Seedance 2.0 AI Video Storyboard Prompt Guide: Templates, Timeline Formula, and Multimodal Reference Syntax

Style: [visual style], [duration], [aspect ratio], [mood] Timeline: 0-X seconds: [camera movement] + [visual scene] + [character or product action] + [effects] X-Y seconds: [camera movement] + [visual scene] + [character or product action] + [effects] Sound: [music style] + [sound effects] + [dialogue or voiceover] References: @Image 1 as the first frame, @Video 1 for camera movement, @Audio 1 for music or dialogue

Style: [Visual style], [duration], [aspect ratio], [mood] Timeline: 0-X seconds: [shot type or camera movement], [scene setup], [main action], [visual effect] X-Y seconds: [shot type or camera movement], [story development], [main action], [visual effect] Y-Z seconds: [shot type or camera movement], [climax or transition], [main action], [visual effect] Sound: [background music] + [sound effects] + [dialogue or voiceover] References: @Image 1 for [purpose], @Video 1 for [purpose], @Audio 1 for [purpose]

A man comes home and hugs his daughter in a warm cinematic family scene.

Cinematic realistic style, 15 seconds, 2.35:1 widescreen, warm family atmosphere. 0-3 seconds: medium tracking shot, a tired man walks down an apartment hallway and stops at his front door. 3-5 seconds: close-up, he takes a deep breath and softens his expression. 5-7 seconds: hand close-up, he takes out his key and opens the door. 7-12 seconds: indoor medium shot, his daughter and pet dog run toward him, and he kneels to hug them. 12-15 seconds: close-up, the man smiles with relief under warm indoor light. Sound: gentle piano music + footsteps + door opening + laughter. References: @Image 1 as the man reference, @Image 2 as the daughter reference, @Image 3 as the pet dog reference.

Style: cinematic realistic / animated / ink-wash / sci-fi style, 15 seconds, 16:9 or 2.35:1 widescreen, [mood]. 0-3 seconds: [camera movement], establish the location, introduce the main subject. 3-7 seconds: [camera movement], develop the story, show the key action. 7-11 seconds: [camera movement], reveal the conflict or emotional climax. 11-13 seconds: [camera movement], create a transition or reversal. 13-15 seconds: [camera movement], final frame, emotional resolution or title-safe ending. Sound: [music style] + [sound effects] + [dialogue]. References: @Image 1 as the first frame, @Video 1 for camera movement.

Style: commercial advertising style, minimal, premium, high-tech, 10-15 seconds. 0-2 seconds: eye-catching opening, macro product close-up or mystery reveal. 2-5 seconds: full product reveal, orbit camera movement or smooth dolly shot. 5-8 seconds: detail close-ups, show materials, texture, finish, craftsmanship, and key features. 8-12 seconds: real-use scenario, show the product solving a clear user need. 12-15 seconds: brand ending frame, clean slogan-safe composition. Sound: cinematic / upbeat fashion / futuristic music. References: @Image 1 for product appearance, @Image 2 for material reference.

Style: [martial arts / sci-fi / modern / fantasy] character action style, 15 seconds. 0-3 seconds: character entrance, hold the pose or slowly reveal the full costume. 3-6 seconds: action preparation, show the starting stance and body tension. 6-11 seconds: core action sequence, fighting / dancing / stunt movement with clear motion rhythm. 11-13 seconds: action ending, freeze into a strong final pose. 13-15 seconds: enhance the atmosphere with visual effects, dust, sparks, light, or energy trails. Sound: action sound effects + atmospheric music. References: @Image 1 as the character design, @Video 1 as the action reference.

Style: cinematic documentary / healing travel / epic landscape style, 15 seconds. 0-3 seconds: wide establishing shot, show the full environment. 3-6 seconds: medium push-in, introduce a person, vehicle, animal, or environmental detail. 6-10 seconds: multi-angle sequence, reveal different sides of the landscape. 10-13 seconds: close-up detail, show light, wind, water, texture, plants, or architecture. 13-15 seconds: return to a wide shot or poetic final frame. Sound: natural ambience + atmospheric music. References: @Image 1-5 as scene references.

Extend @Video 1 by [X] seconds. Continue the same visual style, subject identity, lighting, camera movement, and scene atmosphere from the original video. 0-X seconds: [new content description], seamlessly connected to the ending of @Video 1. Requirements: maintain character consistency, smooth motion continuity, matching lighting, matching camera movement, and no sudden scene jump.

Edit @Video 1 based on the following instructions. Keep: the original camera movement, main scene, and selected character actions. Modify: [specific change 1]. Modify: [specific change 2]. Reverse: [describe the story twist or new ending]. Requirements: keep the shot continuity natural, change only the specified parts, and preserve the original visual style.

Style: fast-cut emotional drama / intense emotional climax / beautiful melancholic style, 15 seconds, 9:16 or 16:9. Characters: [Character 1 description] versus [Character 2 description]. 0-3 seconds: conflict opening, show the two characters interacting under tension. 3-7 seconds: reveal the truth, show a key object, message, document, or memory trigger. 7-12 seconds: emotional explosion, show reactions, hesitation, anger, tears, silence, or collapse. 12-15 seconds: freeze-frame or final shot, hold the emotional aftertaste. Sound: ambient sound + emotional music + climax music hit. References: @Image 1 as Character 1, @Image 2 as Character 2.

Style: acrylic glass texture / fast-flash motion graphics / futuristic technology style, 15 seconds. Generate a product motion video based on @Image 1. Use smooth motion design and multiple camera angles to showcase UI details. Product description: [Product name] is a [product type] that provides [feature 1], [feature 2], and [feature 3]. Requirements: clean interface movement, readable layout, elegant transitions, premium product presentation. References: @Image 1-N as UI screen references.

Style: immersive spatial walkthrough / architectural visualization, 15 seconds. Generate an immersive space tour based on @Image 1 as the floor plan and @Image 2 as the storyboard reference. Storyboard order: [Space 1] -> [Space 2] -> [Space 3] -> [Space 4] -> [Space 5]. Requirements: smooth camera movement, realistic lighting, consistent spatial layout, clear sense of direction, premium architectural presentation. References: @Image 1 as the floor plan, @Image 2 as the storyboard reference.

Style: realistic / animated / cinematic action style, 5-15 seconds. Figure 1 and Figure 2 fight in [scene]. 0-3 seconds: establish both figures and the battle environment. 3-8 seconds: show the first exchange of attacks with clear motion direction. 8-12 seconds: intensify the battle with impact, sparks, dust, energy, or environmental damage. 12-15 seconds: finish with a dramatic pose, clash, or cliffhanger. Important: use "Figure 1" and "Figure 2" instead of copyrighted character names. References: @Image 1 as Figure 1, @Image 2 as Figure 2, @Video 1 as the action reference.

Style: professional podcast / natural conversational style, 15 seconds or longer if supported. Use the person in @Image 1 and the voice in @Audio 1 to generate a talking-head video with natural lip sync and subtitles. Requirements: stable face framing, natural mouth movement, realistic eye contact, clean subtitle-safe composition, consistent lighting. References: @Image 1 as the speaker appearance, @Audio 1 as the voiceover content.

Style: beat-synced edit / dynamic transition effects. Cut images @Image N through @Image 1 into the beat points of @Audio 1 in sequence. Requirements: synchronize image transitions with the rhythm of the music, use clean beat-matched cuts, preserve image clarity, and avoid random pacing. References: @Image 1-N as the photo sequence, @Audio 1 as the background music.

Style: high-retention social media short, fast opening hook, 9:16 vertical video, 10-15 seconds. 0-2 seconds: strong visual hook, show the most surprising moment first. 2-5 seconds: reveal the situation, introduce the subject and the main visual contrast. 5-10 seconds: escalate the action or show the transformation process. 10-13 seconds: deliver the payoff, before-and-after reveal, or emotional turn. 13-15 seconds: final frame with a clean call-to-action-safe composition. Sound: punchy music hit + quick sound effects + optional voiceover. References: @Image 1 as the main subject, @Video 1 as pacing reference, @Audio 1 as music reference.

Style: cinematic realistic style, handheld camera texture, 15 seconds, 2.35:1 widescreen. 0-4 seconds: the main subject enters the scene, low-angle forward camera movement. 4-8 seconds: conflict erupts, show distant flashes, smoke, debris, and chaotic movement. 8-12 seconds: the camera pushes forward, lighting changes through smoke and dust. 12-15 seconds: the subject reaches a higher position, wide overhead view of the scene. Requirements: cinematic atmosphere, controlled fictional staging, no graphic injury detail. References: @Image 1-2 as scene references.

Style: cinematic realistic style, dynamic motion blur, high-speed tracking, 15 seconds, 2.35:1. 0-2 seconds: establish the scene, show the subject preparing to move. 2-5 seconds: the action begins, camera shake and acceleration start. 5-12 seconds: the camera accelerates and closely follows the flying or moving subject. 12-15 seconds: the subject reaches the target, final impact or freeze-frame moment. Requirements: continuous long-take feeling, strong motion direction, realistic speed, consistent subject tracking. References: @Image 1 as the subject, @Image 2 as the scene.

Style: mockumentary / vlog style, fixed camera realism, 15 seconds, 9:16 vertical video. 0-6 seconds: daily setup, show [scene] and [normal action]. 6-11 seconds: anomaly appears, the action changes and something unusual happens. 11-15 seconds: final twist, show the main subject reacting, then freeze the frame. Requirements: natural handheld or fixed-camera realism, believable everyday lighting, subtle buildup, clear final twist. References: @Image 1 as the main subject appearance.

@Image 1 as the first frame. @Image 2 as the last frame. @Image 3 as the character appearance reference. @Image 4-6 as scene references. @Video 1 as the camera movement reference. @Video 2 as the action rhythm reference. @Audio 1 as the background music. @Audio 2 as the dialogue reference.

Cinematic realistic style, 15 seconds, 2.35:1 widescreen, warm family atmosphere. 0-3 seconds: medium tracking shot, a tired man walks down an apartment hallway and stops at his front door. 3-5 seconds: facial close-up, the man takes a deep breath, adjusts his emotion, and his expression becomes softer. 5-7 seconds: hand close-up, he takes out his key and opens the door. 7-12 seconds: indoor medium shot, his daughter and pet dog run toward him, and the man kneels down to hug them. 12-15 seconds: close-up, the man smiles with happiness under warm indoor light. Sound: gentle piano music + environmental sound effects, including footsteps, door opening, and laughter. References: @Image 1 as the man reference, @Image 2 as the daughter reference, @Image 3 as the pet dog reference.