falVideo to videoComing soon

fal-ai/wan-vace-14b/depth

Name: fal-ai/wan-vace-14b/depth
Brand: fal

fal-ai/wan-vace-14b/depth 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` required	text	—	The text prompt to guide video generation.
`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.
`match_input_num_frames`	true or false	false	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.
`num_frames`	number (whole) 17 to 241	81	Number of frames to generate. Must be between 81 to 241 (inclusive).
`match_input_frames_per_second`	true or false	false	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.
`frames_per_second`	number (whole) 5 to 30	16	Frames per second of the generated video. Must be between 5 to 30. Ignored if match_input_frames_per_second is true.
`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. Required for depth task.
`ref_image_urls`	list	—	URLs to source reference image. If provided, the model will use this image as reference.
`first_frame_url`	text	—	URL to the first frame of the video. If provided, the model will use this frame as a reference.
`last_frame_url`	text	—	URL to the last frame of the video. If provided, the model will use this frame as a reference.
`enable_prompt_expansion`	true or false	false	Whether to enable prompt expansion.
`preprocess`	true or false	false	Whether to preprocess the input video.
`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.
`num_interpolated_frames`	number (whole) 0 to 5	0	Number of frames to interpolate between the original frames. A value of 0 means no interpolation.
`temporal_downsample_factor`	number (whole) 0 to 5	0	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.
`enable_auto_downsample`	true or false	false	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.
`auto_downsample_min_fps`	number 1 to 60	15	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 very fast motion, you may need to increase this value. If your video has a very low amount of motion, you could decrease this value to allow for higher downsampling and thus longer sequences.
`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.

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-14b/depth",
    "input": {
      "prompt": "A confident woman strides toward the camera down a sun-drenched, empty street. Her vibrant summer dress, a flowing emerald green with delicate white floral…",
      "video_url": "https://storage.googleapis.com/falserverless/example_inputs/wan-vace-depth-video.mp4"
    }
  }'