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.

If you put landscape listing photos in a vertical reel with Timeline 1.0's default fit: cover, a 3:2 photo shows only 37.5% of its width in a 9:16 frame, so the sides of the room are cut off. Use cover for portrait photos and tight details, contain when the whole room must stay visible, and test blur on one slot. Eight photos at 3 seconds each, with a music bed, cost $0.225 on Sume: $0.125 for the music and $0.10 for the render.
Most listing photos are landscape and most reels are vertical, so every agent makes this trade whether they know it or not. Doing it on purpose, slot by slot, is what separates a reel that shows the house from one that shows the middle third of every room.
What cover removes
The default fit is cover: the photo is scaled until it fills the whole frame, and what does not fit is cut. The default output is 1080 by 1920. A 3:2 photo scaled to that height is 2,880 pixels wide, so only 1,080 of those pixels, 37.5% of the width, are visible. The table gives the visible share for common photo shapes and three common outputs.
That is fine for a doorknob or a kitchen tap. It is not fine for a living room where the window wall and the fireplace are at opposite sides of the photo.
| Photo shape | In 9:16 (1080x1920) | In 4:5 (1080x1350) | In 1:1 (1080x1080) |
|---|---|---|---|
| 3:2 | 37.5% | 53.3% | 66.7% |
| 4:3 | 42.2% | 60.0% | 75.0% |
| 16:9 | 31.6% | 45.0% | 56.2% |
Choose the fit per slot
fit is set on each video[] slot, so one render can mix them. Use cover for portrait photos and for detail shots where cropping is harmless. Use contain for establishing shots, floor plans and any photo with something important at both edges. With contain the whole photo stays in frame and the leftover area of the 1,080 by 1,920 canvas is filled by the renderer, so a 3:2 photo uses 37.5% of the frame height.
blur is the fourth value. Render a test with one blur slot before you commit a batch of listings, since a test render is $0.10, and decide by looking at it on a phone. stretch distorts the photo and is not a good idea for rooms with straight lines.
curl -X POST https://api.sume.com/v1/timeline-1.0/render \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: listing-reel-001" \
-d '{
"audio": { "url": "https://media.sume.com/artifacts/artf_demo/bed.mp3", "duration_seconds": 9 },
"video": [
{ "source_url": "https://media.sume.com/artifacts/artf_demo/front.jpg", "start": 0, "duration": 3, "fit": "contain" },
{ "source_url": "https://media.sume.com/artifacts/artf_demo/tap.jpg", "start": 3, "duration": 3, "fit": "cover",
"transition": { "type": "fade", "duration": 0.5 } },
{ "source_url": "https://media.sume.com/artifacts/artf_demo/den.jpg", "start": 6, "duration": 3, "fit": "contain",
"transition": { "type": "fade", "duration": 0.5 } }
]
}'Or change the output shape
A square or 4:5 output keeps far more of a landscape photo: a 3:2 photo shows 66.7% of its width in 1:1 and 53.3% in 4:5. Set output.width and output.height to even numbers between 256 and 2,160, such as 1080 by 1350. Feeds that accept 4:5 give a listing reel more height than 1:1 without the full crop of 9:16. Check each placement's accepted ratios before you pick one.
Stills are static holds on this surface. The job accepts a motion field and ignores it, and reports motion_ignored as a soft warning. If you want camera movement, make it a video clip first; do not expect the render to pan across a photo.
Cost and checks
- A longer reel of eight photos at 3 seconds is 24 seconds, still one started minute: the same $0.10 render.
- Slots must be at least 0.2 seconds, the first slot starts at 0, and a transition can be at most 1 second.
- Read
warnings[]on every result before you publish. - Do not alter the room: crop, order and time are fine, but a changed room needs a clear disclosure.
| Step | Unit | Price | This reel |
|---|---|---|---|
| Music Router bed | per track | $0.125 | $0.125 |
| Timeline 1.0 render | per started minute | $0.10 | $0.10 |
| Total | $0.225 |
Sources
Related posts
More in Use cases
- Live stream avatar: queue pre-rendered reaction clips instead
For a stream overlay, render ten short Sume avatar clips ahead of time and trigger them from chat events. Ten 6-second clips cost $14.70 on plus.
- Lock the look with one image, then animate it on three video models
Make one approved image, then use it as first_frame on wan-3.0, kling-3 and minimax-h3-max. Same start, three motions, one prompt, so you can compare.
- Meta Feed video ad spec checklist before uploading an AI clip
Meta's Facebook Feed video spec: 4:5, 1440 x 1800, up to 4 GB, MP4 or MOV, H.264 with AAC audio. A checklist, and the Sume Timeline output size that meets it.
- Meta Feed allows 1-second video ads: shortest Sume clip is 2 s
Meta's Feed spec allows video from 1 second. The shortest clip any Sume video model generates is 2 seconds (Wan 3.0). What to do for a 1-second cut test.
Written by Sume