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.

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
| Clip length | Silent, each | Silent, six | Audio on, each | Audio 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
- Kling motion control silent clip with a Lyria music bed for a Short
Set keep_original_sound to false, generate a track with the Music Router, and join them on a timeline. Cost for a 12-second clip, and the YouTube rule to know.
- Korean BBQ restaurant reel: korean-ad captions on spoken Hangul
Caption a restaurant reel with Korean speech using Sume's korean-ad style, language ko, and why slam or punch fails with Hangul. Request body and font choices.
- Landscape listing photos in a vertical reel: cover, contain or blur?
A 3:2 photo in a 9:16 reel shows only 37.5% of its width with fit cover. Pick the fit per photo in Timeline 1.0: eight photos and a bed cost $0.225 on Sume.
- Lip sync AI music video: split a song into 5 to 14.8 second windows
MiniMax H3 Max lip sync accepts 5 to 14.8 seconds of audio per clip. Split a 60-second song into five 12-second ranges: about $6.24 at 768p on Sume.
Written by Sume