falVideo to videoComing soon

fal-ai/bernini-r/reference-edit-video

Name: fal-ai/bernini-r/reference-edit-video
Brand: fal

fal-ai/bernini-r/reference-edit-video 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	—	Text prompt or editing instruction.
`negative_prompt`	text	—	Negative prompt. Defaults to the standard Wan2.2 negative prompt.
`num_inference_steps`	number (whole) 1 to 50	30	Number of denoising steps.
`max_image_size`	number (whole) 256 to 1280	848	Long-edge size (px). Sets the output size for generation tasks and caps source/reference media for editing tasks.
`seed`	number (whole)	—	Seed for reproducibility. Random when omitted.
`enable_prompt_expansion`	true or false	false	Rewrite the prompt with an LLM before generation. The model is tuned on enhanced prompts; off by default.
`num_frames`	number (whole) 5 to 121	81	Number of frames. Snapped internally to 4k+1.
`frames_per_second`	number (whole) 4 to 30	16	Output frames per second.
`acceleration`	one of none, regular	none	Acceleration level. 'regular' enables MagCache step-skipping for faster generation at a small quality cost; 'none' (default) runs the full denoising schedule.
`video_url` required	URL or file	—	Source video to edit.
`reference_image_urls` required	URLs or files	—	Reference image(s) guiding the edit; up to 5.

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/bernini-r/reference-edit-video",
    "input": {
      "prompt": "A cute corgi leaping in a sunny park, Van Gogh oil-painting style.",
      "video_url": "https://storage.googleapis.com/falserverless/example_inputs/seedance_pro_i2v.mp4",
      "reference_image_urls": [
        "<reference_image_urls>"
      ]
    }
  }'