Ugly Christmas sweater party invite: card over a clip, $0.02
Float your invite card over 8 seconds of last year's party footage with timeline compose overlay: $0.02 flat, 9:16 by default, card keeps its shape.

To make an ugly Christmas sweater party invite video, design the invite as a still (date, address, prize for the worst sweater), then use timeline compose with the overlay operation to float that card over a few seconds of last year's party footage. Compose is $0.02 flat per job and the default output is a 1080 by 1920 MP4, which suits a story or Reel. The card keeps its own aspect ratio and the video plays behind it.
What does overlay change compared with stack?
Stack splits the frame into two regions. Overlay keeps the video full-frame and places a plate on top of it. Three layout keys control that plate: position (top, center or bottom), width_ratio (0.05 to 1 of the frame width, default 0.9) and margin_ratio (0 to 0.45 of the height, default 0.05). The plate keeps its aspect, so a tall card stays tall instead of stretching. Mixing the stack keys (split, image_region, ratio) with overlay keys returns a 400.
What does the request look like?
Send operation overlay, image.url, video.url and your layout. Both files must already be your workspace's media.sume.com artifacts or assets. video.duration sets the length, up to 300 seconds, and the card stays up for the whole clip.
{
"operation": "overlay",
"image": { "url": "https://media.sume.com/artifacts/artf_demo/sweater-invite.png" },
"video": {
"url": "https://media.sume.com/artifacts/artf_demo/party-clip.mp4",
"duration": 8
},
"layout": { "position": "bottom", "width_ratio": 0.9, "margin_ratio": 0.05 },
"output": { "width": 1080, "height": 1920 }
}What else can you add?
The compose result is one shot. To add a few seconds of a second clip or a music bed, put the compose output into a Timeline 1.0 video slot and keep rendering at $0.10 per output minute. To stay at two cents, skip the timeline and post the compose result as it is. If you want the date to also be a spoken line or captioned text, use video captions cues at $0.20 for a clip up to 60 seconds.
| Version | Jobs | Listed cost |
|---|---|---|
| Card over a party clip | 1 compose | $0.02 |
| Plus an 8 s cut of the footage | 1 trim, 1 compose | $0.04 |
| Plus burned date and RSVP line as cues | trim, compose, captions | $0.24 |
| Plus a Music Router bed in a timeline | trim, compose, music, timeline | $0.265 before captions |
What should the card contain?
Put the date, time and place on the still itself, because compose does not draw text. Keep the lower edge clear of platform buttons by using position top if you expect an interface bar at the bottom. Make the card for the frame you will post, since output width and height are set on the request.
Sources
Related posts
More in Use cases
- Voice actor or AI voice for a 30-second ad? What an API covers
Hire a voice actor or use AI text to speech for a 30-second ad: what Sume's TTS API does, what it cannot do, and the $0.315 audio bill for three takes.
- AI album cover generator: square art at 3000×3000
Generate square album art, then upscale: Apple recommends at least 3000×3000. On Sume, generate 2400×2400 and upscale it 1.25× to reach 3000×3000.
- AI avatar for online course videos: build and update lessons
Use an AI avatar as your online course instructor: one reusable avatar, a short talking video per section, captions, and one Timeline join per lesson.
- Talking avatar for PowerPoint presentations, slide by slide
Make a talking avatar presenter for PowerPoint: one Sume clip per slide, up to 60 seconds each, in 16:9 or 4:3 to match the slide, inserted as MP4.
Written by Sume