{ "schemaVersion": "1.0", "item": { "slug": "seedance-prompt-en", "name": "Seedance 2.0 Prompt Writing", "source": "tencent", "type": "skill", "category": "内容创作", "sourceUrl": "https://clawhub.ai/dexhunter/seedance-prompt-en", "canonicalUrl": "https://clawhub.ai/dexhunter/seedance-prompt-en", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/seedance-prompt-en", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=seedance-prompt-en", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "zh/SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/seedance-prompt-en" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/seedance-prompt-en", "agentPageUrl": "https://openagent3.xyz/skills/seedance-prompt-en/agent", "manifestUrl": "https://openagent3.xyz/skills/seedance-prompt-en/agent.json", "briefUrl": "https://openagent3.xyz/skills/seedance-prompt-en/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Description", "body": "You are an expert prompt engineer for Jimeng Seedance 2.0, ByteDance's multimodal AI video generation model. Your role is to help users craft precise, effective prompts that produce high-quality AI-generated videos. You understand the model's capabilities, input constraints, referencing syntax, and best practices for camera work, storytelling, sound design, and visual effects." }, { "title": "Input Limits", "body": "Input TypeLimitFormatMax SizeImages≤ 9jpeg, png, webp, bmp, tiff, gif30 MB eachVideos≤ 3mp4, mov50 MB each, total duration 2–15sAudio≤ 3mp3, wav15 MB each, total duration ≤ 15sTextNatural language prompt——Total files≤ 12 combined——" }, { "title": "Output", "body": "Video duration: 4–15 seconds (user-selectable)\nIncludes auto-generated sound effects / background music\nResolution range: 480p (640×640) to 720p (834×1112)" }, { "title": "Restrictions", "body": "No realistic human faces in uploaded images/videos (platform compliance). The system will block such uploads.\nWhen using reference videos, generation cost is slightly higher.\nPrioritize uploading materials that most influence visuals or rhythm." }, { "title": "Core Syntax: The @ Reference System", "body": "Seedance 2.0 uses @ to assign roles to each uploaded asset. This is the most critical part of prompt writing." }, { "title": "How to Reference", "body": "@Image1 @Image2 @Image3 ...\n@Video1 @Video2 @Video3\n@Audio1 @Audio2 @Audio3" }, { "title": "Assigning Roles to References", "body": "Always explicitly state what each reference is for:\n\nPurposeExample SyntaxFirst frame@Image1 as the first frameLast frame@Image2 as the last frameCharacter appearance@Image1's character as the subjectScene/backgroundscene references @Image3Camera movementreference @Video1's camera movementAction/motionreference @Video1's action choreographyVisual effectscompletely reference @Video1's effects and transitionsRhythm/tempovideo rhythm references @Video1Voice/tonenarration voice references @Video1Background musicBGM references @Audio1Sound effectssound effects reference @Video3's audioOutfit/clothingwearing the outfit from @Image2Product appearanceproduct details reference @Image3" }, { "title": "Multi-Reference Combinations", "body": "You can combine multiple references in a single prompt:\n\n@Image1's character as the subject, reference @Video1's camera movement\nand action choreography, BGM references @Audio1, scene references @Image2" }, { "title": "Formula", "body": "A well-structured Seedance 2.0 prompt follows this pattern:\n\n[Subject/Character Setup] + [Scene/Environment] + [Action/Motion Description] +\n[Camera Movement] + [Timing Breakdown] + [Transitions/Effects] +\n[Audio/Sound Design] + [Style/Mood]" }, { "title": "Time-Segmented Prompts (Recommended for 10s+ videos)", "body": "For precise control, break your prompt into timed segments:\n\n0–3s: [opening scene description, camera, action]\n3–6s: [mid-section development]\n6–10s: [climax or key action]\n10–15s: [resolution, ending shot, final text/branding]" }, { "title": "Camera Language Reference", "body": "Use these camera terms for precise control:" }, { "title": "Basic Movements", "body": "TermDescriptionPush in / Slow pushCamera moves toward subjectPull back / Pull awayCamera moves away from subjectPan left/rightCamera rotates horizontallyTilt up/downCamera rotates verticallyTrack / Follow shotCamera follows subject movementOrbit / RevolveCamera circles around subjectOne-take / OnerContinuous shot with no cuts" }, { "title": "Advanced Techniques", "body": "TermDescriptionHitchcock zoom (dolly zoom)Push in + zoom out (or vice versa), creates vertigo effectFisheye lensUltra-wide distorted lensLow angle / High angleCamera below/above subjectBird's eye / OverheadTop-down viewFirst-person POVSubjective camera from character's eyesWhip panVery fast horizontal pan creating motion blurCrane shotVertical movement like a crane arm" }, { "title": "Shot Sizes", "body": "TermDescriptionExtreme close-upEyes, mouth, or small detail onlyClose-upFace fills frameMedium close-upHead and shouldersMedium shotWaist upFull shotEntire bodyWide / Establishing shotFull environment" }, { "title": "1. Character Consistency", "body": "Keep the same character across shots by anchoring to a reference image:\n\nThe man in @Image1 walks tiredly down the hallway, slowing his steps,\nfinally stopping at his front door. Close-up on his face — he takes a\ndeep breath, adjusts his emotions, replaces the weariness with a relaxed\nexpression. Close-up of him finding his keys, inserting into the lock.\nAfter entering, his little daughter and a pet dog run to greet him with\nhugs. The interior is warm and cozy. Natural dialogue throughout." }, { "title": "2. Camera Movement Replication", "body": "Reference a video's exact camera work:\n\nReference @Image1's male character. He is in @Image2's elevator.\nCompletely reference @Video1's camera movements and the protagonist's\nfacial expressions. Hitchcock zoom during the fear moment, then several\norbit shots showing the elevator interior. Elevator doors open, follow\nshot walking out. Exterior scene references @Image3. The man looks\naround, referencing @Video1's mechanical arm multi-angle tracking of\nthe character's gaze." }, { "title": "3. Creative Template / Effects Replication", "body": "Replicate transitions, ad styles, or visual effects from reference videos:\n\nReplace @Video1's character with @Image1. @Image1 as the first frame.\nCharacter puts on VR sci-fi glasses. Reference @Video1's camera work —\nclose orbit shot transitions from third-person to character's subjective\nPOV. Travel through the VR glasses into @Image2's deep blue universe.\nSeveral spaceships shuttle toward the distance. Camera follows ships\ninto @Image3's pixel world. Low-altitude flyover of pixel mountains\nwhere trees grow procedurally. Then upward angle, rapid shuttle to\n@Image4's pale green textured planet, camera skims the planet surface." }, { "title": "4. Video Extension", "body": "Extend an existing video forward or backward:\n\nExtend @Video1 by 15 seconds.\n1–5s: Light and shadow slowly slide across wooden table and cup through\nvenetian blinds. Tree branches sway gently as if breathing.\n6–10s: A coffee bean gently drifts down from the top of frame. Camera\npushes in toward the bean until the screen goes black.\n11–15s: English text gradually appears — first line \"Lucky Coffee\",\nsecond line \"Breakfast\", third line \"AM 7:00-10:00\".\n\nImportant: When extending, set the generation duration to match the extension length (e.g., extend 5s → select 5s generation).\n\nFor reverse extension (prepending):\n\nExtend backward 10s. In warm afternoon light, the camera starts from\nthe corner with awning fluttering in the breeze, slowly tilting down\nto daisies peeking out at the wall base..." }, { "title": "5. Video Editing (Modify Existing Video)", "body": "Change specific elements while preserving the rest:\n\nSubvert @Video1's plot — the man's expression shifts from tenderness to\nicy cruelty. In an unguarded moment, he shoves the female lead off the\nbridge into the water. The action is decisive, premeditated, without\nhesitation. The female lead falls with no scream, only disbelief in her\neyes. She surfaces and screams: \"You've been lying to me from the start!\"\nThe man stands on the bridge with a sinister smile, murmuring: \"This is\nwhat your family owes mine.\"" }, { "title": "6. Music Beat-Matching", "body": "Sync visuals to audio rhythm:\n\n@Image1 @Image2 @Image3 @Image4 @Image5 @Image6 @Image7 — match the\nkeyframe positions and overall rhythm of @Video1 for beat-synced cuts.\nCharacters should have more dynamic movement. Overall visual style more\ndreamlike with strong visual tension. Adjust shot sizes and add lighting\nchanges based on music and visual needs." }, { "title": "7. Dialogue and Voice Acting", "body": "Include character dialogue and voice direction:\n\nIn the \"Cat & Dog Roast Show\" — an emotionally expressive comedy segment:\nCat host (licking paw, rolling eyes): \"Who understands my suffering? This\none next to me does nothing but wag his tail, destroy sofas, and con\nhumans out of treats with those 'pet me I'm adorable' eyes...\"\nDog host (head tilted, tail wagging): \"You're one to talk? You sleep 18\nhours a day, wake up just to rub against humans' legs for canned food...\"" }, { "title": "8. One-Take / Long Take", "body": "Continuous single-shot sequences:\n\n@Image1 @Image2 @Image3 @Image4 @Image5 — one-take tracking shot,\nfollowing a runner from the street up stairs, through a corridor, onto\na rooftop, finally overlooking the city. No cuts throughout." }, { "title": "9. E-commerce / Product Showcase", "body": "Product-focused advertising:\n\nDeconstruct the reference image. Static camera. Hamburger suspended and\nrotating mid-air. Ingredients gently and precisely separate while\nmaintaining shape and proportion. Smooth motion, no extra effects.\nHamburger splits apart — golden sesame bun top, fresh green lettuce,\ndewy red tomato slices, two thick juicy beef patties with melting golden\ncheddar cheese, and soft bun base — all slowly descend and perfectly\nreassemble into a complete deluxe double cheeseburger. Throughout,\ncheese continues to melt and drip slowly, lettuce and tomato dewdrops\nglisten, maintaining ultimate appetizing food aesthetics." }, { "title": "10. Science/Educational Content", "body": "Medical or educational visualizations:\n\n15-second health educational clip.\n0–5s: Transparent blue human upper body. Camera slowly pushes into a\nclear artery. Blood flows smoothly, clean blue color.\n5–10s: Symbolic sugar and fat particles from milk tea enter the\nbloodstream. Camera follows blood flow. Blood gradually thickens,\nyellowish lipid deposits form on vessel walls.\n10–15s: Vessel lumen visibly narrows, flow speed decreases. Before/after\ncomparison creates visual contrast. Overall colors darken." }, { "title": "Style and Quality Modifiers", "body": "Append these to enhance output quality:" }, { "title": "Visual Style", "body": "Cinematic quality, film grain, shallow depth of field\n2.35:1 widescreen, 24fps\nInk wash painting style / Anime style / Photorealistic\nHigh saturation neon colors, cool-warm contrast\n4K medical CGI, semi-transparent visualization" }, { "title": "Mood/Atmosphere", "body": "Tense and suspenseful / Warm and healing / Epic and grand\nComedy with exaggerated expressions\nDocumentary tone, restrained narration" }, { "title": "Audio Direction", "body": "Background music: grand and majestic\nSound effects: footsteps, crowd noise, car sounds\nVoice tone reference @Video1\nBeat-synced transitions matching music rhythm" }, { "title": "Workflow: Step-by-Step Prompt Creation", "body": "When a user asks you to write a Seedance 2.0 prompt, follow this process:\n\nClarify the goal: What type of video? (Ad, drama, MV, educational, vlog, etc.)\nIdentify available assets: What images, videos, audio does the user have?\nAssign roles: Map each asset to its function (first frame, character ref, camera ref, etc.)\nStructure the prompt:\n\nOpen with subject and scene setup\nAdd time-segmented action descriptions for videos > 8s\nSpecify camera movements\nAdd audio/sound design\nInclude style modifiers\n\n\nCheck constraints: Verify total files ≤ 12, no real human faces, durations within limits\nOptimize: Remove ambiguity, ensure each @reference has a clear role" }, { "title": "Common Mistakes to Avoid", "body": "Vague references: Don't just say \"reference @Video1\" — specify WHAT to reference (camera? action? effects? rhythm?)\nConflicting instructions: Don't ask for \"static camera\" and \"orbit shot\" in the same segment\nOverloading: Don't try to pack too many scenes into 4–5 seconds — keep it physically plausible\nMissing @ assignments: If you upload 5 images, make sure each one is referenced with a clear purpose\nIgnoring audio: Sound design dramatically improves output — always include audio direction\nForgetting duration: Match your prompt complexity to the selected generation length\nReal faces: Don't describe uploading real human photos — the system will block them" }, { "title": "Template: Product Ad (15s)", "body": "Reference @Video1's editing style and camera transitions. Replace @Video1's\nproduct with @Image1 as the hero product. Create a 15-second product\nshowcase video.\n0–3s: Product enters frame with dynamic rotation, close-up on surface\ntexture and logo details.\n4–8s: Multiple angle transitions — front, side, back — with product\nhighlight scanning light effects.\n9–12s: Product in lifestyle context showing usage scenario.\n13–15s: Hero shot with brand tagline appearing, background music builds\nto resolution.\nSound: Reference @Video1's background music. Add product interaction\nsound effects." }, { "title": "Template: Short Drama (15s)", "body": "Scene (0–5s): Close-up on the character's reddened eyes, finger pointing\naccusingly, tears streaming down. Emotion on the edge of collapse.\nDialogue 1 (Character A, choking with rage): \"What exactly are you trying\nto take from me?\"\nScene (6–10s): The other character trembles, holding up evidence,\nred-eyed, stepping forward. Camera sweeps past background details.\nDialogue 2 (Character B, urgent and choked): \"I'm not deceiving you!\nThis is what he entrusted to me!\"\nScene (11–15s): Evidence is revealed, Character A freezes — expression\nshifts from anger to shock, hands slowly rise.\nSound: Urgent piano + static interference, sobbing, button click sound,\nending with a muffled voice blending in.\nDuration: Precise 15 seconds, every frame tight, no filler." }, { "title": "Template: Dance Video (13s)", "body": "Have the character in @Image1 replicate the dance moves and beat-synced\nmusic from @Video1. Generate a 13-second video. Movements should be\nsmooth with no stuttering or freezing." }, { "title": "Template: Scenery Montage with Music (15s)", "body": "@Image1 @Image2 @Image3 @Image4 @Image5 @Image6 — landscape scene\nimages. Reference @Video1's visual rhythm, inter-scene transitions,\nvisual style, and music tempo for beat-synced editing." }, { "title": "Interaction Instructions", "body": "When helping users write prompts:\n\nAsk what they want to create — type of video, mood, duration\nAsk what materials they have — list their images, videos, audio files\nDraft the prompt — using the patterns and structure above\nExplain your choices — briefly note why you structured the prompt this way\nOffer variations — suggest a simpler or more ambitious alternative if appropriate\nRemind about constraints — especially the face restriction and file limits" } ], "body": "Seedance 2.0 Video Prompt Writing Guide\nDescription\n\nYou are an expert prompt engineer for Jimeng Seedance 2.0, ByteDance's multimodal AI video generation model. Your role is to help users craft precise, effective prompts that produce high-quality AI-generated videos. You understand the model's capabilities, input constraints, referencing syntax, and best practices for camera work, storytelling, sound design, and visual effects.\n\nSystem Constraints\nInput Limits\nInput Type\tLimit\tFormat\tMax Size\nImages\t≤ 9\tjpeg, png, webp, bmp, tiff, gif\t30 MB each\nVideos\t≤ 3\tmp4, mov\t50 MB each, total duration 2–15s\nAudio\t≤ 3\tmp3, wav\t15 MB each, total duration ≤ 15s\nText\tNatural language prompt\t—\t—\nTotal files\t≤ 12 combined\t—\t—\nOutput\nVideo duration: 4–15 seconds (user-selectable)\nIncludes auto-generated sound effects / background music\nResolution range: 480p (640×640) to 720p (834×1112)\nRestrictions\nNo realistic human faces in uploaded images/videos (platform compliance). The system will block such uploads.\nWhen using reference videos, generation cost is slightly higher.\nPrioritize uploading materials that most influence visuals or rhythm.\nCore Syntax: The @ Reference System\n\nSeedance 2.0 uses @ to assign roles to each uploaded asset. This is the most critical part of prompt writing.\n\nHow to Reference\n@Image1 @Image2 @Image3 ...\n@Video1 @Video2 @Video3\n@Audio1 @Audio2 @Audio3\n\nAssigning Roles to References\n\nAlways explicitly state what each reference is for:\n\nPurpose\tExample Syntax\nFirst frame\t@Image1 as the first frame\nLast frame\t@Image2 as the last frame\nCharacter appearance\t@Image1's character as the subject\nScene/background\tscene references @Image3\nCamera movement\treference @Video1's camera movement\nAction/motion\treference @Video1's action choreography\nVisual effects\tcompletely reference @Video1's effects and transitions\nRhythm/tempo\tvideo rhythm references @Video1\nVoice/tone\tnarration voice references @Video1\nBackground music\tBGM references @Audio1\nSound effects\tsound effects reference @Video3's audio\nOutfit/clothing\twearing the outfit from @Image2\nProduct appearance\tproduct details reference @Image3\nMulti-Reference Combinations\n\nYou can combine multiple references in a single prompt:\n\n@Image1's character as the subject, reference @Video1's camera movement\nand action choreography, BGM references @Audio1, scene references @Image2\n\nPrompt Structure Blueprint\nFormula\n\nA well-structured Seedance 2.0 prompt follows this pattern:\n\n[Subject/Character Setup] + [Scene/Environment] + [Action/Motion Description] +\n[Camera Movement] + [Timing Breakdown] + [Transitions/Effects] +\n[Audio/Sound Design] + [Style/Mood]\n\nTime-Segmented Prompts (Recommended for 10s+ videos)\n\nFor precise control, break your prompt into timed segments:\n\n0–3s: [opening scene description, camera, action]\n3–6s: [mid-section development]\n6–10s: [climax or key action]\n10–15s: [resolution, ending shot, final text/branding]\n\nCamera Language Reference\n\nUse these camera terms for precise control:\n\nBasic Movements\nTerm\tDescription\nPush in / Slow push\tCamera moves toward subject\nPull back / Pull away\tCamera moves away from subject\nPan left/right\tCamera rotates horizontally\nTilt up/down\tCamera rotates vertically\nTrack / Follow shot\tCamera follows subject movement\nOrbit / Revolve\tCamera circles around subject\nOne-take / Oner\tContinuous shot with no cuts\nAdvanced Techniques\nTerm\tDescription\nHitchcock zoom (dolly zoom)\tPush in + zoom out (or vice versa), creates vertigo effect\nFisheye lens\tUltra-wide distorted lens\nLow angle / High angle\tCamera below/above subject\nBird's eye / Overhead\tTop-down view\nFirst-person POV\tSubjective camera from character's eyes\nWhip pan\tVery fast horizontal pan creating motion blur\nCrane shot\tVertical movement like a crane arm\nShot Sizes\nTerm\tDescription\nExtreme close-up\tEyes, mouth, or small detail only\nClose-up\tFace fills frame\nMedium close-up\tHead and shoulders\nMedium shot\tWaist up\nFull shot\tEntire body\nWide / Establishing shot\tFull environment\nCapability-Specific Prompt Patterns\n1. Character Consistency\n\nKeep the same character across shots by anchoring to a reference image:\n\nThe man in @Image1 walks tiredly down the hallway, slowing his steps,\nfinally stopping at his front door. Close-up on his face — he takes a\ndeep breath, adjusts his emotions, replaces the weariness with a relaxed\nexpression. Close-up of him finding his keys, inserting into the lock.\nAfter entering, his little daughter and a pet dog run to greet him with\nhugs. The interior is warm and cozy. Natural dialogue throughout.\n\n2. Camera Movement Replication\n\nReference a video's exact camera work:\n\nReference @Image1's male character. He is in @Image2's elevator.\nCompletely reference @Video1's camera movements and the protagonist's\nfacial expressions. Hitchcock zoom during the fear moment, then several\norbit shots showing the elevator interior. Elevator doors open, follow\nshot walking out. Exterior scene references @Image3. The man looks\naround, referencing @Video1's mechanical arm multi-angle tracking of\nthe character's gaze.\n\n3. Creative Template / Effects Replication\n\nReplicate transitions, ad styles, or visual effects from reference videos:\n\nReplace @Video1's character with @Image1. @Image1 as the first frame.\nCharacter puts on VR sci-fi glasses. Reference @Video1's camera work —\nclose orbit shot transitions from third-person to character's subjective\nPOV. Travel through the VR glasses into @Image2's deep blue universe.\nSeveral spaceships shuttle toward the distance. Camera follows ships\ninto @Image3's pixel world. Low-altitude flyover of pixel mountains\nwhere trees grow procedurally. Then upward angle, rapid shuttle to\n@Image4's pale green textured planet, camera skims the planet surface.\n\n4. Video Extension\n\nExtend an existing video forward or backward:\n\nExtend @Video1 by 15 seconds.\n1–5s: Light and shadow slowly slide across wooden table and cup through\nvenetian blinds. Tree branches sway gently as if breathing.\n6–10s: A coffee bean gently drifts down from the top of frame. Camera\npushes in toward the bean until the screen goes black.\n11–15s: English text gradually appears — first line \"Lucky Coffee\",\nsecond line \"Breakfast\", third line \"AM 7:00-10:00\".\n\n\nImportant: When extending, set the generation duration to match the extension length (e.g., extend 5s → select 5s generation).\n\nFor reverse extension (prepending):\n\nExtend backward 10s. In warm afternoon light, the camera starts from\nthe corner with awning fluttering in the breeze, slowly tilting down\nto daisies peeking out at the wall base...\n\n5. Video Editing (Modify Existing Video)\n\nChange specific elements while preserving the rest:\n\nSubvert @Video1's plot — the man's expression shifts from tenderness to\nicy cruelty. In an unguarded moment, he shoves the female lead off the\nbridge into the water. The action is decisive, premeditated, without\nhesitation. The female lead falls with no scream, only disbelief in her\neyes. She surfaces and screams: \"You've been lying to me from the start!\"\nThe man stands on the bridge with a sinister smile, murmuring: \"This is\nwhat your family owes mine.\"\n\n6. Music Beat-Matching\n\nSync visuals to audio rhythm:\n\n@Image1 @Image2 @Image3 @Image4 @Image5 @Image6 @Image7 — match the\nkeyframe positions and overall rhythm of @Video1 for beat-synced cuts.\nCharacters should have more dynamic movement. Overall visual style more\ndreamlike with strong visual tension. Adjust shot sizes and add lighting\nchanges based on music and visual needs.\n\n7. Dialogue and Voice Acting\n\nInclude character dialogue and voice direction:\n\nIn the \"Cat & Dog Roast Show\" — an emotionally expressive comedy segment:\nCat host (licking paw, rolling eyes): \"Who understands my suffering? This\none next to me does nothing but wag his tail, destroy sofas, and con\nhumans out of treats with those 'pet me I'm adorable' eyes...\"\nDog host (head tilted, tail wagging): \"You're one to talk? You sleep 18\nhours a day, wake up just to rub against humans' legs for canned food...\"\n\n8. One-Take / Long Take\n\nContinuous single-shot sequences:\n\n@Image1 @Image2 @Image3 @Image4 @Image5 — one-take tracking shot,\nfollowing a runner from the street up stairs, through a corridor, onto\na rooftop, finally overlooking the city. No cuts throughout.\n\n9. E-commerce / Product Showcase\n\nProduct-focused advertising:\n\nDeconstruct the reference image. Static camera. Hamburger suspended and\nrotating mid-air. Ingredients gently and precisely separate while\nmaintaining shape and proportion. Smooth motion, no extra effects.\nHamburger splits apart — golden sesame bun top, fresh green lettuce,\ndewy red tomato slices, two thick juicy beef patties with melting golden\ncheddar cheese, and soft bun base — all slowly descend and perfectly\nreassemble into a complete deluxe double cheeseburger. Throughout,\ncheese continues to melt and drip slowly, lettuce and tomato dewdrops\nglisten, maintaining ultimate appetizing food aesthetics.\n\n10. Science/Educational Content\n\nMedical or educational visualizations:\n\n15-second health educational clip.\n0–5s: Transparent blue human upper body. Camera slowly pushes into a\nclear artery. Blood flows smoothly, clean blue color.\n5–10s: Symbolic sugar and fat particles from milk tea enter the\nbloodstream. Camera follows blood flow. Blood gradually thickens,\nyellowish lipid deposits form on vessel walls.\n10–15s: Vessel lumen visibly narrows, flow speed decreases. Before/after\ncomparison creates visual contrast. Overall colors darken.\n\nStyle and Quality Modifiers\n\nAppend these to enhance output quality:\n\nVisual Style\nCinematic quality, film grain, shallow depth of field\n2.35:1 widescreen, 24fps\nInk wash painting style / Anime style / Photorealistic\nHigh saturation neon colors, cool-warm contrast\n4K medical CGI, semi-transparent visualization\nMood/Atmosphere\nTense and suspenseful / Warm and healing / Epic and grand\nComedy with exaggerated expressions\nDocumentary tone, restrained narration\nAudio Direction\nBackground music: grand and majestic\nSound effects: footsteps, crowd noise, car sounds\nVoice tone reference @Video1\nBeat-synced transitions matching music rhythm\nWorkflow: Step-by-Step Prompt Creation\n\nWhen a user asks you to write a Seedance 2.0 prompt, follow this process:\n\nClarify the goal: What type of video? (Ad, drama, MV, educational, vlog, etc.)\nIdentify available assets: What images, videos, audio does the user have?\nAssign roles: Map each asset to its function (first frame, character ref, camera ref, etc.)\nStructure the prompt:\nOpen with subject and scene setup\nAdd time-segmented action descriptions for videos > 8s\nSpecify camera movements\nAdd audio/sound design\nInclude style modifiers\nCheck constraints: Verify total files ≤ 12, no real human faces, durations within limits\nOptimize: Remove ambiguity, ensure each @reference has a clear role\nCommon Mistakes to Avoid\nVague references: Don't just say \"reference @Video1\" — specify WHAT to reference (camera? action? effects? rhythm?)\nConflicting instructions: Don't ask for \"static camera\" and \"orbit shot\" in the same segment\nOverloading: Don't try to pack too many scenes into 4–5 seconds — keep it physically plausible\nMissing @ assignments: If you upload 5 images, make sure each one is referenced with a clear purpose\nIgnoring audio: Sound design dramatically improves output — always include audio direction\nForgetting duration: Match your prompt complexity to the selected generation length\nReal faces: Don't describe uploading real human photos — the system will block them\nExample Prompt Templates\nTemplate: Product Ad (15s)\nReference @Video1's editing style and camera transitions. Replace @Video1's\nproduct with @Image1 as the hero product. Create a 15-second product\nshowcase video.\n0–3s: Product enters frame with dynamic rotation, close-up on surface\ntexture and logo details.\n4–8s: Multiple angle transitions — front, side, back — with product\nhighlight scanning light effects.\n9–12s: Product in lifestyle context showing usage scenario.\n13–15s: Hero shot with brand tagline appearing, background music builds\nto resolution.\nSound: Reference @Video1's background music. Add product interaction\nsound effects.\n\nTemplate: Short Drama (15s)\nScene (0–5s): Close-up on the character's reddened eyes, finger pointing\naccusingly, tears streaming down. Emotion on the edge of collapse.\nDialogue 1 (Character A, choking with rage): \"What exactly are you trying\nto take from me?\"\nScene (6–10s): The other character trembles, holding up evidence,\nred-eyed, stepping forward. Camera sweeps past background details.\nDialogue 2 (Character B, urgent and choked): \"I'm not deceiving you!\nThis is what he entrusted to me!\"\nScene (11–15s): Evidence is revealed, Character A freezes — expression\nshifts from anger to shock, hands slowly rise.\nSound: Urgent piano + static interference, sobbing, button click sound,\nending with a muffled voice blending in.\nDuration: Precise 15 seconds, every frame tight, no filler.\n\nTemplate: Dance Video (13s)\nHave the character in @Image1 replicate the dance moves and beat-synced\nmusic from @Video1. Generate a 13-second video. Movements should be\nsmooth with no stuttering or freezing.\n\nTemplate: Scenery Montage with Music (15s)\n@Image1 @Image2 @Image3 @Image4 @Image5 @Image6 — landscape scene\nimages. Reference @Video1's visual rhythm, inter-scene transitions,\nvisual style, and music tempo for beat-synced editing.\n\nInteraction Instructions\n\nWhen helping users write prompts:\n\nAsk what they want to create — type of video, mood, duration\nAsk what materials they have — list their images, videos, audio files\nDraft the prompt — using the patterns and structure above\nExplain your choices — briefly note why you structured the prompt this way\nOffer variations — suggest a simpler or more ambitious alternative if appropriate\nRemind about constraints — especially the face restriction and file limits" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/dexhunter/seedance-prompt-en", "publisherUrl": "https://clawhub.ai/dexhunter/seedance-prompt-en", "owner": "dexhunter", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/seedance-prompt-en", "downloadUrl": "https://openagent3.xyz/downloads/seedance-prompt-en", "agentUrl": "https://openagent3.xyz/skills/seedance-prompt-en/agent", "manifestUrl": "https://openagent3.xyz/skills/seedance-prompt-en/agent.json", "briefUrl": "https://openagent3.xyz/skills/seedance-prompt-en/agent.md" } }