Asset Studio video in 16:9 and 9:16: two Sume requests
Google's Asset Studio makes horizontal and vertical video in one workflow. With Sume, send one brief as two requests, 16:9 and 9:16, with model limits.

Sume's video requests take one aspect ratio each, so the same brief becomes two requests: one at 16:9 and one at 9:16. Google's August 2026 Demand Gen drop says Multimodal Video Creation in Asset Studio is generally available and lets you "go from storyboarding to creating horizontal and vertical assets in one workflow"; the Sume docs describe no matching single call.
Google's text is from its blog post of 2026-08-27, read 2026-09-30. Sume limits are from Video Router and Timeline 1.0.
What are the per-model limits?
Limits are per model, and the docs tell you to read capabilities from GET /v1/video-router/models instead of assuming one envelope.
| Model or path | Duration | Resolution and ratio |
|---|---|---|
| Auto controls | 3-10 s clips (default 8 s) | 720p default; 16:9 or 9:16 |
seedance-2.5 | 4-30 s | 480p, 720p, 1080p |
gemini-omni-flash-1.1 | 3-10 s | 360p, 720p, 1080p, 4K; 16:9 or 9:16; synced audio always on |
How do I produce both orientations?
Send the same prompt twice to POST /v1/video-router/generate, changing only aspect_ratio. Use a different Idempotency-Key for each so neither replays the other.
const prompt = "A ceramic mug on a wooden desk, steam rising, soft window light";
const ids = [];
for (const aspect_ratio of ["16:9", "9:16"]) {
const res = await fetch("https://api.sume.com/v1/video-router/generate", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.SUME_API_KEY,
"Content-Type": "application/json",
"Idempotency-Key": "mug-" + aspect_ratio,
},
body: JSON.stringify({
model: "seedance-2.5",
prompt,
resolution: "720p",
duration: 8,
aspect_ratio,
}),
});
ids.push(await res.json());
}
console.log(ids);Will the two clips match each other?
Not frame for frame. They are two generations, so composition and motion can differ. If you need the same shot in both shapes, generate once and reframe: Timeline's video[].fit is cover (default), contain, stretch or blur, and the default output is 1080x1920 (see Timeline fit modes). Timeline also joins ordered slots into one MP4 when you want a longer storyboard; see assemble long-form video. For the specs Demand Gen asks for, see Demand Gen video ad specs.
Sources
Related posts
More in Use cases
- Google Merchant apparel images worn by people: reference-guided images
Google asks for apparel product images worn by people. gpt-image-2.5 on Sume takes up to 16 reference images, so a garment photo can guide the image.
- Google Merchant Center image size: 500x500 minimum, 1500x1500 advised
Google lists at least 500 x 500 pixels for product images and recommends 1500x1500 or above. Sume's gpt-image-2.5 can output 1536x1536, which meets the advice.
- Replace a Merchant Center product video: new filename and URL
Google says video_link URLs must stay stable and never be reused for another video. Each Sume trim or filter returns a new artifact URL, so a re-cut fits.
- Google Merchant Center 16 MB and 64 megapixel image limits vs Sume
Google lists no image over 64 megapixels and no file over 16 MB. Sume's gpt-image-2.5 caps output at 8,294,400 pixels; file size is not published.
Written by Sume