Dental clinic intro reel: one 30 s Wan 3.0 job or three Kling 3 clips

A 30-second waiting-room-to-chair story costs $3.75 as one Wan 3.0 720p job, or $4.20 as two silent Kling 3 clips. Which one to pick and why.

5 min readSume
All posts

Make the intro as one Wan 3.0 job if the reel is a single continuous walk-through, and as separate Kling 3 clips if each shot has its own first frame. One 30-second Wan 3.0 clip at 720p is $3.75 on Sume. Two 15-second Kling 3 clips are $4.20 silent or $6.30 with sound, and Kling 3 cannot do 30 seconds in one request because its range is 4 to 15.

The decision

A dental intro usually runs reception, a hygienist greeting, the treatment room, then a smile at the door. That is one location path and one continuous camera. Wan 3.0 generates up to 30 seconds in a single pass, as both Alibaba's launch post and the Model Studio page, read 2026-10-08, state. A single pass means one continuity decision instead of three stitched ones.

If you have approved stills for each space, the opposite is better: use each still as a first frame in its own short clip, so the room matches your real clinic. Kling 3 takes a first frame, an optional end frame, and bills the same for 720p and 1080p.

Cost table, Sume prices

Sume bills provider list times 1.25, rounded up to the cent per job.

Thirty-second intro, three build options (rates read 2026-10-08)
BuildJobsSettingsBilled
Wan 3.0 single take1 x 30 s720p$3.75
Wan 3.0 single take, 1080p1 x 30 s1080p$7.50
Wan 3.0 draft1 x 30 s480p$1.88
Kling 3, silent2 x 15 s1080p$4.20
Kling 3, with sound2 x 15 s1080p$6.30
Kling 3, four shots4 x 7 s (28 s)1080p, silent$3.92

Practical notes for a health-care brand

Faces and clinical equipment are where generated video fails first. Draft at 480p for 30 seconds first and look at hands, instruments and any text on signage before you spend on the final. Alibaba says on-screen text accuracy is still improving, so overlay the clinic name and phone number as captions afterwards.

Do not generate a real dentist's likeness from a photo without that person's written consent. Use a generic presenter or a licensed avatar and say so in your page copy.

  • Pick Wan 3.0 when reception to exit is one continuous take.
  • Pick Kling 3 when you have a still per room and want 1080p for the same per-second price as 720p.
  • Pin the resolution on Wan 3.0, because an omitted resolution is priced at 1080p.

Submit it and read the result

Sume reserves the billable amount from your workspace USD balance when the job is submitted, then returns a polling_url. The 30-second draft at 480p is the cheapest way to check hands and equipment before the final. Poll the job until status is completed or failed; a completed job lists its files in unsigned_urls.

import os
import time
import requests

H = {"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"}
body = {
    "model": "wan-3.0",
    "prompt": "A slow push-in on the scene, soft natural light",
    "duration": 30,
    "resolution": "480p",
    "aspect_ratio": "16:9",
}
r = requests.post("https://api.sume.com/v1/videos", headers=H, json=body, timeout=60)
r.raise_for_status()
url = r.json()["polling_url"]
while True:
    job = requests.get(url, headers=H, timeout=30).json()
    if job["status"] in ("completed", "failed"):
        break
    time.sleep(10)
print(job["status"], job.get("unsigned_urls"))

What I did not verify

I did not test how well either model renders dental tools or tooth shapes; that needs your own 480p draft. The prices above come from the catalog rates and the estimator, and the quoted vendor facts come from the pages listed in sources.

Sources

Related posts

More in Use cases

All Use cases posts

Written by Sume