Seedance 2 Video Edit: AI Video Editor
SD 2.0 Video Edit modifies existing videos based on text prompts and optional reference images.
SD 2.0 Video Edit modifies existing videos based on text prompts and optional reference images.
About this model
SD 2.0 Video Edit is an advanced AI video modification tool from ByteDance. It unleashes multi-shot storytelling by allowing you to seamlessly edit and transform existing videos using natural language prompts. Whether you want to perform style transfers, change backgrounds, or modify specific elements within a scene, this model offers director-level control while maintaining original motion consistency and narrative structure.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | $0.60 base price | muapiapp brings ByteDance's cutting-edge video editing to you early, providing premium video-to-video manipulation starting around $0.60 per edit depending on duration and quality. |
| Competitors | Varies | Many standard APIs lack native video-to-video capabilities of this tier, making muapiapp an exclusive entry point to Hollywood-grade AI editing. |
muapiapp brings ByteDance's cutting-edge video editing to you early, providing premium video-to-video manipulation starting around $0.60 per edit depending on duration and quality.
Many standard APIs lack native video-to-video capabilities of this tier, making muapiapp an exclusive entry point to Hollywood-grade AI editing.
* Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | Text prompt describing the video edit. | Replace the running man with @image1. Preserve the exact running motion, speed, and camera shake. Ensure the armor glows dynamically with the environment lighting and reflects passing car lights. Maintain realistic foot contact with the ground and motion blur consistency. |
| Video URLs | array | Upload up to 1 video URL. (Max size: 10MB, Max duration: 15s) | https://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/seedance-v2.0-video-edit-in.avif |
| Image URLs | array | Upload up to 9 image URLs. | https://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/seedance-v2.0-video-edit.jpg |
| Audio Reference URLs | array | Up to 3 reference audio clip URLs (MP3/WAV, total max 15s). Each Nth audio corresponds to @audioN in the prompt. | undefined |
| Aspect Ratio | Enum (4 options) | - | 16:9 |
| Quality | Enum (2 options) | - | basic |
| Duration (seconds) | int | Output video duration in seconds (4–15). | 5 |
Text prompt describing the video edit.
Replace the running man with @image1. Preserve the exact running motion, speed, and camera shake. Ensure the armor glows dynamically with the environment lighting and reflects passing car lights. Maintain realistic foot contact with the ground and motion blur consistency.Upload up to 1 video URL. (Max size: 10MB, Max duration: 15s)
https://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/seedance-v2.0-video-edit-in.avifUpload up to 9 image URLs.
https://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/seedance-v2.0-video-edit.jpgUp to 3 reference audio clip URLs (MP3/WAV, total max 15s). Each Nth audio corresponds to @audioN in the prompt.
undefined-
16:9-
basicOutput video duration in seconds (4–15).
5Developer documentation
Upload Your Source Video: Provide a valid URL to the target video via the video_urls array (limit 1 video).
(Optional) Add Reference Images: Include up to 9 image URLs via images_list if you want the model to mimic a precise aesthetic, character, or object style during the edit.
Write Your Edit Prompt: Clearly describe what should happen in the video. If you are uploading reference images, use @image1, @image2 to guide the model (e.g., 'Transform the environment into the city from @image1').
Select Duration: Pick output video length (4–15s).
Select Quality Settings: Choose basic ($0.21/sec output + $0.063/sec per input video second) for faster, cost-effective rendering, or high ($0.30/sec output + $0.09/sec per input video second) for maximum visual fidelity. Input source video incurs a 30% surcharge based on its duration.
Submit Request: Once submitted, the model will output a seamlessly edited video matching your prompt.
Frequently asked
Currently, the SD 2.0 video edit model focuses strictly on visual transformations. Audio manipulation is generally handled independently.
For optimal results and to stay within API processing limits, it's recommended to provide source videos under 15 seconds.
'Basic' uses a faster rendering pipeline ideal for rapid prototyping, while 'high' utilizes the standard, deep-rendering pipeline for production-ready, cinematic quality.