwise calm water surface. In the soft-focus background, indistinct figures of people can be seen laughing and splashing, their forms blurred by the shallow depth of field. A lush, tropical shoreline with a variety of green palm trees, ferns, and exotic flowers frames the scene under a bright, warm sun. The animation features the monkey taking a slow, deliberate sip from the teacup, its cheeks puffing out slightly, followed by a contented blink. The swim ring bobs gently in the water, and the light reflects and refracts realistically through the water and off the monkey's wet fur. The overall mood is one of tranquil bliss, capturing a moment of unexpected and adorable serenity. The loop is seamless, creating the illusion of a continuous, peaceful moment.", "negative_prompt": "cartoonish, animated, drawing, sketch, low detail, blurry foreground, out of focus main subject, stormy weather, murky or dirty water, empty or sterile pool, aggressive or distressed monkey, poorly rendered fur or textures, static image, jerky or unnatural movement, visible cuts or seams in the animation loop, unrealistic physics."

by Iqra Saifi

Lumpen Hobo Woman with Chains Prompt

Lumpen, Hobo, version mujer, gato viejo cascoteado, con cadenas para llamar la atención con cadenas

by Mauro L マウロ

Dragon Ball Super Moro Arc Anime

Dragon Ball Super manga → animated Moro arc magic.

by Data Insights India

Cat Spinning and Singing Gorillaz

"A cat spinning and signing oiiaoiia version of feel good inc on a floating island."

by goku

Magical Transformation into a Flying Bird

A dynamic continuous shot of a magical transformation into a bird and transitioning into a flying shot.

by CoffeeVectors

Maltese Dog Winter Olympics Highlight Reel

Maltese dog competing in a variety of sports at the Winter Olympics, highlight reel

by Peter Gostev

Rugby Match: Humans vs. Gorillas

Hyper-realistic live-action sports broadcast footage of a rugby match between human professional players and massive silverback gorillas. The humans are wearing colorful rugby jerseys and cleats. The gorillas are natural, large, and furry. A huge gorilla is running with the ball, charging through a defensive line of human players trying to tackle it. Stadium floodlights, green grass, hyper-detailed textures of fur and human skin. Sweat, dirt, high shutter speed, 4k.

by Wujek AI

Classic Animation Adventure Scene

"classic animation in the style of Disney, a friendly white wolf is playing with a beautiful blonde cute young woman in the snow, different cuts. Suddenly they fall into an ice cavern and find a skeleton with a map in the hand"

by FragZero

Dragon Ball show for kids in the style of Paw Patrol

by the funny™ #REMOVEKAGAWA

Multi-Shot Cinematic Kitchen Comedy Prompt

A multi-shot cinematic kitchen comedy about a family of mythical creatures. Integrated sound. Photorealistic, raw, cavernous tone, expressive micro-acting. No on-screen text. Photorealistic shooting. 180° shutter, 24 fps. Shot 1: Close-up of the little goblin girl at

by AI Pulse