Kling 3 start-and-end-frame transitions: 6 clips for a slideshow

Seven photos need six morphs. Kling 3 Pro takes a first and a last frame: $0.70 per 5 s clip silent, $1.05 with sound, so $4.20 or $6.30. Request shape inside.

5 min readSume
All posts

A slideshow of seven photos has six gaps. If you fill each gap with a generated move between two stills, the picture never cuts; it travels. Kling 3 Pro in the Sume catalog is built for that job: it accepts a first_frame and a last_frame, 4 to 15 seconds, at 720p or 1080p, and 16:9, 9:16 or 1:1.

The price is the same at 720p and 1080p, because the catalog rate is per second with only an audio on/off split.

Cost of the six transitions

Sume catalog, read 2026-10-07. Kling Video v3 Pro list $0.112 (silent) and $0.168 (audio on) per second, x 1.25.
Clip lengthSilent, eachSilent, sixAudio on, eachAudio on, six
4 s$0.56$3.36$0.84$5.04
5 s$0.70$4.20$1.05$6.30
8 s$1.12$6.72$1.68$10.08
10 s$1.40$8.40$2.10$12.60

Send frame pairs

Each job takes photo n as first_frame and photo n+1 as last_frame. Both URLs must be public HTTPS. Keep the same aspect ratio across all seven photos; if one is off, crop it before you send, because the model fits the clip to aspect_ratio and does not re-frame for you.

The prompt describes the move between them, not the photos. Kling 3 does not accept reference images, so a prompt cannot point to a third picture.

{
  "model": "kling-3",
  "prompt": "Smooth push-in from the beach to the sunset terrace, same light",
  "duration": 5,
  "resolution": "1080p",
  "aspect_ratio": "9:16",
  "generate_audio": false,
  "frame_images": [
    {"type": "image_url", "image_url": {"url": "https://example.com/p1.jpg"}, "frame_type": "first_frame"},
    {"type": "image_url", "image_url": {"url": "https://example.com/p2.jpg"}, "frame_type": "last_frame"}
  ]
}

Where this beats the alternatives

Kling 3 is a medium-slow model on Sume's latency labels, so submit the six jobs in parallel and collect them with callback_url instead of waiting in a loop. If you only need a loop of one image, the same row takes the same photo as first and last frame. And if you want a longer single shot with synced sound, Omni Flash tops out at 10 seconds and has no square ratio, so Kling is the pick when you need 1:1 with an end frame.

Sources

Related posts

More in Use cases

All Use cases posts

Written by Sume