Bytedance Seedance 2.0 Video Edit

Bytedance Seedance 2.0 Video Edit

Playground

Seedance 2.0 (Video-Edit) edits an input video from a natural-language prompt. The reference video drives subject identity, composition, and motion while the model rewrites lighting, style, weather, environment, or specific elements as instructed. Built on ByteDance Seed’s unified multimodal architecture for cinematic, motion-stable output.

Features

Seedance 2.0 Video-Edit

Seedance 2.0 Video-Edit transforms an input video from a natural-language prompt — change lighting, weather, style, environment, or specific elements while preserving the subject identity, composition, and motion of the original. Built on ByteDance Seed’s unified multimodal architecture for cinematic, motion-stable output.

Key Features

• Conversational video editing — Describe the change in plain language; the model rewrites the scene while keeping the original motion intact.
• Subject and motion preservation — Faces, objects, and camera movement from the input video stay consistent through the edit.
• Multi-reference support — Optionally guide style, character identity, or audio with reference images and audio clips.
• Native audio synchronization — Generates synchronized audio in a single pass.
• Cinematic output quality — Director-level lighting, framing, and motion stability inherited from Seedance 2.0.

Parameters

How to Use

1. Upload the input video. Anything longer than 15 s is trimmed to the first 15 s automatically.
2. Write the edit prompt. Describe the change you want — the prefix Edit the input video. is added for you.
3. (Optional) Add references. Reference images can constrain style or identity; reference audio can constrain the soundtrack.
4. (Optional) Set a duration. Auto-detected from the input video length if not provided.
5. Run. Receive the edited video with synchronized audio.

Pricing

Billed per second across input duration + output duration. Input duration is capped at 15 s.

Examples (input 5 s, output 5 s = 10 billed seconds):

Examples (input 12 s, output 12 s = 24 billed seconds):

Best Use Cases

• Style and look transfer — Re-grade footage into a cinematic, vintage, animated, or stylized look.
• Lighting and weather edits — Change time of day, add rain or snow, swap golden hour for blue hour.
• Object or background swaps — Replace clothing, props, or environments while keeping motion intact.
• Marketing variants — Generate quick variations of an existing ad clip without reshooting.

Pro Tips

• Be specific about what should change and what should stay the same.
• Mention lighting, mood, color palette, and camera intent for stronger output.
• Use reference images when you need to lock in a particular character or style.
• Trim your source video to the most relevant 4-15 s before uploading for the strongest edits.

Notes

• Inputs longer than 15 s are trimmed to 15 s before editing — billing reflects the trimmed length.
• Auto-detected duration matches the input length (rounded up), clamped to the 4-15 s range.
• Native audio generation is included.

Related Models

• Seedance 2.0 Image-to-Video — Generate video from a reference image and prompt.
• Seedance 2.0 Text-to-Video — Generate video from a text prompt.
• Seedance 2.0 Fast Video-Edit — Faster, cheaper variant of this model.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-2.0/video-edit" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "resolution": "720p",
    "enable_web_search": false
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"