Landscaping yard transformation clip: Seedance 2.5 first+last frame
Send the muddy yard as first_frame and the finished lawn as last_frame to Seedance 2.5 on Sume: 8 seconds at 16:9 is $2.15 at 480p, $4.62 at 720p.

For a yard transformation, give seedance-2.5 the before photo as first_frame and the finished photo as last_frame. An 8-second 16:9 clip costs $2.15 at 480p, $4.62 at 720p and $11.37 at 1080p on Sume. Seedance 2.5 takes both frame types and 4 to 30 seconds (Video generation, read 2026-10-05).
What does the request look like?
Use two photos taken from the same spot and height. The model fills in the work between them, so a fixed camera position gives the bridge the least to invent.
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"seedance-2.5","prompt":"Time-lapse of a backyard being cleared and landscaped, fixed camera, daylight","duration":8,"resolution":"720p","aspect_ratio":"16:9","frame_images":[{"type":"image_url","image_url":{"url":"https://example.com/yard-before.jpg"},"frame_type":"first_frame"},{"type":"image_url","image_url":{"url":"https://example.com/yard-after.jpg"},"frame_type":"last_frame"}]}'What is the price by resolution?
The video-token count scales with pixels and seconds; 1080p also uses a higher token rate on Seedance 2.5, so the step from 720p to 1080p is larger than the step from 480p to 720p.
| Resolution | Video tokens | Price |
|---|---|---|
| 480p | 80,352 | $2.15 |
| 720p | 172,800 | $4.62 |
| 1080p | 388,800 | $11.37 |
How do I poll and download the result?
A submit returns 202 with id, polling_url, status and model. Poll GET /v1/videos/{id} until status is completed (the other terminal values are failed and cancelled), then download from GET /v1/videos/{id}/content?index=0 with the same bearer key. A 480p pass is a cheap way to check that the bridge between your two photos looks believable.
curl https://api.sume.com/v1/videos/JOB_ID -H "Authorization: Bearer $SUME_API_KEY"
curl -L "https://api.sume.com/v1/videos/JOB_ID/content?index=0" \
-H "Authorization: Bearer $SUME_API_KEY" --output clip.mp4Is it honest to show an AI transformation?
Label it as an illustration of the plan if the in-between frames are generated, and show the real finished photo next to it. The clip shows motion between your two photos; it is not footage of the work.
Sources
Related posts
More in Use cases
- Licensed voices only: what an ad team checks before take one
Microsoft says MAI-Voice-2 synthesizes only authorized, licensed voices. Here is the rights checklist to run for any AI voiceover, and what Sume's docs cover.
- LinkedIn Lead Gen Form hidden fields: tag each lead with its variant
A LinkedIn Lead Gen Form allows up to 20 hidden fields. Keep your own index-to-variant table from the Sume bulk queue so every lead traces to one creative.
- LinkedIn Lead Gen Form image 552x200: make it from a 3:1 render
LinkedIn recommends a 552px by 200px form image. Sume has no 552:200 ratio, so ask Ideogram for 3:1, center-crop about 8% of the width, and resize.
- LinkedIn video ad intro text 150 characters, headline 70: test copy
LinkedIn video ads show 150 characters of intro text and a 70-character headline. Test copy on one rendered clip and save Sume jobs for hook variants.
Written by Sume