Seedance 2.0 Reference-to-Video

seedance-2.0/reference-to-video

Seedance 2.0 Reference-to-Video creates a new 4–15 second clip from a prompt plus reference images, videos, and optional audio. Images guide appearance, videos guide motion and camera rhythm, and audio guides sound; at least one image or video is required, with 12 assets maximum.

Input

Prompt
97/20000
Reference images
0/9
Reference videos
0/3
Reference audio
0/3
Total references0/12
Resolution
Duration
Aspect ratio
Advanced

Generate audio

Ask the model to generate an audio track with the video.

Return last frame

Keep the video result and request the final frame as an additional file.

Web search

Send the optional web-assisted generation field.

Output

Idle

Your generated files will appear here

Set the inputs, choose a duration, then run the asynchronous video task.

5 sec × $0.200/sec = $1.000

Continue with

Examples

Use Reference Image 1 only for the copper humanoid robot's oval ivory faceplate, slim adult proportions, articulated copper plates, graphite joints, amber chest line, five-fingered hands, and flat feet. Use Reference Video 1 only for the three-beat choreography, weight shifts, timing, and waist-height semicircular camera path; do not copy the masked performer, indigo suit, ribbon, or black-box theater. Use Reference Audio 1 only for the three action beats and room-to-step timing; replace cloth sound with restrained servo movement. Create one continuous four-second shot on a vast white salt flat at sunrise. The robot performs the same low arc, single pivot, and raised spiral gesture using empty hands, then settles facing the camera. Preserve the referenced robot identity and construction throughout. Synchronized audio: three ceramic-metal foot contacts, quiet servos, and open-air wind. No cuts, no humans, no ribbon, no theater, no dialogue, no music, no readable text, no logos, no brands, no products, no advertising, no watermark.

Seedance 2.0 Reference-to-Video

Seedance 2.0 Reference-to-Video creates a new 4–15 second clip from a prompt plus reference images, videos, and optional audio. Images guide appearance, videos guide motion and camera rhythm, and audio guides sound; at least one image or video is required, with 12 assets maximum.

Why Choose This?

  • References have distinct jobs.Images, videos, and audio guide appearance, motion or camera, and sound or rhythm separately.

  • Full resolution range.Choose 480p, 720p, 1080p, or 4K according to the delivery target.

  • Continuous duration control.Select any whole-second duration from 4 through 15 instead of a short preset list.

  • Explicit advanced controls.Request audio, a returned last frame, web assistance, and an optional integer seed.

Parameters

ParameterRequirementDescription
promptRequired

Trimmed length 1–20,000; the Playground supplies a mode-specific example.

durationRequired

Any integer from 4 through 15 inclusive; Playground default 5.

resolutionRequired

480p, 720p, 1080p, 4k; Playground default 720p.

Default720p480p1080p4k
aspect_ratioOptional

auto, 21:9, 16:9, 4:3, 1:1, 3:4, or 9:16; Playground default 16:9.

Default16:99:161:121:94:33:4auto
reference_image_urlsConditional

Up to 9 public image URLs; an image or video is required.

reference_video_urlsConditional

Up to 3 public video URLs; each duration is floored separately and added to billed seconds.

reference_audio_urlsOptional

Up to 3 public audio URLs. Audio cannot stand alone; all reference assets total at most 12.

generate_audioOptional

Boolean. The Playground explicitly sends true by default.

Defaulttrue
return_last_frameOptional

Boolean. The Playground explicitly sends false by default.

Defaultfalse
web_searchOptional

Boolean. The Playground explicitly sends false by default.

Defaultfalse
seedOptional

Integer with no published range; omitted when empty.

How to Use

  1. Assign each referenceUse images for appearance, videos for motion or camera, and audio for sound or rhythm.

  2. Direct the movementUse concrete verbs and separate subject motion from camera motion.

  3. Set the outputChoose 480p, 720p, 1080p, 4k, a 4–15 second duration, and the applicable composition.

  4. Review advanced controlsConfirm audio, last-frame, web-assistance, and seed choices.

  5. Submit and trackRun the request, then poll the task ID or process its terminal callback.

Pricing

One credit equals $0.005. Without reference video, bill output duration. With video, add each separately floored reference duration and apply the with-video rate to every billed second.

UsageRateDetails
480p billing20 / 11.5 credits per billed second$0.100/s without reference video; $0.0575/billed second with reference video, including its duration.
720p billing40 / 25 credits per billed second$0.200/s without reference video; $0.125/billed second with reference video, including its duration.
1080p billing90 / 62 credits per billed second$0.450/s without reference video; $0.310/billed second with reference video, including its duration.
4k billing200 / 128 credits per billed second$1.000/s without reference video; $0.640/billed second with reference video, including its duration.

Best Use Cases

  • Character-guided shotsUse a character image for appearance and a video reference for motion guidance in a new shot.

  • Motion referenceUse a source video's action and camera rhythm to guide a new clip.

  • Brand visualsUse image references to retain a product, character, or visual language.

  • Rhythm-led clipsUse an audio reference to establish intended sound or beat.

Pro Tips

  • Order the prompt as subject and setting, action, camera, light and mood, then sound intent.
  • Name the job of each reference in the prompt so guidance does not conflict.
  • Use concrete motion verbs and separate subject movement from camera movement.
  • Choose composition before describing where the subject sits in frame.
  • When timing matters, describe an opening, development, and final beat.

Notes

  • Use at most 9 images, 3 videos, 3 audio files, and 12 references total; audio cannot stand alone.
  • resolution is required by the public OpenAPI, so examples and the Playground always send it explicitly.
  • _reference_video_billing_seconds is internal and must never appear in a frontend or API request.
  • Standard accepts 480p, 720p, 1080p, and 4K.
  • Tasks are asynchronous; poll only while status is not_started or running.

Frequently Asked Questions about Seedance 2.0 Reference-to-Video API

What is the Seedance 2.0 Reference-to-Video API?

Seedance 2.0 is a ByteDance Seedance model. This Reference-to-Video endpoint accepts a prompt plus image, video, and optional audio references, then returns an asynchronous video-generation task through the documented REST request contract.

How do I call the Seedance 2.0 Reference-to-Video API?

Send POST /api/generate/submit with Authorization: Bearer VIDGO_API_KEY. A successful response includes task_id for the unified status endpoint.

How much does the Seedance 2.0 Reference-to-Video API cost?

Without reference video, multiply output seconds by the without-video rate. With video, add every separately floored reference duration to output duration and multiply every billed second by the with-video rate. 480p: 20 credits ($0.100)/s; 720p: 40 credits ($0.200)/s; 1080p: 90 credits ($0.450)/s; 4k: 200 credits ($1.000)/s.

What inputs does the Seedance 2.0 Reference-to-Video API accept?

It accepts a prompt, up to 9 reference images, 3 videos, and 3 audio files, with 12 assets total. An image or video is required, and audio cannot stand alone.

How do I get the generated video?

Poll GET /api/generate/status/{task_id}, or submit callback_url. Continue only for not_started or running; read every data.files[].file_url after finished, and stop with the error after failed.

Which Seedance 2.0 endpoint should I choose?

Choose Text with no source asset, Image for a start or start/end frame, and Reference for image, video, or audio guidance. Standard offers resolutions through 4K; Fast is limited to 480p/720p at lower current rates.