Ad storyboards
Combine product shots, brand material, movement samples, a script and a music brief into one commercial concept.
Multimodal video model by ByteDance
Official model guide and online generator
Seedance 2.0 AI Video Generator
Direct multi-shot video with text, image, video, and audio references, native stereo sound, and precise creative control. Use the Seedance 2.0 AI video generator directly below to create from a prompt, image, frame pair, or supported references.
Generate with Seedance 2.0 online
The complete MuseGen video workspace is embedded here and starts with Seedance 2.0 selected. You can still compare variants or switch models without losing the rest of the workflow.
Generation requires an account and uses credits based on the selected model, variant, duration, resolution, and other settings. Failed tasks are refunded automatically.
What is Seedance 2.0 and when should you use it?
Understand where Seedance 2.0 fits before spending time on references, prompts, and final-resolution generations.
Seedance 2.0 runs on one multimodal architecture for sound and picture together. A single project can join a written brief to still references, movement samples, sound cues and recorded voices, with the prompt giving each file its own job. It shines when a scene needs more than one starting image.
For commercial directors, agencies, e-commerce teams, musicians, game developers and story-driven filmmakers, the practical advantage is not a single headline benchmark. It is the way Seedance 2.0 combines Text, image, frames, multi-reference, video to video, editing and extension with A text brief, up to 9 images, up to 3 clips and up to 3 audio files. That combination determines whether the model can preserve a prepared visual direction or needs to invent most of the scene from language alone.
On this page, research and production live in one flow. Read the official specifications, study the source material, use the prompt framework, and then work in the embedded generator. The selected model defaults to Seedance 2.0, while the rest of MuseGen's upload, progress, history, reuse, and download experience stays available.
Seedance 2.0 specifications and supported formats
Use these official capabilities to plan the input, format, duration, and production tier before you generate.
Developer
ByteDance
Model release
February 2026
Generation modes
Text, image, frames, multi-reference, video to video, editing and extension
Inputs
A text brief, up to 9 images, up to 3 clips and up to 3 audio files
Duration
4–15 seconds
Resolution
480p, 720p, 1080p and as high as 4K
Aspect ratios
Wide, tall, square and portrait frames, 21:9, or adaptive
Audio
Native stereo speech, music, ambience and effects
Best use cases for Seedance 2.0
Start with work where the model's strongest controls create a practical advantage rather than choosing only by maximum resolution.
Stories led by characters
Feed in several character and costume images while you direct expressions, blocking, lines and camera moves.
Music and performance pieces
Match sound and visual rhythm at once for stage performance, choreography, fashion and mood-led pieces.
Restyling and continuing footage
Lengthen a clip, or keep its motion while the art direction, location, subjects or next story beat change.
Official Seedance 2.0 example and source material
This official media was downloaded from the model developer's launch or product material and optimized for fast playback on this page.
Seedance 2.0 official multimodal showcase
Official source material: Showcase clip from ByteDance's official Seedance 2.0 product page.
How to create video with Seedance 2.0
Move from a creative idea to a configured Seedance 2.0 generation without leaving this model page.
1
Describe the shot
Write the subject, action, environment, camera, style, timing, and sound. If you have reference media, upload it and explain the role of each asset.
2
Configure Seedance 2.0
Keep Seedance 2.0 selected, choose the appropriate variant, mode, duration, aspect ratio, resolution, and audio settings, then check the displayed credit cost.
3
Generate, review, and reuse
Start the task, follow progress in the result panel, review the completed video, reuse its settings for another take, or download the finished file.
Why creators choose the Seedance 2.0 AI video generator
The defining capabilities that shape how Seedance 2.0 handles direction, references, motion, sound, and delivery.
Four kinds of input
Combine words, pictures, video and sound in one direction rather than forcing every decision into the text.
References for everything
Point to examples for layout, characters, props, movement, camera language, effects, voice, tempo and sound design.
Several shots in one clip
Plan a short sequence with evolving framing, acting and locations in one video of up to 15 seconds.
Edit and extend footage
Carry an existing video forward, or use plain instructions to change subjects, actions, shots and story.
Native stereo audio
Speech, background music, ambience and synchronised effects come out as part of one audiovisual composition.
Mini, Fast and Standard
Start with quick Mini concepts, iterate on Fast and finish on high-resolution Standard without changing how you work.
How to prompt Seedance 2.0 for more controllable video
A strong Seedance 2.0 prompt behaves like a compact production brief: it gives the model a subject, an ordered action, a camera plan, an art direction, and a soundtrack.
Reusable prompt structure
Subject + ordered action + environment + camera + lighting + visual style + timing + dialogue and sound + consistency constraints
Example Seedance 2.0 prompt
“Image 1 is the dancer, Image 2 is the costume, Video 1 sets the orbiting camera and Audio 1 sets the tempo. Make a 12-second dance film: a still close-up, a sharp spin onto a sunlit rooftop, and a last wide pose against the skyline. Keep the same face and costume from start to finish.”
Give each reference a job
Say which picture sets the character, which clip sets the movement and which sound file sets the tempo or the voice.
Write in timed beats
Split a long request into an opening, a build, a transition and a closing image so the sequence can be planned.
Keep constants apart from changes
Name plainly what must stay the same and what may change, travel or develop as the clip plays.
Seedance 2.0 modes, references, and output options
Choose a tier and format based on where you are in the creative process. Draft settings are for finding the shot; premium settings are for finishing a direction that already works.
| Capability | Seedance 2.0 support |
|---|---|
| Variants | Standard, Fast and Mini |
| Generation modes | Text, image, frames, multi-reference, video to video, editing and extension |
| Inputs | A text brief, up to 9 images, up to 3 clips and up to 3 audio files |
| Reference control | Stills, footage, sound files, scripts or storyboards |
| Duration | 4–15 seconds |
| Resolution | 480p, 720p, 1080p and as high as 4K |
| Aspect ratios | Wide, tall, square and portrait frames, 21:9, or adaptive |
| Audio | Native stereo speech, music, ambience and effects |
4–15 seconds480p, 720p, 1080p and as high as 4KNative stereo speech, music, ambience and effects
Plan around the limits of generative video
AI video is most reliable when the prompt gives each shot one readable visual idea. Review important details before publishing and treat the first generation as a directed take that can be refined.
Complex multi-character interaction, fast occlusion, readable text, logos, hands, and exact object counts can still vary between takes. Use clear references, simplify crowded action, and inspect continuity frame by frame.
Higher resolution does not replace art direction. Lock the story beat, composition, movement, and sound at an economical setting first; then move the strongest direction to the premium variant or resolution.
Seedance 2.0 AI video generator FAQ
What is Seedance 2.0?
Seedance 2.0 is a ByteDance AI video generation model. Seedance 2.0 runs on one multimodal architecture for sound and picture together. A single project can join a written brief to still references, movement samples, sound cues and recorded voices, with the prompt giving each file its own job. It shines when a scene needs more than one starting image. MuseGen places the complete generator on this page so you can move from research to creation without opening a separate workspace.
Which generation modes does Seedance 2.0 support?
Seedance 2.0 supports Text, image, frames, multi-reference, video to video, editing and extension. That range lets you start with a written idea, guide the opening with an image, or use additional references when the composition, identity, or motion must be more controlled.
How long and what resolution can Seedance 2.0 generate?
You can create 4–15 seconds video with output at 480p, 720p, 1080p and as high as 4K. Pick a lower resolution for quick creative exploration, then use the highest appropriate setting when you are ready to evaluate detail or deliver the shot.
Can Seedance 2.0 generate audio?
Seedance 2.0 supports Native stereo speech, music, ambience and effects. Write dialogue, ambience, music, and effects as deliberate parts of the prompt so the soundtrack supports the visible action and emotional rhythm of the scene.
What can I upload to the Seedance 2.0 AI video generator?
The model accepts A text brief, up to 9 images, up to 3 clips and up to 3 audio files. Its reference workflow supports Stills, footage, sound files, scripts or storyboards. Give every uploaded asset a clear role in the prompt instead of expecting the model to infer which image controls identity, style, composition, or movement.
Who should use Seedance 2.0?
Seedance 2.0 is a strong fit for commercial directors, agencies, e-commerce teams, musicians, game developers and story-driven filmmakers. The best choice still depends on the shot: use this page's facts, features, examples, and prompt guide to decide whether its particular balance of control, speed, resolution, sound, and references matches the job.
How do I write a better Seedance 2.0 prompt?
A reliable prompt names the subject, action, location, camera, lighting, visual style, timing, and sound. Put events in chronological order, quote exact dialogue, and state what must remain consistent. When you upload references, identify each one explicitly.
Can I use Seedance 2.0 directly on this page?
Yes. The full Seedance 2.0 generator is embedded directly below the hero on this page. Choose text, image, frames, or references as appropriate, configure the available controls, review the visible credit cost, and start the generation without leaving the model guide.
Official Seedance 2.0 sources
Model capabilities and media on this page were researched from the developer's official product pages, announcements, and documentation.
Create your next video with Seedance 2.0
Open the complete Seedance 2.0 AI video generator above, add your prompt or references, and turn the next shot on your list into a finished video.
Start generatingBrowse all models