Bytedance Seedance 2.0 Mini Video Edit API Documentation

Bytedance Seedance 2.0 Mini Video Edit API Documentation

Playground

Seedance 2.0 Mini Video Edit is ByteDance’s faster, lower-cost video editing model for prompt-guided video modification. It edits existing videos with cinematic multi-shot quality, AI camera control, consistent characters, 480P / 720P / 1080P / 4K output, 4-15s duration, and flexible aspect ratios. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

ByteDance Seedance 2.0 Mini Video Edit edits an existing video with a text prompt. Upload a source video, describe the edit you want, optionally add reference images or audio, and generate an edited video with selectable resolution, aspect ratio, and native audio settings.

• Need to generate from text instead? Try ByteDance Seedance 2.0 Mini Text-to-Video.
• Need to extend a video instead? Try ByteDance Seedance 2.0 Mini Video Extend.
• Need to generate from a start image instead? Try ByteDance Seedance 2.0 Mini Image-to-Video.

Why Choose This?

• Prompt-based video editing
  Edit an input video by describing the desired change in natural language.

• Reference-guided editing
  Use optional reference images to guide subject identity, style, or visual direction.

• Audio reference support
  Add optional reference audio to guide audio generation.

• Native audio generation
  Generate native audio for the edited output, or preserve the input video’s audio track when audio generation is disabled.

• Flexible aspect ratios
  Choose from 16:9, 9:16, 4:3, 3:4, 1:1, and 21:9, or let the output adapt to the input video.

• Resolution options
  Generate edited videos in 480p, 720p, 1080p, or 4k.

Parameters

How to Use

1. Write your edit prompt — Describe the edit you want to apply to the input video.
2. Upload the source video — Provide the video URL you want to edit.
3. Add references optional — Upload reference images or reference audio when you need extra visual or audio guidance.
4. Choose aspect ratio optional — Select an output aspect ratio, or leave it empty to adapt to the input video.
5. Choose resolution — Select 480p, 720p, 1080p, or 4k.
6. Set duration optional — Choose an output duration from 4 to 15 seconds, or leave it empty for auto-detection.
7. Configure audio optional — Keep generate_audio enabled for native audio generation, or disable it to preserve the input video’s audio track.
8. Submit — Generate the edited video.

Example Prompt

Change the scene into a cinematic rainy night atmosphere, with neon reflections on the street, soft camera motion, dramatic lighting, realistic color grading, and a polished film look.

Writing Effective Prompts

Editing keeps your source video and changes only what you name. Be precise about the scope, and describe the change as from A to B.

State the change plainly

Name exactly what to add, remove, or modify — and use an editing trigger word (add, remove, replace, change to, modify) so the intent is unambiguous.

• “Replace the man’s coffee cup with a book, keep everything else unchanged.”
• “Remove the subtitles.”
• “Change the background from a city street to a snowy forest.”

Use timestamps for partial edits

Confine a change to a time range so the rest of the clip is untouched.

• “From 4-6s, change the man’s action from drinking coffee to waving; leave the rest unchanged.”

Reference images for edits

Attach images to specify a replacement, and bind each explicitly (see below).

• “Replace the woman on the right with the person in @image1.”

Referencing uploaded assets

When you attach images, videos, or audio, bind each one explicitly in the prompt by its upload order — @image1, @video1, @audio1 — and say what it’s for. Don’t rely on labels drawn inside the image itself.

• “The knight in @image1 walks through the castle in @image2.”
• “Refer to @video1 for the camera movement only; keep its shot order.”
• “@image1 and @image2 are Character 1, voiced by @audio1.”

When a reference is already accurate, just point to it — no need to re-describe it in detail.

Audio edits

You can add, remove, or modify audio too.

• “Translate the dialogue to Spanish, keep lip movements matched, no subtitles.”
• “Remove the background music; keep only ambient and action sounds.”

Negative control

Positive descriptions work best, but you can suppress subtitles and audio:

• “No subtitles.”
• “No BGM — ambient and action sounds only.”
• “No audio.”

Weak vs. strong

Pricing

Price depends on selected resolution, input video duration, and output duration.

Rate per Counted Second

Example Costs: 5s Input Video + 5s Output Duration

Example Costs: 10s Input Video + 10s Output Duration

Example Costs: 15s Input Video + 15s Output Duration

Best Use Cases

• Video restyling — Change the visual style, lighting, mood, or atmosphere of an existing video.
• Prompt-guided edits — Apply natural-language editing instructions to a source video.
• Reference-based edits — Use reference images to guide identity, style, or visual consistency.
• Audio-aware editing — Generate native audio or preserve the original input audio depending on the workflow.
• Creative video iteration — Test multiple edit directions from the same source video.
• Short-form content editing — Create polished edited clips for social, ads, concepts, and creative production.

Pro Tips

• Use a clear source video with visible subjects and stable motion.
• Keep the prompt focused on the exact edit you want.
• Add reference images when subject identity or visual style needs stronger guidance.
• Add reference audio when audio direction matters.
• Use 480p for quick testing, 720p for standard output, 1080p for higher-resolution results, and 4k for maximum-resolution output.
• Disable generate_audio when you want to preserve the input video’s original audio track.

Related Models

• ByteDance Seedance 2.0 Mini Text-to-Video — Generate video directly from text prompts.
• ByteDance Seedance 2.0 Mini Video Extend — Continue an existing video with a new generated segment.
• ByteDance Seedance 2.0 Mini Image-to-Video — Generate video from a start image and prompt.

Notice: Use @image1, @image2, @audio1, etc. to reference your uploaded assets. The references will stay as plain text—don’t worry.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "enable_web_search": false,
  "generate_audio": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-2.0-mini/video-edit" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters