Timeline defaults to 1080x1920: join 16:9 AI clips without a crop
Timeline 1.0 renders 1080 by 1920 by default and fits slots with cover. For 16:9 Seedance, Wan or H3 clips, set output width and height and fit.

Timeline 1.0 renders a vertical 1080 by 1920 MP4 by default, and each slot's fit defaults to cover, so 16:9 clips from seedance-2.5, wan-3.0 or minimax-h3 are scaled up and cropped to fill a vertical frame. To keep them landscape, set output.width to 1920 and output.height to 1080, or pick fit: "contain" to keep the whole picture with bars.
Defaults and ranges come from Sume's Timeline 1.0 docs, read 2026-10-02; clip aspect ratios from the Video Router docs.
What are the defaults and the safe overrides?
Width and height must be even integers from 256 to 2160, so 1920 by 1080 is allowed. If you omit output.fps, Timeline renders at the rate the sources run at, and a differing rate is met by repeating or dropping frames, which shows as judder.
| Field | Default | Allowed |
|---|---|---|
output.width, output.height | 1080 by 1920 | Even integers, 256-2160 |
video[].fit | cover | cover, contain, stretch, blur |
output.fps | Matches the sources | 24, 25, 30, 60 |
video[].transition | None | fade, wipeleft, wiperight, slideup, slidedown, dissolve |
When do I pick contain or blur?
Use cover when the frame should be full and a crop is acceptable. Use contain when nothing may be cut, such as a product label at the edge. Use blur to put a 16:9 clip in a vertical frame with a blurred fill instead of bars. stretch distorts the picture and is rarely right.
A vertical 9:16 generation avoids all of this. Request aspect_ratio: "9:16" from the model and keep Timeline's default.
What else trips up a first join?
Inputs must be your workspace's media.sume.com artifacts; a generated clip's result URL qualifies, and off-host URLs are rejected at admit. video[0].start must be 0 and later starts must increase. Run POST /v1/timeline-1.0/plan first: it is unbilled and returns the duration and estimated cost without creating a job.
Timeline's public rate is $0.10 per ceil output minute, to confirm live in GET /v1/catalog. For the frame-rate side see Wan 30 fps versus HappyHorse 24 fps.
Check the first render's warnings[] array. Soft warnings such as padded or looped short sources and a changed frame rate are not failures, but they tell you the join is not exactly what you declared, which is easier to fix before you render 20 clips.
Sources
Related posts
More in Media tools
- TikTok trending video transcripts via API: what summary_mode returns
Can you get a transcript with Sume's trending video search? summary_mode transcript returns metadata plus an unsupported warning. What to do for the words.
- Trim an AI clip first, or use source_in on the timeline?
For a shot that is too long, set source_in and duration on the Timeline 1.0 slot. Use video_trim ($0.02 per job) only when another step needs a new MP4 file.
- Put a product shot above a UGC creator clip: compose stack
Timeline compose stacks one Sume-hosted still over one video into a single MP4. Set ratio for the still's share. The public rate is $0.02 per job.
- Veo upscaling on Vertex works on any video: Sume's 1.1x to 4x job
Google's Veo upscaling on Vertex AI is a private preview that takes any source video up to 4K. Sume's upscale job takes a public HTTPS video, 1.1x to 4x.
Written by Sume