Before-after video for cleaning and organizing products, Q4
The Sume before-after Format builds a transformation video with matched framing and a clear reveal. Brief it with a real before photo and call it by API.
For a cleaning, organizing or restoring product, a before-and-after clip is the proof a shopper wants, and Sume has a Format for it. sume-before-after is described as creating a finished before-and-after video with matched identity, framing and lighting and a clear reveal. Start from a real photo of the "before" state, and let the clip show what your product does.
What does the Format do?
Read the live entry with GET /v1/formats/sume/sume-before-after first. It returns the description and the io profile that says what input the Format expects.
| Item | Value |
|---|---|
| Slug | sume-before-after, at the sume handle |
| Intended use | Beauty, styling, cleaning or product transformation, backed by evidence |
| Looks after | Matched identity, framing and lighting; a clear reveal |
| Not for | Static campaign deliverables |
How do I call it?
Send your real before photo in attachments and describe the transformation in instruction. Add generation_spend_cap_usd so a run cannot spend past your limit, and an Idempotency-Key so a retry does not start a second run. The result comes by webhook or by polling status_url, and primary_output_url is the finished clip on media.sume.com.
Runs that make video take minutes, so design for the asynchronous path. See Calling a Format for every field.
curl -sS -X POST "https://api.sume.com/v1/formats/sume/sume-before-after/runs" \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: oven-rack-before-after-v1" \
-d '{
"instruction": "9:16, about 10 seconds. Same angle and light before and after. The rack is cleaned with the spray. Clear reveal at the end.",
"attachments": [{ "type": "input_image", "image_url": "https://cdn.example.com/oven-rack-before.jpg" }],
"generation_spend_cap_usd": 15
}'What must stay honest?
A generated "after" is a picture, not a measured result. If the clip suggests a result your product does not deliver, it can mislead a shopper and break advertising rules. Test the product yourself, shoot a real after photo, and compare it with what the clip shows. If they differ, fix the instruction or use your own footage.
For a side-by-side cut of two real clips, Video filter can stack them for a flat $0.02 per encode.
Which Q4 products suit it?
The Format fits any product where the difference can be seen in one shot. Choose products where the change is visible and fast.
- Cleaning sprays, wipes and scrubs on a stained surface.
- Organizers on a messy drawer, shelf or desk.
- Restoring products such as leather balm or scuff erasers.
- Gift-wrapping kits, from loose items to a finished parcel.
How do I read the receipt?
The run returns a receipt with primary_output_url and artifacts. Open the clip, then check the first and last frame against your photos before it goes into an ad.
Related posts
More in Formats
- Sume Format output_error codes: which to retry and which to fix
output_extraction_failed is transient: re-read the run, then retry with a new key. output_schema_unsatisfied means the schema or recipe is wrong. Six codes.
- Sume Format run spend cap: 0 is rejected, null means $500
generation_spend_cap_usd on a Sume Format run: up to 500 is accepted, null uses the $500 maximum, 0 or above 500 returns 400. An unset Format defaults to $400.
- Team Format returns 403 workspace_key_required: which key to mint
A personal key on a team Format gets 403 workspace_key_required. details.workspace_id names the workspace. Create the key there. Other keys see 404.
- Ready-made Formats for product video: the Sume Format catalog
Sume ships ready-made Formats for product and UGC-style video and images, each callable from your backend with one HTTP request at the reserved sume handle.
Written by Sume