Investor update deck to a 15-second teaser: ten slides into Wan 3.0
Pick the ten slides that carry numbers and charts, send them to wan-3.0 as reference images, and ask for 15 s. $1.88 at 720p. Why charts need a real overlay.

Choose the ten slides that carry the story, export them as PNGs and send them to wan-3.0 as input_references with a prompt for a 15-second teaser. At 720p that costs 15 x $0.10 x 1.25 = $1.875, which Sume rounds to $1.88. Alibaba's page lists PPT and PDF as inputs to its own Wan 3.0 endpoint, but Sume's video docs list image, video and audio references only, so slides arrive as images.
Which ten slides
- The title slide or logo slide, as the opening frame.
- One slide each for growth, product, customers and team, chosen for strong visuals rather than dense text.
- Two chart slides at most. Charts are where a generated redraw is least trustworthy.
- A closing slide with the ask or the date of the next update.
| Length | 480p | 720p | 1080p |
|---|---|---|---|
| 10 s | $0.63 | $1.25 | $2.50 |
| 15 s | $0.94 | $1.88 | $3.75 |
| 30 s | $1.88 | $3.75 | $7.50 |
Do not let the model write the numbers
Alibaba lists on-screen text accuracy as a current limitation. An investor teaser with a wrong revenue figure is worse than none, so ask for motion without readable figures: gentle camera moves over the slide imagery, blurred chart shapes, no captions. Then place the real numbers as an overlay from the source deck.
Sume's timeline joins Sume-hosted clips and audio into one MP4, which is the place to join the generated clip with a final slide exported straight from the deck. That final slide is a still, so its text is exact.
Practical limits
- Ten reference images is the wan-3.0 cap on Sume, so a 30-slide deck needs selection, not three jobs.
- References are guidance, not exact frames. If one slide must appear unchanged, use it as a first_frame, but then references are not used because frame_images wins.
- Check your confidentiality rules before you upload investor material to any generation service. That decision sits with you, not with the price table.
- A 480p draft is $0.94 for 15 s, which is enough to see which slides the model lingers on.
Prompt shape for a deck teaser
Write the prompt as a short sequence rather than a list of slides: open on the logo, push through the growth visual, settle on the product, finish on the ask. Tell the model what motion to use between them, such as a slow dolly or a soft dissolve, and tell it to leave text unreadable or absent. A teaser of fifteen seconds holds about five beats of three seconds each, which is two slides per beat for ten slides, so the model will skip some. That is acceptable for a teaser, and the draft shows you which slides it skipped.
If an investor must see a specific slide, make it the last frame instead. Wan 3.0 lists end-frame support, so a last_frame image can end the clip on the slide you chose, though in that case the job runs as image-to-video and the other nine references are not used.
A two-pass plan
Pass one is a 480p draft at $0.94 with all ten slides. Look at which slides appear, in what order, and for how long. Pass two moves to 720p with the weakest slides swapped for stronger ones. A 1080p final at 15 s is $3.75, and the whole three-step path costs $0.94 + $1.88 + $3.75 = $6.57 if you render all three tiers, or $2.82 if you stop at 720p.
Sources
Related posts
More in Use cases
- How do I keep a product label exact in an AI product video?
Animate the product photo, then overlay your real label still with Timeline compose: $0.63 for a 5-second clip plus $0.02 for the overlay on Sume.
- Kling motion control silent clip with a Lyria music bed for a Short
Set keep_original_sound to false, generate a track with the Music Router, and join them on a timeline. Cost for a 12-second clip, and the YouTube rule to know.
- 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.
- 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.
Written by Sume