ByteDance's Seedance 2.5 prompt guide: Copy-ready templates for videos up to 30 seconds

How to assign roles across 50 assets, structure a 30-second video, or change just one part of an existing clip—the official guide turns every task into a reusable template.

By 字节跳动官方提示词指南08-02 · 14 min read⚑ Tutorial / how-to
Tool guide · XiaoHu explains
One-minute overview
  • ByteDance has published its own guide to writing Seedance 2.5 prompts. It covers one-line generation, asset orchestration, long-form sequencing, video editing, and extension—with official templates and every example collected on this page for easy copying.
  • The guide follows one rule: Do not make the model guess. Learn its three recurring patterns, and you understand half the system.
  • It also spells out what the model cannot do. For several types of content, ByteDance itself says not to expect a perfect first-pass result.
⚑ This article is based on ByteDance's official Seedance 2.5 Prompt Guide, published as a bilingual Lark document. Templates and examples are reproduced from the original, while several checklist items have been condensed. ByteDance notes that the examples demonstrate prompt structure only; actual results depend on the input assets, task complexity, and generation settings.
Background

What Seedance 2.5 is

Just two days after releasing Seedance 2.5, ByteDance published an official prompt guide covering everything from one-line generation to orchestrating 50 reference assets, structuring a 30-second video, and changing a single part of an existing clip. Every task comes with a template you can copy directly. For anyone creating videos with Jimeng AI or the API, this is the first comprehensive official guide to the new features. Until now, users had to piece together techniques from community posts.

Here is the quick primer. Seedance 2.5 is a video creation model released by ByteDance's Seed team on July 31. It doubles the maximum length of a single generated video from 15 seconds to 30 seconds, raises the number of reference assets that can be combined in one job from 15 to 50, and adds editing and extension for existing videos. It became available in Jimeng AI and Doubao Pro on launch day. Those expanded capabilities demand a different kind of prompt: Assets need numbered roles, and longer videos need scene-by-scene structure. That is exactly what this guide addresses.

ByteDance highlights four major advances over 2.0:

01A wider narrative canvas: Native 30-second videos and high-fidelity temporal extension
  • The maximum duration of a single clip rises to 30 seconds, allowing more coherent shot construction, emotional development, and narrative progression without stitching clips together in post-production.
  • High-fidelity temporal extension can naturally expand short footage while preserving characters, scenes, and camera continuity. This speeds up production and improves quality, especially for narrative-heavy work such as TV commercials, short dramas, and brand films.
02Expanded omni-modal referencing: Upload up to 50 omni-modal reference assets
  • A single job can accept up to 50 omni-modal reference assets in any mix of images, video, and audio. Creators can provide a full cast, location set, reference shots, and brand music at once, allowing the model to interpret them together and produce a result closer to the intended concept.
  • Consistency across complex assets has also improved. Detailed assets such as professional 3D blockouts, product packaging, and brand visual identity systems can be carried into the output with much higher fidelity, preserving earlier design and shot-planning work.
03Precise video editing: Professional refinement with faster iteration
  • New localized editing tools can precisely change a background, product, person, or other element while keeping the overall frame, camera work, and pacing intact—making it practical to create once and deliver multiple versions.
  • Generated footage can now be edited and refined for production, reducing rework in post. Typical uses include localizing ads by swapping people, products, or copy; reusing e-commerce footage across multiple SKUs; and producing channel-specific versions of brand content.
04Native support for more than 10 languages and stronger instruction control
  • Native support for more than 10 languages lets creators describe ideas in their own language without translating them first.
  • Instruction following has also improved, with more precise control over complex camera choreography, emotional turns, and layered scene descriptions for global creative and commercial work.
Official Seedance 2.5 trailer, 2 minutes 37 seconds: It moves from a glowing paper airplane at a boy's window to a Jimeng AI prompt that turns an entire city into a world of building blocks. An on-screen label states that the whole film was generated with Seedance 2.5. Source: ByteDance.

Our full launch breakdown, demo videos, and access links are here:

Related coverage
ByteDance launches Seedance 2.5: Create 30-second videos from 50 reference assets
Our launch-day breakdown covers the model's capabilities, demos, availability, and pricing.

Read the full guide and every technique points to the same principle: Specify everything the model would otherwise have to guess. Three recurring patterns run through the document: "Use only... Do not use..."; "At the end, the frame shows..."; and "X corresponds to @ImageN." You will see them repeatedly in the sections below.

Basics

A prompt has six parts—use only what you need

The basic formula is simple: subject + action or event is required. It tells the model who or what is doing what. Four other parts are optional: scene and environment, visual style, camera movement and cuts, and sound. Omit anything the task does not need. Summarize the main action first, add detail only to critical movements, and do not describe the same action twice. Generation settings such as duration and aspect ratio belong in the generation interface or API, not in the prompt.

Subject + action + Scene + Visual style + Camera + Sound
The six parts of a prompt: The solid block is required; every dashed block is optional.
Basic template
<Subject> performs <primary action or event> in <scene and environment>.
The visuals feature <visual style>.
Use <shot size, camera angle, camera movement, or cuts>.
Audio includes <dialogue, ambience, sound effects, or music>.
Official example · Potter
A ceramic artist finishes a pale blue cup in a studio at dawn, lifts it from the wheel, and places it in the center of a wooden shelf.
Soft morning light enters through the window. The wet clay has a delicate sheen, and the workbench remains tidy.
Begin with a medium shot of the wheel-throwing process, slowly push in toward the cup's surface texture, then cut to a frontal view of the shelf.
Retain the low hum of the pottery wheel, the friction of clay, and subtle indoor ambience.

Four symbols separate music, sound effects, dialogue, and subtitles

Natural language works throughout the prompt. When you need to distinguish music, sound effects, dialogue, and subtitles, use these symbols:

ContentSymbolExample
Music()(Soft, measured piano music plays in the background)
Sound effect<><A bell rings in the distance>
Dialogue{}{Hello, welcome back}
Subtitle【】【Chapter 1: Departure】

To control subtitles and sound, state exactly what to keep and what to exclude:

Direct controls for sound and subtitles
No background music. Keep only the characters' dialogue, ambience, and action sound effects.
No subtitles.
No audio at all.

Reinforce the intended dialogue language

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

Official example · Specify the dialogue language
The girl says softly in Japanese: {もう大丈夫です}

If English text is spoken in Chinese, or you need a regional accent, reinforce the instruction with this formula:

Dialogue-language reinforcement formula
Dialogue Language + Regional Variety or Accent + Delivery Style + Speaker + {Dialogue}

Dialogue language: American English. The girl says in natural, conversational American English: {I thought you weren't coming.}

Dialogue language: authentic Los Angeles English. The young man says in natural Los Angeles vernacular: {No way, you actually made it.}
Assets

You can load 50 assets, but the reliable range is much smaller

A single job can combine up to 50 reference assets. Each of the four asset types has an input limit, but the guide also gives a much smaller recommended range. The limit defines what the model accepts; the recommended range is where it tends to stay reliable. Stability usually falls as the number of assets rises:

Asset typeInput rangeRecommended range
ImagesUp to 30 images, each no larger than 4K1 to 8 subjects is ideal for subject images
VideoUp to 10 clips, no more than 30 seconds total1 to 5 subjects, with each clip lasting 5 to 10 seconds
AudioUp to 10 clips, no more than 30 seconds totalKeep only dialogue, voice, ambience, or music directly relevant to the task
Video editingEdit with a source video and reference imagesSource video under 20 seconds and 1 to 5 reference images

You can still go beyond the recommended range: subject images can cover 9 to 12 subjects, subject audio or video can cover 6 to 10, and editing jobs can use 6 to 8 reference images. One more detail improves stability: When the same subject needs several angles, use one image per angle instead of combining the views into a collage. Declare them like this:

Declaring multiple views of one subject
@Image 1 defines the front view of the same folding desk lamp.
@Image 2 defines the left-side structure of the same folding desk lamp.
@Image 3 defines the right-side structure of the same folding desk lamp.
@Image 4 defines the rear structure of the same folding desk lamp.
All four images define one folding desk lamp. The output must contain only one lamp throughout.
Assets

Define every asset: What to use and what to reject

Once the assets are uploaded, state what each one contributes. Three rules are non-negotiable: Put the mapping directly in the prompt; do not rely only on text labels embedded in the images; and never make the model guess which asset belongs to which person, prop, or scene. You do not need a "do not use" clause for every asset. Add one only when a person, background, or composition could leak into the final video by mistake.

@Image1 Potter Use only face · hair · apron ✕ Do not use background @Image2 Pottery studio Use only bench · window · light ✕ Do not use people @Video1 Action rhythm Use shaping · lifting · placing ✕ Exclude person, clothes, scene
Asset routing: Give every asset one mapping line. State exactly what must be used, then explicitly reject anything likely to leak into the output.
Asset role template
@Image 1 defines <subject>'s <appearance, clothing, structure, or material>.
@Video 1 defines <motion, camera movement, or pacing>.
@Audio 1 defines <character or sound type>'s <voice, dialogue, ambience, or music>.

<Subject> completes <primary action or event> in <scene>.
The visuals feature <visual style>, with <camera treatment>.
View the official example: Potter with reference assets 
@Image 1 defines the ceramic artist's facial features, hairstyle, and dark green apron. Do not use the image background.
@Image 2 defines the wooden workbench, window placement, and morning light of the pottery studio. Do not use the people in the image.
@Video 1 defines the pacing of throwing clay with both hands, lifting the cup, and placing it down. Do not use the person's identity, clothing, or scene from the video.

The ceramic artist finishes a pale blue cup in the pottery studio at dawn, lifts it from the wheel, and places it in the center of a wooden shelf.
Begin with a medium shot of the wheel-throwing process, then slowly push in toward the cup's surface texture. Retain the sound of the wheel, the friction of clay, and indoor ambience.

One more rule: If a reference video already defines the action, camera movement, and sequence precisely, state what to inherit instead of narrating every movement again. Repetition can conflict with the asset itself.

Assets

How to organize dozens of assets: Assign them scene by scene

Once the asset count grows, the prompt's real job is to define the relationships among people, props, scenes, actions, and sounds. Cramming every asset into one sentence does not help. ByteDance proposes a five-step method designed to make the model select the right assets in each scene. Getting every asset on screen at once is never the goal:

Define roles → Map subjects → Group by type → Build profiles → Assign by scene
Scene 1 | Conservation lab inspection—only call what it needs
Conservator Sample box Conservation lab @Video1 box-opening
Registrar Record board Gallery Other assets stay out
The five-step method ends with scene-based asset assignment: Name only the assets needed in each scene and leave the rest out.

First, give every person, product, and prop a unique name and bind it to an asset:

Step 1 · Subject mapping
<Character A> corresponds to @Image 1. Use only the appearance, hairstyle, and clothing.
<Character B> corresponds to @Image 2. Use only the appearance, hairstyle, and clothing.
<Prop A> corresponds to @Image 3. Use only the structure, material, and color.
<Scene A> references @Image 4. Use only the spatial layout, architecture, and lighting. Do not use the people in the image.
Bad example: "@Image1 through @Image4 define four characters respectively." It never says which image maps to which character, so the model still has to guess.

Second, sort larger asset sets by type—people, props, scenes, actions, and sounds each get their own group:

Step 2 · Group by type
[Characters]
<Conservator> corresponds to @Image 1. Use only the appearance, hairstyle, and clothing.
<Registrar> corresponds to @Image 2. Use only the appearance, hairstyle, and clothing.
<Exhibition Installer> corresponds to @Image 3. Use only the appearance, hairstyle, and clothing.
<Guide> corresponds to @Image 4. Use only the appearance, hairstyle, and clothing.
Do not interchange the four characters' appearances, clothing, actions, positions, or dialogue.

[Props]
<Sample Case> corresponds to @Image 5 and belongs only to <Conservator>.
<Record Board> corresponds to @Image 6 and belongs only to <Registrar>.

[Scenes]
<Conservation Lab> references @Image 7. Use only the space, materials, and lighting.
<Gallery> references @Image 8. Use only the space, materials, and lighting.

[Motion and Audio]
@Video 1 defines the motion of <Conservator> opening <Sample Case>. Do not use the person or scene from the video.
@Audio 1 defines <Guide>'s voice and specified dialogue.

Third, when the same character uses several assets across multiple scenes, build a single consolidated profile:

Step 3 · Key-subject profile
[Subject Profile: Conservator]
Appearance and clothing: @Image 1.
Fixed prop: <Sample Case> from @Image 5.
Locations: <Conservation Lab> and <Gallery>.
Motion references: the case-opening motion from @Video 1 and the sample-placement motion from @Video 2.
Do not use: other characters' clothing. Do not give this character <Record Board> or guide equipment.

Fourth, call assets scene by scene. Each scene names only the assets it uses, the event that occurs, and the required end state:

Step 4 · Scene-based asset assignment
Scene 1 | Inspection in the Conservation Lab
Use: <Conservator>, <Sample Case>, <Conservation Lab>, and the case-opening motion from @Video 1.
Event: <Conservator> opens <Sample Case> at the workbench and inspects the sample inside.
End state: <Conservator> remains on the inner side of the workbench. <Sample Case> stays beside the conservator's right hand, which is on the left side of the frame.

Scene 2 | Registration in the Gallery
Use: <Registrar>, <Record Board>, and <Gallery>.
Event: <Registrar> checks the number on <Record Board> beside the display case.
End state: <Registrar> still holds <Record Board> with both hands. No other character enters the display-case area.
Long video

For a 30-second video, split the story into stages and change one thing at a time

Break event-heavy stories into consecutive stages. Give each stage one major state change, then state what must be directly visible at the end: who holds the bouquet, or which side of the table the scissors return to. The crucial line is "At the end." It gives the model a visible target.

Stage 1
Event: Arrange and trim stems
End: Bouquet in left hand
Stage 2
Event: Wrap and tie ribbon
End: Bouquet centered on table
Stage 3
Event: Move to pickup shelf
End: Bouquet on pickup shelf
The structure of a long video: One major change per stage, with the final visible state stated explicitly.
30-second video template
[Generation Goal]
Generate a <video type>. The central subject is <subject>, and the primary event is <story summary>.

[Stage 1]
Initial state: <initial state of characters, props, and scene>.
Primary event: <one primary action or event>.
End state: <character positions, prop ownership, or visible scene state>.

[Stage 2]
Continue from the previous stage: <state that must remain unchanged>.
Primary event: <one primary action or event>.
End state: <observable state>.

[Stage 3]
Primary event: <closing event>.
End state: <final visible state>.

[Maintain Consistency]
Keep <character identity, number of characters, clothing, prop ownership, spatial direction, and audio relationships> consistent.
View the official example: Packaging a flower-shop order 
[Generation Goal]
Generate an instructional video showing a flower shop's order-packing process. <Florist> and <Store Assistant> arrange, wrap, and hand off a bouquet together.

[Stage 1]
Initial state: <Florist> stands behind the workbench. Loose flower stems, scissors, and wrapping paper lie on the tabletop.
Primary event: <Florist> arranges the stems and trims them to length.
End state: <Florist> holds the bouquet in the left hand, and the scissors are back on the right side of the workbench.

[Stage 2]
Continue from the previous stage: both characters retain the same identities and clothing, and <Florist> still holds the bouquet.
Primary event: <Store Assistant> unfolds the wrapping paper. <Florist> places the bouquet inside and ties it with a green ribbon.
End state: the wrapped bouquet lies flat in the center of the workbench, with the ribbon bow facing the camera.

[Stage 3]
Primary event: <Store Assistant> picks up the bouquet and places it on the pickup shelf.
End state: the bouquet is centered on the pickup shelf, and both characters stand behind the workbench inspecting the finished order.

[Maintain Consistency]
Keep <Florist> and <Store Assistant>'s identities, clothing, workbench orientation, scissors position, and bouquet ownership consistent.

Three levels of timing control—use stages for most narratives

Use one-second timing only when you need to control a critical handoff, entrance, exit, transition, or beat:

MethodBest forExample
Time rangeAllocating story beats0-3 seconds... 3-7 seconds... 7-12 seconds...
Exact timePlacing one key eventAt second 5, the camera quickly pans left and completes the transition.
Relative timeDescribing a delay between events3 seconds after the character presses the button, the room lights gradually fade out.
Timestamp example
0-5 seconds: Show an empty wooden display table. A hand places a white ceramic plate on it. End state: the hand has left the frame, and only the white plate remains in the center of the table.
5-10 seconds: Remove the white plate, then place a clear glass on the table. End state: only the clear glass remains in the center of the table.
10-15 seconds: Remove the clear glass, then place a green ceramic vase on the table. End state: only the green vase remains in the center of the table.
Time ranges must be continuous and must not overlap. They are time budgets, so actions may begin or end slightly around a boundary. Too little content leaves the model room to improvise; too much can cause excessive cuts or missing story beats. Do not use timestamps to force an impossible frequency either. "Complete the action three times in one second" will not work.
Editing

To edit a video, establish one master and fence off the change

Before editing, remember this parameter table. Three task types automatically lock some generation settings based on the input assets. Locked settings cannot be changed in either the generation interface or the API.

Task typeAspect ratioDuration
Video editingAutomatically preserves the input video's aspect ratio; lockedAutomatically preserves roughly the input video's duration; locked. Frame processing may produce a difference of up to about 0.3 seconds
First-frame or first-and-last-frame generationAutomatically uses the first image's aspect ratio. The first and last frames should match, or the last frame may be stretchedConfigurable
Video extensionAutomatically preserves the input video's aspect ratio; lockedExtension length is configurable

Editing an existing video follows a fixed five-part structure: Establish the source video as the sole editing master, then define the editing goal, target asset role, editing scope, and preserved content. The essential move is to draw a boundary around the one thing that must change and explicitly keep everything else intact:

@Video1 frame Person: Keep Right wall light Change only this: Blue to orange, 4-7 sec Keep all people, actions, shots, and sound
Editing is boundary-setting: Isolate the object and time range to change, then explicitly preserve everything else.
Video editing · General five-part template
[Edit Goal]
Edit @Video 1. Within <the entire video or a specific time range>, <add, remove, replace, or adjust> <visual object, region, or audio category>.

[Source Video Role]
@Video 1 is the sole editing master. It defines <characters, scene, actions, composition, camera movement, occlusion relationships, audio, and event order>.

[Target Material Role]
@Image 1 or @Audio 1 defines <specified attributes of the target object or sound>.

[Edit Scope]
Modify only <object, region, time range, or audio category>.

[Content to Preserve]
Keep <visual content, motion, audio, and timing relationships that must not change> from @Video 1.
View the official example: Change cool blue light to warm orange at 4-7 seconds 
[Edit Goal]
Edit @Video 1. Only from 4-7 seconds, change the cool blue light on the right wall to warm orange light.

[Source Video Role]
@Video 1 is the sole editing master. It defines the character, room layout, actions, composition, camera movement, audio, and event order.

[Edit Scope]
Change only the light color on the right wall and the area it illuminates. Allow the character's skin tone to respond naturally to the environmental light.

[Content to Preserve]
Keep the character's identity, clothing, expression, position, motion, room structure, camera movement, dialogue, and ambience from @Video 1.

Subject replacement: The new object must inherit the old object's entire timeline

Replacing one object with another requires an additional "timeline inheritance" section. The new object must inherit every appearance, occlusion, and exit point from the original, along with its path and speed. Think of it as changing the actor without changing the script: The replacement must hit every mark at exactly the same moment.

Subject replacement template
[Edit Goal]
Edit @Video 1. Change only <original object> to <target object>.

[Source Video Role]
@Video 1 is the sole editing master. It defines the original scene, camera position, camera movement, motion path, occlusion relationships, and event order.

[Target Reference Role]
@Image 1 defines <target object>'s <appearance, structure, or material>. Do not use <irrelevant background, people, or composition>.

[Edit Scope]
Modify only <specific object and area>. The entire video contains <number> target object(s). Do not modify <content to preserve>.

[Timeline Inheritance]
<Target object> inherits every appearance, motion, occlusion, and exit of <original object>, including timing, duration, path, and speed changes.
Except for the object or area explicitly modified above, keep all other people, props, scene content, camera movements, cuts, and event order from @Video 1 unchanged.
View the official example: Replace a yellow desk lamp with a white one 
[Edit Goal]
Edit @Video 1. Replace only the yellow folding desk lamp with the white folding desk lamp in @Image 1.

[Source Video Role]
@Video 1 is the sole editing master. It defines the desk, books, hand movements, camera position, camera movement, occlusion relationships, and event order.

[Target Reference Role]
@Image 1 defines only the white folding desk lamp's appearance, structure, and material. Do not use the image's background, composition, or other objects.

[Edit Scope]
Keep exactly one white folding desk lamp throughout the video. Replace only the original yellow folding desk lamp. Do not modify the books, desk, hands, or background.

[Timeline Inheritance]
The white folding desk lamp inherits every appearance, lamp-arm rotation, hand occlusion, and exit of the original yellow folding desk lamp, including timing, path, and speed changes.
Except for the object or area explicitly modified above, keep all other people, props, scene content, camera movements, cuts, and event order from @Video 1 unchanged.

Background replacement: Change only the area outside the subject's outline

Background replacement template
[Edit Goal]
Edit @Video 1. Replace only <original background area> with <target environment> from @Image 1.

[Source Video Role]
@Video 1 is the sole editing master. It defines the people, foreground objects, actions, composition, camera movement, and event order.

[Target Reference Role]
@Image 1 defines only <target environment>'s spatial layout, materials, depth of field, ambient color, and lighting direction. Do not use the people or foreground objects in the image.

[Edit Scope]
Modify only <background outside the subject's silhouette>. Do not modify <subject identity, facial features, hairstyle, clothing, expression, position, size, or motion>.

[Timeline Inheritance]
Keep the character actions and occlusion relationships from @Video 1. Except for the object or area explicitly modified above, keep all other people, props, scene content, camera movements, cuts, and event order from @Video 1 unchanged.
View the official example: Replace a light-gray background with a daytime greenhouse 
@Video 1 is the sole editing master. It defines the people, actions, composition, camera treatment, and event order.
@Image 1 provides only the spatial layout, depth of field, ambient color, and lighting direction of a daylit glass greenhouse. Do not use the people in the image.

Replace only the light gray background outside the person's silhouette in @Video 1 with the daylit glass greenhouse from @Image 1.
Keep the person's identity, facial features, hairstyle, clothing, expression, position, size, and arm-raising motion from @Video 1.
Except for the object or area explicitly modified above, keep all other people, props, scene content, camera movements, cuts, and event order from @Video 1 unchanged.

Sound can be edited independently

Dialogue, language, voice, background music, and sound effects can all be handled separately. Specify the speaker or sound category, the intended change, and whether every other sound must remain intact:

Two sound-editing examples
Edit @Video 1. Remove only the original background music. Keep the character dialogue, lip sync, ambience, and action sound effects; preserve the visuals, camera treatment, and editing rhythm from @Video 1.

Edit @Video 1. Change <Presenter>'s spoken language to natural American English while preserving the dialogue content and speaking times. Keep all other character voices, background music, ambience, and visuals from @Video 1.
Extension

To extend a video, align the boundary frame first

Video extension creates new content beyond the original clip's boundary. Adding footage after the final frame is backward extension; adding it before the opening frame is forward extension. Both directions follow the same rule: First describe the boundary frame as a continuity constraint, then describe the new content. The same subject must remain one continuous object throughout—never duplicated or split.

Forward extensionAdded before Source video Backward extensionAdded after Extension end = source first frame Extension start = source last frame Lock boundary continuity, then add content
Each extension direction has one boundary frame that must be aligned.

Backward extension: The extension's first frame must continue the source video's final frame

Basic backward-extension template
@Video 1 is the source video to extend forward.

Extend @Video 1 forward. The first frame of the extended segment directly continues from the last frame of @Video 1. Maintain continuity in <subject pose and orientation>, <prop position>, <background and spatial relationships>, <camera position and composition>, <lighting>, and <motion direction>.

Then, <describe the new action, event, camera treatment, or audio to add>.

Throughout the extension, maintain continuity in <character identity and clothing>, <key props>, <background layout>, and <axis of action>.
Keep each subject as the same continuous instance throughout: do not duplicate or split it, and keep the person's appearance or the object's number of parts stable.
View the official example: A paper airplane continues gliding out of frame 
@Video 1 is the source video to extend forward.

Extend @Video 1 forward. The first frame of the extended segment directly continues from the last frame of @Video 1. Maintain the same locked-off medium shot, the orange paper airplane's position and orientation, the classroom-window background, the afternoon lighting, and its movement toward the right side of the frame.

Then, the orange paper airplane continues gliding toward the right and exits the frame while the white curtain beside the window sways slightly. Keep the camera and classroom background in the state established by the source video's last frame.
How to include other reference assets: Template and gardener example
Backward extension · Reference-asset template
@Image 1 defines <Character A>'s facial features.
@Image 2 defines <Character A>'s clothing.
@Image 3 defines <key prop>'s structure and material.
@Video 1 is the source video to extend forward.

Extend @Video 1 forward. The first frame of the extended segment directly continues from the last frame of @Video 1. Maintain continuity in <boundary-frame state>.

Then, <Character A uses the key prop to complete a new action or event>.

Throughout the extension, maintain continuity in <character identity and clothing>, <key prop>, <background layout>, and <axis of action>.
Keep each subject as the same continuous instance throughout: do not duplicate or split it, and keep the person's appearance or the object's number of parts stable.
Official example · Gardener
@Image 1 defines <Gardener>'s facial features.
@Image 2 defines <Gardener>'s light green work apron.
@Image 3 defines <Wicker Flower Basket>'s structure and material.
@Video 1 is the source video to extend forward.

Extend @Video 1 forward. The first frame of the extended segment directly continues from the last frame of @Video 1. Maintain the greenhouse workbench, <Gardener>'s position, and <Wicker Flower Basket>'s position.

Then, <Gardener> lifts <Wicker Flower Basket> with both hands and places it on the middle shelf of the wooden rack behind them.

Throughout the extension, maintain continuity in <Gardener>'s face, apron, greenhouse layout, and camera direction.
New assets can supplement a person, prop, or sound, but they cannot override the source video's final frame as the authority for the extension's opening image.

Forward extension: Make the source video's first frame the extension's required end state

ByteDance calls out one specific failure mode here. If you write only "then continue into the original video," the model may introduce a person or effect before it should appear, or change the frame again after reaching the target state. The correct approach is to describe what happens before the original video begins, then define every part of its first frame as the extension's required end state:

Basic forward-extension template
@Video 1 is the source video to extend backward.

Extend @Video 1 backward. Before the source video begins, <describe the preceding action, event, camera treatment, or audio>.

The last frame of the extended segment naturally connects to the first frame of @Video 1: <subject pose and orientation>, <prop position>, and <background and spatial relationships>. Match the <camera position and composition>, <lighting>, and <motion direction> of @Video 1's first frame.

Throughout the extension, maintain continuity in <character identity and clothing>, <key props>, <background layout>, and <axis of action>.
Keep each subject as the same continuous instance throughout: do not duplicate or split it, and keep the person's appearance or the object's number of parts stable.
View the official example: Open on an empty glass greenhouse 
@Video 1 is the source video to extend backward.

Extend @Video 1 backward. Before the source video begins, show an empty establishing shot of the same glass greenhouse. Morning mist drifts slowly near the floor, the overhead shade rises gradually, and no people are present yet.

The last frame of the extended segment naturally connects to the first frame of @Video 1. Match the greenhouse's central aisle, planting tables on both sides, glass frame, soft morning light, and locked-off wide composition. At the end, the shade is fully raised, the aisle is empty, and the leaves still sway slightly.
How to include other reference assets: Template and curator example
Forward extension · Reference-asset template
@Image 1 defines <Character A>'s facial features.
@Image 2 defines <Character A>'s clothing.
@Image 3 defines <key prop>'s structure and material.
@Video 1 is the source video to extend backward.

Extend @Video 1 backward. Before the source video begins, <Character A completes a preceding action or event>.

The last frame of the extended segment naturally connects to the first frame of @Video 1: <Character A's pose and orientation>, <key prop's position and state>, and <other characters' positions>. Match the <background and spatial relationships>, <camera position and composition>, <lighting>, and <motion direction> of @Video 1's first frame.

Keep each subject as the same continuous instance throughout: do not duplicate or split it, and keep the person's appearance or the object's number of parts stable.
<Materials that should appear only after the source video begins> must not appear early in the backward extension.
Official example · Curator
@Image 1 defines <Curator>'s facial features.
@Image 2 defines <Curator>'s dark blue work jacket.
@Image 3 defines <Wooden Display Case>'s structure and material.
@Image 4 defines the gray workwear of two <Exhibition Assistants>.
@Image 5 defines <Exhibition Preparation Room>'s space and lighting.
@Video 1 is the source video to extend backward.

Extend @Video 1 backward. Before the source video begins, <Curator> walks to the workbench, picks up the closed <Wooden Display Case>, and opens its lid.

The last frame of the extended segment naturally connects to the first frame of @Video 1. <Curator> stands in the center of the frame, holding the open <Wooden Display Case> with both hands. The two <Exhibition Assistants> stand behind the curator, one on each side. Match the vertical frontal medium shot, workbench position, preparation-room background, and morning light from the left established by @Video 1's first frame.
The boundary should look naturally continuous, but pixel-perfect identity is not possible. The extended segment may also differ slightly in volume. Review the images and sound on both sides of the boundary, as well as the complete extended clip.
Advanced

Advanced controls: Keyframes, storyboards, and blockouts

First and last frames require no mode switch—declare them in the first line

In omni-modal reference mode, state directly in the first prompt sentence that @Image1 is the first frame and @Image2 is the last frame. The system locks the output aspect ratio to the first frame, while duration remains configurable. The first and last frames must use the same aspect ratio or the last frame may be stretched. Define each anchor image separately; do not combine them into a vague instruction such as "@Image1 and @Image2 are the first and last frames." Other reference images can still define people, props, and scenes, but they may supplement only the specified attributes and must not replace the anchor compositions.

First and last frames with reference assets
@Image 1 is the first frame. It defines the opening composition, subject position, pose, prop state, scene, and camera direction.
@Image 2 is the last frame. It defines the ending composition, subject position, pose, prop state, scene, and camera direction.
@Image 3 defines <Subject A>'s <appearance, clothing, structure, or material>. Do not change the first-frame composition defined by @Image 1 or the last-frame composition defined by @Image 2.
@Image 4 defines <specified attributes> of <Subject B, prop, or scene>. Do not change the first-frame composition defined by @Image 1 or the last-frame composition defined by @Image 2.

<Describe one continuous action or event>.
The video begins naturally from the first frame defined by @Image 1 and reaches the last frame defined by @Image 2 after the continuous action.
Between the first and last frames, maintain continuity in <character identity, prop structure and ownership, scene layout, and camera direction>.
View the official example: Perfume workshop 
@Image 1 is the first frame. It defines the opening composition, character positions, poses, tabletop prop states, perfume-workshop scene, and camera direction.
@Image 2 is the last frame. It defines the ending composition, character positions, poses, tabletop prop states, perfume-workshop scene, and camera direction.
@Image 3 defines <Perfumer>'s face, hairstyle, and dark green apron. Do not change the first-frame composition defined by @Image 1 or the last-frame composition defined by @Image 2.
@Image 4 defines <Glass Perfume Bottle>'s shape, material, and label position. Do not change the first-frame composition defined by @Image 1 or the last-frame composition defined by @Image 2.

Starting from the first-frame pose, <Perfumer> picks up a dropper and <Glass Perfume Bottle>, drips amber fragrance oil into the bottle, swirls it gently, closes the stopper, places the finished bottle in the center of the table, and naturally reaches the last frame defined by @Image 2.
Between the first and last frames, maintain continuity in <Perfumer>'s identity and clothing, bottle count and structure, wooden-table layout, warm side lighting, and camera direction.

Multiple keyframes: Control the stage order, not frame-by-frame replication

When separate images define different stages of a process, begin with: "Use @Image1 through @ImageN as keyframes in that order." Then describe the key state represented by each image. Independent keyframes are easier to align than several frames combined into one contact sheet.

Multiple-keyframe sequence template
Use @Image 1 through @Image N as keyframes in this order.

@Image 1 is the first frame. It defines <opening composition, subject position, pose, prop state, and camera direction>.
@Image 2 defines the second keyframe: <visible end state of Stage 1>.
@Image 3 defines the third keyframe: <visible end state of Stage 2>.
@Image N is the last frame. It defines <ending composition, subject position, pose, prop state, and camera direction>.

The video passes through the states defined by @Image 1, @Image 2, @Image 3, and @Image N in order, using continuous action to transition naturally between stages.
Maintain continuity in <subject identity, prop structure and ownership, scene layout, lighting, and axis of action> throughout.
View the official example: Four paper-airplane keyframes 
Use @Image 1 through @Image 4 as keyframes in this order.

@Image 1 is the first frame. It shows an orange paper airplane resting on the left side of a classroom desk, pointed toward the right, in a locked-off medium shot.
@Image 2 defines the second keyframe: one hand lifts the same orange paper airplane from the desk without changing its direction.
@Image 3 defines the third keyframe: the same orange paper airplane passes the window while the curtain moves slightly to the right.
@Image 4 is the last frame. It shows the same orange paper airplane resting on the middle shelf of the bookcase on the right, still pointed toward the right.

The video passes through the states defined by @Image 1, @Image 2, @Image 3, and @Image 4 in order. Keep flight direction and speed continuous between stages.
Maintain the paper airplane's orange material, size, and folds, as well as the classroom layout, afternoon side lighting, and camera axis.

Storyboard grids: Define the story and shot order, not exact panel replication

A storyboard grid supplies the overall story, shot order, and rough composition. ByteDance recommends no more than 15 panels, using simple line drawings or clean diagrams with minimal text. The prompt must define the reading order, then describe the subject's action, framing and camera movement, final visual style, and sound for each panel.

Storyboard-grid template
@Image 1 provides an <N-panel storyboard grid> for shot order and approximate composition. Read it <left to right, top to bottom>. Do not use the grid's <line-art style, text labels, or placeholder characters>.
@Image 2 defines <Subject A>'s <appearance and clothing>.
@Image 3 defines <key prop or scene>'s <structure, material, or lighting>.

Shot 1: <shot size, subject action, and scene state>.
Shot 2: <shot size, subject action, camera movement, or transition>.
...
Shot N: <closing action and final visible state>.

The final video uses <visual style>. Audio includes <dialogue, ambience, action sound effects, or music>.
View the official example: Four-panel pottery storyboard 
@Image 1 provides a four-panel pottery-making storyboard for shot order and approximate composition. Read it left to right, top to bottom. Do not use the storyboard's line-art style or text labels.
@Image 2 defines <Ceramic Artist>'s face, short hair, and dark gray apron.
@Image 3 defines <Blue-Glazed Cup>'s proportions, glaze color, and curved handle.

Shot 1: a wide shot establishes a quiet pottery studio with <Ceramic Artist> seated at the wheel.
Shot 2: a side medium shot shows both hands shaping the rotating clay as the cup body takes form.
Shot 3: a close-up shows fingers refining the rim and handle joint while slip moves slowly over the fingertips.
Shot 4: a medium close-up shows the fired <Blue-Glazed Cup> placed on a wooden shelf as <Ceramic Artist> withdraws both hands.

Use a realistic documentary look. Retain the wheel's rotation, wet-clay friction, and studio ambience.

Blockouts: Know whether you have a motion skeleton or a finished model

A blockout is a reference video built from gray geometry or untextured models to previsualize movement and camera placement. It is like rehearsing a film with stand-ins and cardboard boxes: Positions and timing are locked first, then real actors and props replace them in the final production. ByteDance divides blockouts into two levels, so identify which kind you have before writing the prompt:

TypeBest forAsset requirementsPrompt focus
Coarse blockoutPrevisualizing actions, paths, positions, camera movement, or cuts with simple geometryClear geometric relationships and a complete action sequence; may be supplemented with images of people, props, and scenesMap every blockout subject individually and state which timing and spatial information to inherit
Fine blockoutReplacing people, materials, colors, scenes, or style in an already complete modelComplete model structure and a clean frame with motion paths, axes, and camera frustums removedPreserve structure, action, and camera work while explicitly defining which attributes to rerender

Every geometric object in a coarse blockout must map individually to a final subject or prop. Attached structures such as arms or wings should be used as blockout information only when their motion sequence is complete; otherwise, they can cause rigid movement or structural misinterpretation.

Coarse-blockout template
@Video 1 is a coarse blockout reference. It provides only <motion paths, subject blocking, camera position, camera movement, cuts, lighting changes, sound rhythm, or spatial relationships>. Do not use its blockout appearance, materials, or scene.
<Blockout Subject A> in @Video 1 corresponds to <Subject A>.
<Blockout Subject B or geometric prop> in @Video 1 corresponds to <Subject B or key prop>.
@Image 1 defines <Subject A>'s <appearance, clothing, or structure>.
@Image 2 defines <specified attributes> of <Subject B, key prop, or scene>.

<Subject> completes <primary action or event> in <scene>.
Keep <motion path, blocking, camera movement, cuts, lighting, or sound rhythm> from @Video 1.
The final video uses <characters, scene, materials, and visual style>. Audio includes <dialogue, ambience, or action sound effects>.
View the official example: Cylinder becomes a guide, cuboid becomes a display cart 
@Video 1 is a coarse blockout reference. It provides only the character's walking path, cart direction, locked-off camera, one push-in, and two cuts. Do not use its gray geometry or empty scene.
The tall cylinder in @Video 1 corresponds to <Guide>.
The rectangular block in @Video 1 corresponds to <Mobile Display Cart>.
@Image 1 defines <Guide>'s face, blue uniform, and name badge.
@Image 2 defines <Mobile Display Cart>'s white metal frame and clear cover.
@Image 3 defines the technology gallery's curved walls, gray floor, and overhead strip lights.

<Guide> pushes <Mobile Display Cart> along the curved wall, stops in front of the central display, and opens the clear cover.
Keep the walking path, subject blocking, push-in direction, and cut points from @Video 1.
Use a bright, realistic museum-documentary style. Retain footsteps, wheel sounds, and gallery ambience.
Fine-blockout template
@Video 1 is a fine blockout reference. Preserve <subject structure, action, spatial layout, camera position, camera movement, and cuts>. Do not use its original gray materials or empty background.
@Image 1 defines <subject>'s <character appearance, material, color, or surface details>.
@Image 2 defines <scene>'s <space, materials, lighting, or visual style>.

Re-render <subject> from @Video 1 as <final subject>, and re-render the scene as <final scene>.
Keep <structure, action, camera treatment, and spatial relationships> from @Video 1. Use <materials, colors, and style>. Audio includes <ambience, sound effects, or music>.
View the official example: Rerender a gray model as a brass-and-glass sculpture 
@Video 1 is a fine blockout reference. Preserve the kinetic sculpture's complete structure, three-ring rotation relationship, pedestal position, orbiting camera movement, and cuts. Do not use the gray materials or empty background.
@Image 1 defines the outer ring's brushed-brass material.
@Image 2 defines the inner blades' translucent blue-glass material.
@Image 3 defines a contemporary gallery with white curved walls, a dark gray floor, and soft overhead lighting.

Re-render the ring structure from @Video 1 as a kinetic sculpture made of brass and blue glass, and re-render the scene as a contemporary art gallery.
Keep the structure, rotation rhythm, orbiting camera movement, and cuts from @Video 1. Retain the sculpture's low mechanical rotation sound and quiet interior ambience.
Finished video

One-click videos and seamless transitions: Turn loose images and separate clips into one piece

One-click video: Specify all five parts—do not just say "make a video"

One-click video generation turns multiple images, or images plus a style-reference video, into a complete clip with consistent pacing. The prompt must cover five things: asset roles, image order, amount of motion, editing style, and sound. If image order matters, define every image individually. If the model may arrange them freely, explicitly say that it may organize them by theme. As always, name and bind every person or product separately.

One-click video template
[Material Roles]
@Image 1 is used for <character, product, scene, or opening image>.
@Image 2 is used for <character, product, scene, or process image>.
@Image 3 is used for <character, product, scene, or ending image>.
@Video 1 is used only for <editing rhythm, transitions, subtitle treatment, or music style>. Do not use its character identities or scene (optional).

[Arrangement]
Show the images in <upload order, a specified order, or a model-selected thematic order>.
<State the character, product, location, and event relationships that must remain consistent>.

[Image Motion]
Apply <subtle live motion, parallax, push-in/pull-out, lateral movement, or local action> to each image.
Keep <subject appearance, product structure, text, or background relationships> stable.

[Final Style]
Use <editing rhythm, transition style, subtitle or graphic treatment, and color style>.

[Audio]
Include <dialogue, ambience, sound effects, or music>.
View the official example: A night-market travel video from six images 
[Material Roles]
@Image 1 is used for the night-market entrance and opening environment.
@Image 2 is used for <Traveler> walking along the street.
@Image 3 is used for the lantern stall and craft details.
@Image 4 is used for three friends eating together.
@Image 5 is used for the riverside night view and reflections.
@Image 6 is used for the final group photo by the bridge.
@Video 1 is used only for light editing rhythm, hand-drawn stickers, and transition style. Do not use its character identities or locations.

[Arrangement]
Show @Image 1 through @Image 6 in order to form a complete sequence: arrival, street exploration, dinner, riverside walk, and group photo.
Keep the three friends' appearances and clothing consistent. Do not mix their identities.

[Image Motion]
Use slow push-ins and subtle parallax for environment images. Add only natural blinking, head turns, glass-raising, and slight clothing movement to character images.
Keep stall structure, table position, and bridge railing stable.

[Final Style]
Use an upbeat travel-video rhythm. Connect scenes with natural occlusion and similar colors. Keep hand-drawn stickers at the frame edges.

[Audio]
Retain night-market chatter, light dish sounds, and riverside wind, with upbeat but unobtrusive instrumental music.

Seamless transitions: Define the trigger, transformation, and arrival state

A seamless transition generates continuous footage between two videos. Write it as a chain:

Clip roles → Trigger → Camera move → Transformation → Arrival state → Sound bridge
The seamless-transition chain: Define the role of each clip, then describe the entire transition from trigger to sound bridge.
Transition typeWhat to specify
Dive or reversalCamera direction, speed changes, and the point at which the next scene begins
Character rotationBody position, rotation direction, and how clothing or the background changes continuously
Foreground occlusionWhen the foreground object fills the screen and what composition appears after it clears
Object transformationThe corresponding shapes and materials before and after, plus the transformation process
Push, pull, or focus shiftCamera movement, focus subject, and the continuous spatial relationship between the two scenes
Seamless-transition template
@Video 1 is the before-transition clip. Use its <ending subject, action, composition, camera direction, and audio>.
@Video 2 is the after-transition clip. Use its <opening subject, composition, camera direction, and audio>.
Keep <character identity, product structure, scene, and primary action> stable in the original portions of @Video 1 and @Video 2.

At the end of @Video 1, <subject or foreground object> triggers the transition through <action>.
The camera <movement direction and speed change>, while <shape, material, light, or space> gradually transforms into <corresponding element> at the start of @Video 2.
The transition ends naturally at @Video 2's opening composition, preserving continuity in <subject position, camera direction, and motion trend>.
Audio transitions smoothly from <before audio> to <after audio>.
Official example · Red umbrella becomes a skylight
@Video 1 is the before-transition clip. Use its rainy night street, red umbrella, slow push-in, and rain sound.
@Video 2 is the after-transition clip. Use its circular gallery skylight, upward camera movement, and quiet interior reverberation.
Keep the people, street, gallery structure, and primary actions in the two original videos stable.

At the end of @Video 1, the red umbrella approaches the camera and gradually fills the entire frame, triggering the transition.
The camera continues moving forward. The umbrella's circular edge gradually becomes the skylight's metal ring, and the red fabric transitions into white daylight passing through the skylight.
The transition ends naturally at @Video 2's upward-looking opening composition, with the camera movement changing smoothly from forward motion to an upward rise.
The rain gradually fades into footsteps reverberating inside the gallery.
Performance and camera

Translate abstract direction into visible behavior

Emotion: Describe observable behavior so the model does not improvise

Words such as "nervous," "warm," or "oppressive" give the model a general direction, but leave the performance open to interpretation. For reliable acting, describe what can be seen or heard: the eyes, brows, mouth, breathing, gaze, or hands. For a single emotional turn, 2 to 4 clear signals are enough. If the emotion changes several times, divide it into stages around the triggering events.

Emotion word only

"The young actor looks nervous, then relaxes."

  • Frown, clench a fist, or pace? The model decides
  • There is no anchor for when the shift occurs
Observable behavior
  • The fingers gripping the program suddenly stop
  • The gaze slowly turns toward the curtain while the shoulders remain tense
  • After confirming the curtain call, the actor exhales softly
  • A restrained smile appears as the eyes gradually fill with tears
Single emotional turn
The overall emotion shifts from <starting emotion> to <ending emotion>.
After <triggering event>, <subject> first shows <immediate observable reaction>.
Then, <eyes, brows, mouth, breathing, gaze, or hand movement> gradually <changes>.
Finally, <subject> expresses <target emotion> through <restrained or explicit outward behavior>.
Multi-stage emotional progression
When <subject> hears or sees <first triggering event>, <first observable reaction>.
When <second triggering event> occurs, <change in expression, gaze, or breathing>.
After confirming <critical information>, the emotion that <subject> tries to restrain or conceal gradually becomes visible through <observable behavior>.
Finally, <subject's final action, expression, or manner of speaking>.
Official example · Young actor at curtain call
Applause marking the end of the performance comes from behind the stage. The young actor's fingers suddenly stop on the program, the gaze turns slowly toward the curtain, and the shoulders remain tense.
After confirming that the curtain call is over, the actor exhales softly. The shoulders gradually relax, a restrained smile appears, and the eyes slowly well with tears, but the actor never turns to leave.

Camera language: Use common terms directly and translate obscure ones into visible effects

Seedance recognizes standard camera language directly in the prompt:

CategoryCommon supported terms
Shot sizeExtreme wide shot, wide shot, medium shot, close-up, extreme close-up
Camera movementDolly in, dolly out, pan, truck, follow, orbit, dive, pull back, tilt up, handheld shake
Position and perspectiveLow angle, overhead view, first person

Popular camera techniques can also be named directly, but when several subjects share the frame, specify which one the camera follows, where the move begins, and where it ends:

TechniqueRecommended description
One-shot sequenceDescribe the subjects, spaces, and events the camera passes through in order
Dolly zoomState that the subject keeps the same size while the background appears to move closer or farther away, creating a disorienting effect
Aerial viewSpecify the viewing height, movement direction, and environmental area to reveal
FPVDescribe the first-person flight or traversal path, speed, and turns
Bullet timeDefine the action to freeze or slow down and the direction of the camera orbit
Handheld shotName the subject being followed and the amount of shake; "handheld feel" alone provides no camera target
Speed ramp with reboundState where the action accelerates, slows, or rebounds, and define the final resting state

For obscure terms without a consistent industry meaning, keep the name but translate it into directly observable changes in the frame:

Formula for translating obscure camera terms
Cinematography Term + Target Subject + Visual Change + Foreground/Background Relationship + Direction or Speed

Rack focus: shift focus smoothly from the leaves in the foreground to the person in the background. The leaves gradually blur while the person's face changes from soft to sharp.
View five official cinematography examples 
Example 1. Shallow-depth-of-field portrait: keep <Pastry Chef>'s eyes and face sharp while the glass jars and lights in the background become soft, circular bokeh.

Example 2. Tracking shot: move horizontally at the same speed as <Skateboarder>, keeping the subject sharp while the roadside wall forms horizontal motion blur from right to left.

Example 3. Golden hour: warm, low-angle sunlight enters from behind and to the left of <Hiker>, casting long shadows across the mountain ridge.

Example 4. Natural vignette: darken the four corners gradually while keeping the brightness and skin tone of <Pianist> in the center natural, without a black border.

Example 5. Whip-pan transition: at 5 seconds, move the camera rapidly to the left. Cut when the foreground bookshelf fully covers the frame, then continue moving left at a similar speed in the next scene.
You can specify aperture, focal length, and shutter values, but describing the visible result is usually clearer than providing a number alone.
Final checks

The preflight checklist—and what Seedance admits it cannot do

The guide compresses its advice into a final checklist. Run through every item before submitting:

✅ Preflight checklist: 14 official checks

What the guide admits Seedance cannot do

A separate limitations section states the model's boundaries plainly:

  • Timestamps can allocate time across events, but they cannot define frame-accurate edit points.
  • Editing prompts can improve the odds that key events align with the source video, but cannot guarantee exact frame-by-frame correspondence.
  • Multi-asset creation is about selecting and combining the right assets. Showing every asset at once has never been the goal.
  • For subtitles, formulas, signs, product specifications, and frame-level timing that must be perfectly accurate, ByteDance recommends using precomposited assets and finishing the work in post-production. Do not expect a perfect direct generation.
  • Video editing locks the source video's aspect ratio and approximate duration. The output may differ by up to about 0.3 seconds.
  • First-frame or first-and-last-frame generation locks the aspect ratio to the first frame. If the two images use different ratios, the final frame may be stretched.
  • Video extension locks the source video's aspect ratio, and the extended segment may differ slightly in volume.
  • When image order or character mapping matters in a one-click video, it must be explicitly defined in the prompt.
  • Seamless transitions aim for visual and sonic continuity, but cannot keep the two source clips pixel-for-pixel unchanged.

That brings us back to the three patterns from the beginning. "Use only... Do not use..." controls assets. "At the end, the frame shows..." controls the process. "X corresponds to @ImageN" controls identity. The guide's dozens of templates are variations on those three ideas. Specify everything the model would otherwise have to guess, and the output becomes more reliable.

Source
Seedance 2.5 Prompt GuideByteDance (Jimeng AI Dreamina)·Lark document in Chinese
Further reading
Dreamina Seedance 2.5 Prompt Guide in English·XiaoHu: Seedance 2.5 launch breakdown
Editorial note
Templates and official examples are reproduced from the Chinese guide. The 14-item preflight checklist is a condensed paraphrase of the original. Diagrams were created by XiaoHu. The background section's feature list and trailer come from official ByteDance assets; the remaining background information comes from our launch coverage.
↑ End of article
✓ This article is free to read in full

Members can copy or download the full Markdown, and let their AI subscribe and ask.

Subscribe · $59/yrSee what's included →
Read the original ↗
📮 New explainers, straight to your inbox

Found this useful? Leave your email — every new explainer, the moment it's out. Unsubscribe anytime.

Related explainers

Practice
Seedance 2.5 official user guide: a hands-on manual for cinematic AI video, with copy-ready formulas and examples
08-03 · 28 min read
Deep Dive
10 Video Creation Tips for Google Flow: Helping Gemini Omni Understand Your Camera Directions
10-01 · 14 min
Practice
MiniMax H3 official guide: a three-part formula for turning prompts from scene descriptions into asset assignments
08-09 · 12 min read