fal-ai/scail-2

SCAIL-2 is an end-to-end character animation model that drives a reference character from a source video without relying on intermediate pose representations like skeleton maps.

Inference

Commercial use

Schema

LLMs

Playground API

Input

Prompt*

Type # to reference inputs.

Image Url*

Hint: Drag and drop image files from your computer, images from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: jpg, jpeg, png, webp, gif, avif

Video Url*

Hint: Drag and drop video files from your computer, video from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: mp4, mov, webm, m4v, gif

Mode

Subject Type

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Download

{
  "video": {
    "file_size": 1048576,
    "file_name": "output.mp4",
    "url": "https://storage.googleapis.com/falserverless/example_outputs/scail2-output.mp4",
    "content_type": "video/mp4"
  }
}

SCAIL-2 is billed per second of generated video at a flat rate of $0.20 per second, the same for both output resolutions (512p and 704p).

Generated video is always produced at 16 fps, so billed seconds = total output frames ÷ 16 — which is simply the duration of the output video in seconds.

How your cost is calculated:

Billed seconds = output duration (total frames ÷ 16 fps)
Cost = billed seconds × $0.20

Example — 5-second output: 5 × $0.20 = $1.00

Each request is capped at 10 seconds of video (160 frames at 16 fps), so the maximum cost per request is $2.00.

fal-ai/scail-2

Input

Result

What would you like to do next?

Logs