falImage to videoComing soon

fal-ai/davinci-magihuman

fal-ai/davinci-magihuman 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

$0.065 per second. Billed on duration, default 5. 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 content.
image_url requiredURL or file—URL of the reference image for image-to-video generation.
audio_urlURL or file—Optional URL of the driving audio for lipsync mode. If omitted, audio is generated from the prompt.
durationnumber (whole)
1 to 30
5Duration of the generated video in seconds.
resolutionone of
256p, 540p, 720p, 1080p
256pOutput resolution. '256p' uses the official base-model 448x256 path. '1080p' uses the official base + 1080p super-resolution pipeline. '540p' and '720p' reuse that sharper 1080p SR path and downsample to the requested output size.
num_inference_stepsnumber (whole)
1 to 50
—Number of denoising steps. Defaults to 8 for 256p and 32 for 540p/720p/1080p (base + SR).
guidance_scalenumber
0 to 20
5Classifier-free guidance scale.
seednumber (whole)—Random seed for reproducibility.

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/davinci-magihuman",
    "input": {
      "prompt": "A woman is walking through a metro station and says, '\''I love walking through this station, it always feels so alive.'\''",
      "image_url": "https://v3b.fal.media/files/b/0a93a275/W1Nnkr552fPfcTuE2UgKL_Zmt1dxWICl_oX5nbuMVLQ.jpeg"
    }
  }'