Seedance 2.0 API

About Seedance 2.0

ByteDance's Seedance 2.0 reference-to-video builds one shot from your own material: up to 9 images, 3 video clips and 3 audio tracks, with no first frame. Output is 4 to 15 seconds at 480p, 720p, 1080p or 4K, with native audio.

Call it with the model name bytedance/seedance-2.0/reference-to-video on POST /jobs/createTask, from 33 credits for a 5-second clip ($0.33). New accounts get 30 free credits to try it in the Playground first.

Introduction

Seedance 2.0 Reference-to-Video creates a new video using supplied images, clips or audio as creative guidance. Choose it when the subject, setting and movement come from different materials, rather than from one fixed opening frame.

ByteDance introduced the model in its February 12, 2026 launch article. Its multimodal reference capability lets a brief assign different jobs to different assets. On this endpoint, provide a prompt and at least an image or video reference; audio can supplement that visual material.

Choose the starting point for your Seedance 2.0 sequence

Key features

Multimodal creative direction

Seedance 2.0 brings text, images, video and audio into one creative process. References can guide a character's appearance, a scene's composition, movement, camera language or sound, rather than serving only as pictures to animate.

Complex motion and interaction

The model is designed to handle sequences involving several subjects, connected actions and interaction with the environment. Its motion modeling covers both larger movements and smaller details such as gestures, facial expressions and moving fabric.

Audio and video generated together

Speech, environmental sound, effects and music can be generated alongside the picture. This joint approach lets sound participate in the scene's rhythm instead of being treated solely as a separate editing step.

Storytelling and camera control

Natural-language direction can describe a sequence of shots, changes in viewpoint and the progression of a performance. The model family also supports video editing and continuation; those operations require a compatible video-input workflow, not text-only or first-frame generation.

Request parameters

Pricing

Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.

Each task is rounded up to whole credits, so one run at the lowest tier costs 33 credits for a 5-second clip ($0.33).

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

Place a character in a new setting

Use an authorized character image and a separate location reference. Describe one action connecting them, then check the subject's appearance, relative scale and contact with the environment.

Borrow a camera move for a different subject

Provide a motion clip and a subject image. Specify that only the camera movement should carry over, not the original clip's people or background. Review framing and movement separately from appearance.

Build a scene around a visual and sound brief

Combine a workshop image with an authorized sound reference and a written action. Check that the audio supports the scene rather than replacing its intended mood or introducing an unwanted speaker.

Prompt guide & pro tips

How to assign roles to Seedance 2.0 references

Start by saying what to borrow from each asset. A reference can supply a subject, setting, camera movement or sound; it should not have to supply all of them at once.

1. Put the subject image and location image in reference_image_urls.
2. Put the camera reference in reference_video_urls.
3. Match the prompt labels to upload order: image 1, image 2, video 1.
4. Define a stable name for the subject, then describe the shots.

This example uses a courier portrait, a courtyard image and a camera-movement clip:

Define the person in the orange jacket in image 1 as the Courier.
Use image 2 for the courtyard and morning light.
Borrow only the slow sideways camera track from video 1, not its people or location.

Shot 1: Medium shot. The Courier walks through the courtyard carrying a small parcel.
Shot 2: The Courier stops beside the wooden door and knocks twice.
Shot 3: Close-up. The Courier looks toward the opening door and gives a small smile.

Keep the Courier's jacket and parcel consistent.
Sound: footsteps, two knocks and quiet courtyard ambience. No music or captions.

Keep character references unambiguous

If appearance drifts, separate the face reference from the full-body or clothing reference and say which supplies which detail. Reuse the same subject name throughout the prompt. Avoid putting several views of the same person into a collage that could be interpreted as several people.

Choose assets by role rather than filling every upload slot. Remove redundant references or resolve competing styles before adding more material.

Distinguish referencing from editing

“Borrow the camera movement from video 1” asks for a new scene. “Edit video 1” asks to modify that footage. Use the wording that matches the intended operation; do not mix editing or extension instructions into a new-scene reference brief.

Plan the shots, then the sound

Use numbered shots rather than exact timestamps for Seedance 2.0. If adding an audio reference, identify whether it supplies voice, ambience or musical character, and keep a visual reference in the request: this endpoint does not accept an audio-only brief.

API quick start

Call the Seedance 2.0 API in three steps

1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
2. Send the request. POST /jobs/createTask with model bytedance/seedance-2.0/reference-to-video and an input object that follows the parameter table. The response returns a task ID straight away.
3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.

# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "bytedance/seedance-2.0/reference-to-video",
  "input": {
    "prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
    "reference_image_urls": [
      "https://media.popnow.ai/influencer/examples/ava.webp"
    ],
    "aspect_ratio": "adaptive",
    "resolution": "720p",
    "duration_seconds": 5,
    "generate_audio": true
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

Seedance 2.0 API questions

All Seedance models

Seedance 2.5 runs single takes up to 30 seconds; Seedance 2.0 goes up to 4K but stops at 15 seconds.

• Seedance 2.5 APIByteDance's newest: 30-second clips with native audioFrom 56 credits for a 5-second clip
• Seedance 2.0 Mini APILightweight Seedance for quick 720p drafts with soundFrom 9 credits for a 5-second clip
• Seedance 2.0 APICinematic clips up to 4K with native audioFrom 33 credits for a 5-second clip
• Seedance 2.0 Fast APIFaster Seedance 2.0 with sound at 720pFrom 17 credits for a 5-second clip
• Seedance 1.5 Pro APINative-audio clips with an optional locked cameraFrom 9 credits for a 5-second clip

Other video APIs

• MiniMax H3 APIExpressive clips with audio, up to 2KFrom 28 credits for a 5-second clip
• Kling 3.0 API4K clips, multi-shot cuts and motion controlFrom 51 credits for a 5-second clip
• Vidu Q4 Preview APIUp to 4K clips with sound and spoken dialogueFrom 34 credits for a 5-second clip
• Wan 3.0 APIUp to 30-second clips with synced audioFrom 34 credits for a 5-second clip
• Kling O3 APIKling’s unified model: create, animate, reference and edit up to 4KFrom 51 credits for a 5-second clip
• MiniMax H3 Max APIFast clips with ambience, effects and musicFrom 38 credits for a 5-second clip

More about Seedance 2.0

Try it

Seedance 2.0 AI Video Generator onlineCreate videos with Seedance 2.0 in PopNow

Compare

Seedance 2.0 vs Seedance 2.5

Docs

Seedance 2.0 model ID and input schema in the API docsPopNow API quickstart: your first request in five minutesImage to video guide for the PopNow APIWebhooks: get Seedance 2.0 results without polling