Kling Motion Control character_orientation: video or image?
Pick 'video' (the default) for complex motion up to 30 s; 'image' follows camera movement but fal documents a 10 s limit. Sume bills $0.1575 per second.

Use character_orientation: "video", the Sume default, when the reference motion is complex or long. Use "image" when you want the character to keep the orientation of your still and follow camera movement. fal's page documents video for clips up to 30 seconds and image up to 10 seconds, so the choice also caps your motion video length.
The two values
Sume's Kling 3.0 Motion Control route is POST /v1/kling/3.0/motion-control. The options and what the fal page says about each are below.
| Value | fal description (read 2026-10-05) | Length limit on fal |
|---|---|---|
video (Sume default) | Character pose direction aligns with the reference video; better for complex motions | Up to 30 seconds |
image | Character orientation matches the reference image; better for following camera movements | Up to 10 seconds |
Other fields
The other body fields are image_url or an avatar id/handle (exactly one), motion_video_url (required, it drives all output motion), duration_seconds (1-30, required) and keep_original_sound (default true; false gives a silent clip).
duration_seconds is the reservation basis only. Sume never forwards it, because the length of the motion video sets the output length.
Price
The price is ceil(duration_seconds) x $0.126 (fal list) x 1.25 = $0.1575 per second. A 5 s clip reserves 5 x $0.1575 = $0.7875 and a 30 s clip 30 x $0.1575 = $4.725, before any rounding of the final amount.
Example body
A request using image orientation. Keep the motion video within 10 s.
{
"image_url": "https://example.com/character.png",
"motion_video_url": "https://example.com/dance-8s.mp4",
"duration_seconds": 8,
"character_orientation": "image",
"keep_original_sound": true
}Sources
Related posts
More in Media tools
- Lip-sync a saved avatar with H3 Max: avatar_handle, not image_url
Use a ready Sume avatar as the face for MiniMax H3 Max Lip Sync: send avatar_handle plus Sume-hosted audio, 5-14.8 seconds, and see the price at 768p.
- Put a logo or lower third over a talking avatar video with compose
Timeline compose overlay places a Sume-hosted still over an avatar clip, at the top, center or bottom. $0.02 flat per job. The layout keys and a request.
- Use a MAI-Voice-2.1 clip as avatar audio? Sume needs its own file
A talking still on Sume takes Sume-hosted audio under 10 MB. A MAI-Voice-2.1 clip sits elsewhere, so make the line with Sume TTS instead. Sizes and limits.
- Match voice emotion and music mood: one mood word, two Sume fields
Set generation_config.emotion on TTS and the emotion axis in the Music prompt from the same mood word, so a short's voice and bed do not argue.
Written by Sume