← All models
Reframe entire videos scene-by-scene using Wan VACE 2.1
Example
Details
- Accepts
- video
Pricing
- Price
- 10 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | Random seed for reproducibility. If None, a random seed is chosen. |
| shift | number | Shift parameter for video generation. |
| prompt | string | The text prompt to guide video generation. Optional for reframing. |
| sampler | stringenum: unipc, dpm++, euler | Sampler to use for video generation. |
| sync_mode | boolean | If `True`, the media will be returned as a data URI and the output data won't be available in the request history. |
| video_urlrequired | string | URL to the source video file. This video will be used as a reference for the reframe task. |
| paste_back | boolean | Whether to paste back the reframed scene to the original video. |
| resolution | stringenum: auto, 240p, 360p, 480p, 580p, 720p | Resolution of the generated video. |
| zoom_factor | number | Zoom factor for the video. When this value is greater than 0, the video will be zoomed in by this factor (in relation to the canvas size,) cutting off the edges of the video. A value of 0 means no zoom. |
| acceleration | — | Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster. |
| aspect_ratio | stringenum: auto, 16:9, 1:1, 9:16 | Aspect ratio of the generated video. |
| trim_borders | boolean | Whether to trim borders from the video. |
| video_quality | stringenum: low, medium, high, maximum | The quality of the generated video. |
| guidance_scale | number | Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt. |
| negative_prompt | string | Negative prompt for video generation. |
| scene_threshold | number | Threshold for scene detection sensitivity (0-100). Lower values detect more scenes. |
| video_write_mode | stringenum: fast, balanced, small | The write mode of the generated video. |
| return_frames_zip | boolean | If true, also return a ZIP file containing all generated frames. |
| transparency_mode | stringenum: content_aware, white, black | The transparency mode to apply to the first and last frames. This controls how the transparent areas of the first and last frames are filled. |
| interpolator_model | stringenum: rife, film | The model to use for frame interpolation. Options are 'rife' or 'film'. |
| num_inference_steps | integer | Number of inference steps for sampling. Higher values give better quality but take longer. |
| enable_safety_checker | boolean | If set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked. |
| enable_auto_downsample | boolean | Whether to enable auto downsample. |
| auto_downsample_min_fps | number | Minimum FPS for auto downsample. |
Output
| Field | Type | Description |
|---|---|---|
| video | — | The output video file. |