Open house invitation clip: MiniMax H3 Max, 8 seconds at 768p
A listing photo to an 8-second 16:9 open-house invitation with minimax-h3-max on Sume costs $0.80 at 768p, $0.50 at 480p and $1.60 at 1080p.

An 8-second 16:9 open-house clip from one listing photo is a minimax-h3-max job at $0.80 for 768p, $0.50 at 480p and $1.60 at 1080p on Sume. H3 Max accepts 5 to 15 seconds at 480p, 768p and 1080p (Video Router, read 2026-10-05).
What do I send?
Use the front-of-house photo as the first frame and ask for a slow, honest camera move. Put the date, time and address in an overlay on your own template, because the clip should not be the source of facts.
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"minimax-h3-max","prompt":"Slow push-in toward the front door, afternoon sun, gentle breeze in the trees","duration":8,"resolution":"768p","aspect_ratio":"16:9","frame_images":[{"type":"image_url","image_url":{"url":"https://example.com/listing-front.jpg"},"frame_type":"first_frame"}]}'What are the price steps?
Native renders are 480p and 768p. 1080p is a latent refinement from the 768p render and is priced higher per second than 768p.
| Length | 480p | 768p | 1080p |
|---|---|---|---|
| 5 seconds | $0.31 | $0.50 | $1.00 |
| 8 seconds | $0.50 | $0.80 | $1.60 |
| 12 seconds | $0.75 | $1.20 | $2.40 |
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. H3 Max makes stereo audio on every clip; trim or detach it if you do not want it.
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.mp4What do I check on a 1080p image-to-video clip?
Look at the first few frames of any 1080p image-to-video result before you use it, as covered in H3 Max 1080p latent refinement.
Sources
Related posts
More in Use cases
- Open house teaser: four Omni room clips, 360p drafts then 720p finals
A 40-second open-house teaser from four listing photos on Sume: image-to-video clips drafted at 360p, finished at 720p, joined on a timeline. Cost per pass.
- Orchestral music for a product reveal: build, hit, resolve brief
Brief a cinematic orchestral cue for a 20-second product reveal with Lyria 3.5 on Sume: section tags, a hit at 0:12, and fade-out settings. $0.125 per take.
- Pad an AI image to a white square for listings with ImageOps.pad
Marketplaces want square product images. Use ImageOps.pad on a Sume 4:5 or 3:2 image to add white bars without cropping the product, then save a JPEG.
- Paper abstract to a 30 s explainer: Wan 3.0 scenes, claims as captions
Turn a research abstract into a 30 s Wan 3.0 explainer on Sume without invented results: the model draws the scene, you type every claim as a caption.
Written by Sume