GET
/v1/schemas/fal/video/fal-ai/wan-22-vace-fun-a14b/reframe
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above.Source trace77fa563c41eab9270ae944bb7b8c3d278aa8bad935c12c72e28c54179a62c30c{
"fetchedAt": 1786338105,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
31 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| video_url* | string | URL to the source video file. This video will be used as a reference for the reframe task. | |
| 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. | 0 ≤ n ≤ 0.9 · default: 0 |
| match_input_frames_per_second | boolean | If true, the frames per second of the generated video will match the input video. If false, the frames per second will be determined by the frames_per_second parameter. | default: true |
| negative_prompt | string | Negative prompt for video generation. | default: "letterboxing, borders, black ba… |
| enable_auto_downsample | boolean | If true, the model will automatically temporally downsample the video to an appropriate frame length for the model, then will interpolate it back to the original frame length. | default: false |
| first_frame_url | string | URL to the first frame of the video. If provided, the model will use this frame as a reference. | nullable |
| resolution | enum | Resolution of the generated video. | auto | 240p | 360p | 480p | 580p | 720p · default: "auto" |
| match_input_num_frames | boolean | If true, the number of frames in the generated video will match the number of frames in the input video. If false, the number of frames will be determined by the num_frames parameter. | default: true |
| video_write_mode | enum | The write mode of the generated video. | fast | balanced | small · default: "balanced" |
| enable_safety_checker | boolean | If set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked. | default: false |
| last_frame_url | string | URL to the last frame of the video. If provided, the model will use this frame as a reference. | nullable |
| trim_borders | boolean | Whether to trim borders from the video. | default: true |
| auto_downsample_min_fps | number | The minimum frames per second to downsample the video to. This is used to help determine the auto downsample factor to try and find the lowest detail-preserving downsample factor. The default value is appropriate for most videos, if you are using a video with … | 1 ≤ n ≤ 60 · default: 15 |
| enable_prompt_expansion | boolean | Whether to enable prompt expansion. | default: false |
| shift | number | Shift parameter for video generation. | 1 ≤ n ≤ 15 · default: 5 |
| num_inference_steps | integer | Number of inference steps for sampling. Higher values give better quality but take longer. | 2 ≤ n ≤ 50 · default: 30 |
| guidance_scale | number | Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt. | 1 ≤ n ≤ 10 · default: 5 |
| aspect_ratio | enum | Aspect ratio of the generated video. | auto | 16:9 | 1:1 | 9:16 · default: "auto" |
| transparency_mode | enum | 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. | content_aware | white | black · default: "content_aware" |
| sampler | enum | Sampler to use for video generation. | unipc | dpm++ | euler · default: "unipc" |
| frames_per_second | integer | Frames per second of the generated video. Must be between 5 to 30. Ignored if match_input_frames_per_second is true. | 5 ≤ n ≤ 30 · nullable |
| 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. | default: false |
| interpolator_model | enum | The model to use for frame interpolation. Options are 'rife' or 'film'. | rife | film · default: "film" |
| acceleration | enum | Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster. | none | low | regular · nullable |
| seed | integer | Random seed for reproducibility. If None, a random seed is chosen. | nullable |
| temporal_downsample_factor | integer | Temporal downsample factor for the video. This is an integer value that determines how many frames to skip in the video. A value of 0 means no downsampling. For each downsample factor, one upsample factor will automatically be applied. | 0 ≤ n ≤ 5 · default: 0 |
| num_frames | integer | Number of frames to generate. Must be between 81 to 241 (inclusive). | 17 ≤ n ≤ 241 · default: 81 |
| return_frames_zip | boolean | If true, also return a ZIP file containing all generated frames. | default: false |
| prompt | string | The text prompt to guide video generation. Optional for reframing. | default: "" |
| num_interpolated_frames | integer | Number of frames to interpolate between the original frames. A value of 0 means no interpolation. | 0 ≤ n ≤ 5 · default: 0 |
| video_quality | enum | The quality of the generated video. | low | medium | high | maximum · default: "high" |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/wan-22-vace-fun-a14b/reframe","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}