Seedance 2.5 Prompt Guide

The examples in this guide illustrate prompt-writing techniques only.

“Copied from official Bytedance guide https://bytedance.larkoffice.com/docx/A88jd0B47oAd8zxWp5ycZFMfnxh”

Dreamina Seedance 2.5 supports both text-only video generation and creation with image, video, and audio references. It can also edit existing videos. Start by stating what you want to generate, then add reference materials, event progression, visual treatment, and audio as needed.

1. Basic Prompting Techniques

1.1 The Core Prompt Formula

Prompts can flexibly combine the following elements:

Subject + Action or Event + Scene and Environment (Optional) + Visual Style (Optional) + Camera Movement/Cut (Optional) + Audio (Optional)

  • Subject + Action or Event: State who or what is doing what. This is the foundation of the video.
  • Scene and Environment: Describe the location, time, weather, spatial relationships, and background state.
  • Visual Style: Describe lighting, color, materials, image texture, or the overall mood.
  • Camera Movement/Cut: Describe shot size, camera angle, camera movement, the focus subject, and shot transitions.
  • Audio: Describe dialogue, voice characteristics, ambience, sound effects, and music.

Basic Template

Example

You may omit any components you do not need. Generation parameters do not need to be included in the prompt; configurable parameters are set on the generation page or through the API.

1.2 When Using Reference Materials, Prepare Them and Define Their Roles

Material Quantity and Selection

Seedance 2.5 can combine up to 50 reference materials. Each material type follows the input limits below. The recommended ranges are intended to improve generation stability; they are not capability limits.

Material Quantity and Selection

Material Type

Input Limit

Recommended Range

Images

Up to 30 images, each no larger than 4K

Prefer 1-8 distinct subjects across subject-reference images

Videos

Up to 10 videos, with a combined duration of no more than 30 seconds

Prefer 1-5 distinct subjects and 5-10 seconds per subject video

Audio

Up to 10 audio clips, with a combined duration of no more than 30 seconds

Keep only dialogue, voice characteristics, ambience, or music directly relevant to the task

Video Editing

A source video may be used together with reference images

Prefer a source video under 20 seconds and 1-5 reference images

You may still try ranges above these recommendations: 9-12 subjects in subject images, 6-10 subjects in subject audio/video, or 6-8 reference images for video editing. Stability may decrease as the number of materials grows. If more than five subjects also require multiple views, place different views in separate images; independent view images are usually more stable than combining several views into one collage.

Define Each Material's Role

After uploading reference materials, specify exactly what each one contributes. Add exclusions when people, backgrounds, or compositions in a material could be unintentionally carried into the output. Material mappings must be written in the prompt: do not rely only on text labels inside images, and do not make the model infer which person, prop, or scene each material represents.

Reference Role Template

Example

If several images show different views of the same person or product, state this explicitly:

When a reference video already defines the motion, camera movement, and sequence accurately, state only which attributes to inherit; there is no need to restate every action. Repeating the motion description may conflict with the reference itself. A blockout video mainly provides motion and spatial structure, so the prompt must still define the intended subjects, scene, action, and visual style.

1.3 Special Syntax for Audio and Text

Prompts can be written entirely in natural language. When you need to distinguish music, sound effects, dialogue, and subtitles more explicitly, use the following syntax:

1.3 Special Syntax for Audio and Text

Content

Syntax

Example

Music

()

(Soft, rhythmic piano music plays in the background)

Sound Effects

<>

<A bell rings in the distance>

Dialogue

{}

{Hello, welcome back.}

Subtitles

【】

【Chapter One: Departure】

Dialogue Language Reinforcement

When dialogue is not in Chinese, specify the language before the line:

If the dialogue text is in English but the model speaks it in Chinese, or if you need a specific regional variety, reinforce the language before the line. Use this formula:

Dialogue Language + Regional Variety or Accent + Delivery Style + Speaker + {Dialogue}

2. New Capabilities in Dreamina Seedance 2.5

2.1 Multi-Reference Creation: Tell the Model Which Materials to Use in Each Scene

Seedance 2.5 supports up to 50 reference materials. When many materials are provided, the goal is not to put every reference into one sentence, but to define the relationships among characters, props, scenes, actions, and audio.

Use the following order:

Define Each Material's Role → Map Subjects → Group by Type → Create Subject Profiles → Select References by Scene

Step 1: Name and Map Each Subject Individually

Bind each person, product, and prop to its reference material separately:

Do not write, "@Images 1 through 4 define four characters respectively." That wording does not state which image corresponds to which character.

Step 2: Group Materials by Type

Step 3: Create a Centralized Profile for Important Subjects

When the same character uses several references across multiple scenes, add a subject profile:

Step 4: Select References by Scene

The goal of multi-reference creation is to help the model select the correct materials for the current scene, not to make every material appear at the same time.

2.2 30-Second Videos: Organize Events with Stages and End States

When a video contains several events, divide the story into consecutive stages. Give each stage only one primary state change, and state what should be directly visible at the end of that stage.

Long-Video Template

Example

Timestamps and Pacing Control

For ordinary narratives, use stages by default. Use one-second precision only when you need to control a critical handoff, entrance or exit, transition, or explicit beat. Use time ranges to allocate pacing, exact time points for a single key event, and relative timing to describe a delay between events.

Timestamps and Pacing Control

Pattern

Example

Time range

0-3 seconds... 3-7 seconds... 7-12 seconds...

Exact time point

At 5 seconds, the camera whip-pans rapidly to the left and completes the transition.

Relative timing

Three seconds after the character presses the button, the room lights gradually turn off.

Time ranges should be consecutive and non-overlapping. They represent an event's time budget, not a precise edit point, so actions may occur slightly before or after a boundary. Too little content in a range gives the model more freedom; too much can cause excessive cutting or omitted events. Do not use timestamps to demand frequencies such as “complete three actions in one second.”

2.3 Parameter Rules for Editing, First/Last-Frame, and Extension Tasks

Video editing, first-frame or first-and-last-frame generation, and video extension automatically lock some generation parameters based on the input materials.

2.3 Parameter Rules for Editing, First/Last-Frame, and Extension Tasks

Task Type

Aspect Ratio

Duration

Video editing

Automatically preserves the input video's aspect ratio; cannot be set separately

Automatically preserves approximately the input video's duration; cannot be set separately. Input-frame processing may introduce a difference of up to approximately 0.3 seconds

First-frame or first-and-last-frame generation

Automatically uses the first image's aspect ratio. The first and last images should use the same aspect ratio to avoid stretching the last frame

Can be set

Video extension

Automatically preserves the input video's aspect ratio; cannot be set separately

Can be set

Parameters automatically locked for these tasks cannot be specified separately on the generation page or through the API. Other parameters depend on the options currently available.

2.4 Video Editing: Define the Master Video, Edit Scope, and Content to Preserve

When editing an existing video, first define the source video as the sole editing master. Then specify the edit target, edit scope, target material, and content to preserve. The output automatically preserves the input video's aspect ratio and approximately preserves its duration; neither can be set separately. Input-frame processing may introduce a difference of up to approximately 0.3 seconds, usually because of transition-frame handling, while the overall content and event order remain substantially unchanged.

General Editing Pattern

Template

Example

Subject Replacement

Template

Example

Background Replacement

Template

Example

Audio Editing

Dialogue, language, voice, background music, and sound effects can be edited separately. State the speaker or sound category, the intended change, and which other sounds must remain unchanged.

2.5 Video Extension: Align the Boundary Frame Before Describing New Content

Video extension creates content beyond the boundary of a source video. For a forward extension after the original video, the extension's first frame should continue from the source video's last frame. For a backward extension before the original video, the extension's last frame should connect to the source video's first frame. In addition to the boundary frame, inspect whether the characters, props, background, and events in the extended segment are correct.

Forward Extension (After the Original Video)

First describe the continuous state of the source video's last frame, then describe what happens afterward.

Basic Template

Example

With Additional Reference Materials

Define the role of every additional material first, then state that the source video controls the extension boundary. New materials may supplement characters, props, or audio, but they must not override the source video's last-frame control over the extension's opening image.

Template

Example

Backward Extension (Before the Original Video)

First describe what happens before the source video begins, then define the source video's first frame as the explicit end state of the extended segment. Writing only "then connect to the source video" may introduce later characters or effects too early, or cause the image to change again after reaching the target state.

Basic Template

Example

With Additional Reference Materials

Define each material's role, and state which materials are used in the backward extension and which should appear only after the source video begins. This reduces the chance that later characters, props, or effects enter the preceding segment too early.

Template

Example

Boundary frames should connect naturally at a visual level; this does not mean they will be pixel-identical. During review, inspect both sides of the boundary and the complete extended segment.

3. Advanced Techniques

3.1 Keyframes, Storyboards, and Blockout References

First and Last Frames with Additional References

In multimodal reference mode, you can state in the first line that @Image 1 is the first frame and @Image 2 is the last frame. There is no need to switch to a separate first/last-frame mode. The system locks the output aspect ratio to the first image, while duration is set on the generation page or through the API. The first and last images should use the same aspect ratio; mismatched ratios may stretch the last frame. Additional images can still define characters, props, scenes, and materials.

Basic Template

Example

Describe each anchor image separately. Do not combine them into a sentence such as "@Images 1 and 2 are the first and last frames." The first and last images should use the same aspect ratio. Other references should supplement only their specified attributes and must not replace the first- or last-frame composition.

Multi-Keyframe Sequence Control

When separate images define different stages of a process, begin with “Use @Image 1 through @Image N as keyframes in this order,” then describe the key state represented by each image. Independent keyframe images are usually easier to align than several frames combined into one grid. They control stage order and key states; they do not reproduce every frame exactly.

Basic Template

Example

Storyboard Grids

A storyboard grid communicates the overall story, shot order, and approximate compositions. It is not intended for strict reproduction of every detail in every panel. Prefer no more than 15 panels, use clean line art or simple diagrams, and minimize text labels. State the reading order, then describe each panel's subject action, shot size or camera movement, final visual style, and audio.

Basic Template

Example

Blockout References and Rendering

Blockout references fall into two categories. Coarse blockouts mainly provide temporal information such as action, paths, blocking, camera movement, cuts, lighting, and sound. Fine blockouts already contain complete structures and are mainly used for re-rendering materials, colors, characters, scenes, and visual style. First determine whether the blockout controls a motion skeleton or a complete model, then use the corresponding prompt structure.

Blockout References and Rendering

Type

Best For

Material Requirements

Prompt Focus

Coarse blockout

Simple geometry that previews action, paths, blocking, camera movement, or cuts

Clear relationships between shapes and a complete action sequence; character, prop, and scene images may be added

Map every blockout subject and state which temporal and spatial information to inherit

Fine blockout

Complete modeling that needs new characters, materials, colors, scenes, or style

Complete, clean model; avoid path lines, coordinate axes, and camera frustums

Preserve structure, action, and camera treatment while defining the attributes to re-render

Coarse Blockouts

Use a coarse blockout to lock action paths, motion direction, blocking, entrances and exits, camera paths, cut points, lighting changes, and sound rhythm. Map each geometric object separately to its final subject or prop. Additional images can define the appearance of characters, props, and scenes.

Coarse Blockouts

Blockout Information

What to State in the Prompt

Path

Action trajectory, motion direction, subject blocking, and entrance/exit order

Camera movement

Camera position, path, direction, and speed changes

Lighting

Light direction, brightness changes, and when those changes occur

Cuts

Cut positions and the subject/composition before and after each cut

Audio

Whether to inherit dialogue, music, ambience, or action sound effects

Prefer simple geometry with clear relationships. Arms, wings, and other appendages should be used only when the action sequence is complete; otherwise they may cause stiff motion or structural misinterpretation.

Basic Template

Example

Fine Blockouts

A fine blockout already contains complete character, prop, or scene structures. Use it to change materials, colors, character appearance, scene, or overall visual style. Keep the blockout clean: remove path lines, coordinate axes, controllers, camera frustums, and other production markers.

Basic Template

Example

3.2 One-Click Video

One-click video is designed to organize multiple images, or images plus a style-reference video, into a complete video with consistent pacing and visual packaging. State each material's role, image order, amount of motion, editing rhythm, visual treatment, and audio. Do not write only “turn these materials into a video.”

Material Roles → Image Order → Motion Amount → Editing Style → Visual Treatment → Audio

Basic Template

Example

If image order matters, state the exact sequence. If the model may arrange the materials freely, say that it may organize them by theme. When several characters or products appear, continue to name and bind each one separately.

3.3 Seamless Video Transitions

A seamless video transition generates continuous bridge content between two videos. First identify the before-transition and after-transition videos, then describe the trigger action, camera movement, visual transformation, arrival state, and audio transition.

Before Video → After Video → Trigger Action → Camera Movement → Visual Transformation → Arrival State → Audio

3.3 Seamless Video Transitions

Transition Method

What to Specify

Dive or reverse movement

Camera direction, speed change, and when the next scene begins

Character rotation

Pose, rotation direction, and how clothing or background changes continuously

Foreground occlusion

When the foreground object fills the frame and the composition that follows

Object morph

Corresponding shapes, materials, and the transformation process

Push/pull or focus change

Camera movement, focus target, and continuous spatial relationship

Basic Template

Example

The goal of a seamless transition is visual and audio continuity. A prompt may ask to preserve the primary content of both source videos, but a generated bridge is not a pixel-identical edit splice.

3.4 Emotional Direction and Observable Performance

Emotion words such as "tense," "warm," or "oppressive" communicate an overall direction, but they leave more room for interpretation in the performance. For more stable control of acting, add directly visible or audible cues such as eye movement, brow tension, mouth movement, breathing, gaze direction, and hand movement.

You do not need to list every facial detail. For a single emotional transition, two to four clear cues are usually enough. Use event-triggered stages only when the emotion changes several times.

Single Emotional Transition: Default Structure

Multi-Stage Emotion: Progress Through Triggering Events

Example

3.5 Professional Cinematography Terms

Basic camera language and popular camera techniques can be written directly in the prompt. When a term is uncommon, may have several interpretations, or requires precise control, also state which subject it applies to, how the image changes, and the intended visible result.

Basic Camera Language

Basic Camera Language

Type

Common Supported Terms

Shot size

extreme wide shot, wide shot, medium shot, close-up, extreme close-up

Camera movement

push in, pull out, pan, lateral move, follow shot, orbit, dive, dolly out, tilt up, handheld shake

Camera position and viewpoint

low angle, overhead view, first-person view

The following popular camera techniques can be used directly. If the frame contains several subjects, still state which subject the camera follows or revolves around, where the movement begins, and where it ends.

Popular Camera Techniques

Technique

What to Specify

One-take shot

The subjects, spaces, and events the continuous camera passes through in order

Dolly zoom

The subject size to preserve and whether the background appears to move closer or farther away

Aerial view

Viewing height, movement direction, and the environmental area to reveal

FPV

First-person flight or traversal path, speed, and turns

Bullet time

The action to freeze or slow down and the camera's orbit direction

Handheld camera

The subject being followed and the amount of shake

Bounce speed ramp

Where the action accelerates, decelerates, or rebounds, and its final resting state

Uncommon Cinematography Terms

For a niche term, a term with inconsistent industry usage, or a term the model may not recognize, keep the term itself and translate it into a directly observable visual change.

Cinematography Term + Target Subject + Visual Change + Foreground/Background Relationship + Direction or Speed

For a precise transition, also state the trigger time, occluding object, camera direction, transition method, and the composition or motion trend that should continue afterward.

Cinematography Examples

Aperture, focal length, and shutter values can be included, but the intended visible result is usually clearer than a numeric value alone.

4. Pre-Submission Checklist

  • Does the prompt clearly state the subject and primary action or event?
  • Does every reference material state what to use and what not to use?
  • Is every distinct character, product, and prop named and bound to a reference?
  • Are references selected by scene instead of being required to appear all at once?
  • Does each stage of a long video contain only one primary change and a clear end state?
  • Do the number of characters, clothing, prop ownership, and spatial relationships remain consistent?
  • For video editing, does the prompt define the sole editing master, edit scope, target quantity, and content to preserve?
  • Are abstract emotions and cinematography terms paired with directly visible or audible cues?
  • Are first/last frames and multiple keyframes assigned one role per image, and do the first and last images use the same aspect ratio?
  • Does the storyboard state which structure to inherit? For blockouts, did you first identify whether the reference is coarse or fine and specify the temporal, structural, material, and style information to inherit?
  • Do video editing, first/last-frame generation, and video extension follow their automatically locked aspect-ratio and duration rules?
  • For video extension, did you check the boundary image, motion trend, and audio continuity?
  • For one-click video, does the prompt define material roles, image order, motion amount, editing style, and audio?
  • For seamless transitions, does the prompt define the two videos' roles, trigger action, transition process, and arrival state?

5. Usage Limitations

  • Timestamps allocate time to events; they are not frame-accurate edit points.
  • Video-editing prompts can improve the probability that critical events align with the source video, but they cannot guarantee frame-by-frame overlap.
  • The goal of multi-reference creation is to select and combine the correct materials, not to make every material appear at the same time.
  • For subtitles, formulas, signs, product specifications, or frame-level timing that must be completely accurate, use prepared reference materials, video generation, and post-production together.
  • Video editing automatically locks the input video's aspect ratio and approximate duration; neither can be set separately. The output may differ from the input by up to approximately 0.3 seconds.
  • First-frame or first-and-last-frame generation locks the aspect ratio to the first image, while duration can be set. Mismatched first/last image ratios may stretch the last frame.
  • Video extension locks the input video's aspect ratio, while extension duration can be set. The extended segment's volume may differ slightly from the source video.
  • For one-click video, if image order or character mapping matters, specify it explicitly in the prompt.
  • Seamless video transitions aim for visual and audio continuity; they do not guarantee pixel-identical preservation of both source videos.

6. Guide Disclaimer

The examples in this guide illustrate prompt-writing techniques only. Actual generation results may vary depending on the input materials, task complexity, and generation parameters.