falVideo to videoComing soon

fal-ai/wan-vace-apps/long-reframe

Name: fal-ai/wan-vace-apps/long-reframe
Brand: fal

fal-ai/wan-vace-apps/long-reframe is a video to video tool from fal that runs in the background and returns video. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Priced by usage

Pricing

$0.104 per second. Measured from the input file. The final charge comes from usage.

Limits

Runs: In the background
Returns: video
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`prompt`	text		The text prompt to guide video generation. Optional for reframing.
`negative_prompt`	text	letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards	Negative prompt for video generation.
`seed`	number (whole)	—	Random seed for reproducibility. If None, a random seed is chosen.
`resolution`	one of auto, 240p, 360p, 480p, 580p, 720p	auto	Resolution of the generated video.
`aspect_ratio`	one of auto, 16:9, 1:1, 9:16	auto	Aspect ratio of the generated video.
`num_inference_steps`	number (whole) 2 to 50	30	Number of inference steps for sampling. Higher values give better quality but take longer.
`guidance_scale`	number 1 to 10	5	Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt.
`sampler`	one of unipc, dpm++, euler	unipc	Sampler to use for video generation.
`shift`	number 1 to 15	5	Shift parameter for video generation.
`video_url` required	URL or file	—	URL to the source video file. This video will be used as a reference for the reframe task.
`acceleration`	one of none, low, regular	regular	Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster.
`video_quality`	one of low, medium, high, maximum	high	The quality of the generated video.
`video_write_mode`	one of fast, balanced, small	balanced	The write mode of the generated video.
`enable_auto_downsample`	true or false	true	Whether to enable auto downsample.
`auto_downsample_min_fps`	number 1 to 60	6	Minimum FPS for auto downsample.
`interpolator_model`	one of rife, film	film	The model to use for frame interpolation. Options are 'rife' or 'film'.
`transparency_mode`	one of content_aware, white, black	content_aware	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.
`return_frames_zip`	true or false	false	If true, also return a ZIP file containing all generated frames.
`zoom_factor`	number 0 to 0.9	0	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.
`trim_borders`	true or false	true	Whether to trim borders from the video.
`scene_threshold`	number 0 to 100	30	Threshold for scene detection sensitivity (0-100). Lower values detect more scenes.
`paste_back`	true or false	true	Whether to paste back the reframed scene to the original video.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/wan-vace-apps/long-reframe",
    "input": {
      "video_url": "https://storage.googleapis.com/falserverless/web-examples/wan/t2v.mp4"
    }
  }'