Sign inGet started
falImage to videoComing soon

fal-ai/wan/v2.7/reference-to-video

fal-ai/wan/v2.7/reference-to-video is an image 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

duration: 2 $0.26, 3 $0.39, 4 $0.52, 5 (default) $0.65, 6 $0.78, 7 $0.91, 8 $1.04, 9 $1.17, 10 $1.30, otherwise $1.30 per run. The final charge comes from usage.

Limits

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

Input

FieldKindDefaultDescription
prompt requiredtext—Text prompt describing the desired video. Max 5000 characters.
reference_image_urlsURLs or files—Reference image URLs for character/object appearance. Pass multiple images for multi-subject generation. Max 20 MB each.
reference_video_urlsURLs or files—Reference video URLs for character/object appearance and motion. Pass multiple videos for multi-subject generation. Max 100 MB each.
negative_prompttext—Content to avoid in the video. Max 500 characters.
aspect_ratioone of
16:9, 9:16, 1:1, 4:3, 3:4
16:9Aspect ratio of the generated video.
resolutionone of
720p, 1080p
1080pOutput video resolution tier.
durationone of
2, 3, 4, 5, 6, 7, 8, 9, 10
5Output video duration in seconds (2-10).
multi_shotstrue or falsefalseWhen true, enables intelligent multi-shot segmentation. When false (default), generates a single continuous shot.
seednumber (whole)—Random seed for reproducibility (0-2147483647).

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/v2.7/reference-to-video",
    "input": {
      "prompt": "A person walking through a beautiful garden, cinematic style."
    }
  }'