Hotel room tour clip from 10 photos with Omni Flash 1.1
Gemini Omni Flash 1.1 on Sume takes up to 10 reference images and 3 short clips. An 8-second room tour costs $1.00 at 720p, $1.50 at 1080p and $3.00 at 4K.

Send up to 10 photos of the room as input_references to gemini-omni-flash-1.1, plus a prompt that walks through them, and Sume returns a clip of up to 10 seconds. An 8-second tour costs $1.00 at 720p, $1.50 at 1080p and $3.00 at 4K.
The limits are Sume's: up to 10 reference images and 3 reference clips of 3 seconds each, 16:9 or 9:16 only, with synced audio always on. Source: Video Router, read 2026-10-06. A reference photo is a likeness guide, not a pinned shot, so expect the camera to invent the path between rooms.
What does the tour cost by resolution?
Eight seconds, 16:9.
| Model id | Resolution | Length | Sume price | Note |
|---|---|---|---|---|
| gemini-omni-flash-1.1 | 720p | 8 s | $1.00 | |
| gemini-omni-flash-1.1 | 1080p | 8 s | $1.50 | |
| gemini-omni-flash-1.1 | 4K | 8 s | $3.00 | highest rung |
How do I refer to each photo?
The Video Router docs give Omni's reference addresses as <IMAGE_REF_0> to <IMAGE_REF_9> and <VIDEO_REF_0> for clips. Name them in the prompt in the order you want them to appear.
curl -sS -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-omni-flash-1.1",
"prompt": "Slow walk-through: start at <IMAGE_REF_0> the bed, pan to <IMAGE_REF_1> the window seat, end on <IMAGE_REF_2> the bathroom",
"duration": 8,
"resolution": "1080p",
"aspect_ratio": "16:9",
"input_references": [
{"type": "image_url", "image_url": {"url": "https://example.com/bed.jpg"}},
{"type": "image_url", "image_url": {"url": "https://example.com/window.jpg"}},
{"type": "image_url", "image_url": {"url": "https://example.com/bath.jpg"}}
]
}'What if the tour needs more than 10 seconds?
Omni's ceiling is 10 seconds. Generate a longer tour as separate clips, one per room, so you can re-render a single room without redoing the lot.
Sources
Related posts
More in Use cases
- How long can an AI video be? Shorts 3 min, TikTok ads 10 min
YouTube allows Shorts up to 3 minutes and TikTok non-Spark ads up to 10. A Sume clip is at most 30 s, but Timeline renders up to 1800 s from several clips.
- How to split a training lesson into avatar clips under 60 seconds
Sume refuses avatar videos over 60 seconds. Split a 6-minute lesson by words, render each part, and stitch with Timeline 1.0. Word counts and cost by tier.
- HR onboarding welcome video with an AI avatar: day-one clip
A 30-second welcome clip that lists the three things a new hire does on day one. Script size, cost per tier, and what must stay in text, not video.
- Bulk queue idempotency: header or body key, and the header wins
A Sume bulk queue takes an Idempotency-Key as a header or as a body idempotency_key. If you send both, the header wins. Replays return 202 with the old queue.
Written by Sume