Google released Gemini Omni 1.1 Flash on 27 August 2026. In SunoMV it is a selectable video row for music-video shots: text or image in, first-and-last-frame camera moves, landscape or portrait, 720P or 1080P. Our measured 360p first–last-frame run came back in 60.4 seconds.
Omni 1.1 is a shot-level lever: first-and-last-frame interpolation, 720P or 1080P, 1–15 seconds. MiniMax H3 Max is the cheaper 480P/720P iteration row. Veo 3.1 is a separate Google row. If you already have two lyric stills and need the camera to move between them in HD, this is the row. Do not ask it for 4K upscaling or 40-second scene extension — those are on Google's announcement, not this picker.
A music video is a stack of short clips that must still look like one camera. Omni 1.1's job in that stack is the shot that walks from one still to the next without jumping outfit, face or room.
Pin the opening picture and the closing picture. The model fills the motion in between — whip-pans, push-ins, orbits — so consecutive lyric lines keep the same singer instead of rolling a new face every bar.
The picker lists 720P and 1080P. Quota is 250 credits per 5 seconds at 720P; 1080P is 1.5×, 375 credits per 5 seconds. Draft the verse at 720P, restage the chorus at 1080P. Higher resolution costs more — that is on the picker note.
Duration is not locked to an 8-second transition slot. Set 1–15 seconds and pick 16:9 or 9:16. That is the whole setup for a TikTok chorus or a YouTube wide shot.
The announcement and the picker are not the same list. Mixing them up wastes a generation.
Text-to-video, image-to-video, and first-and-last-frame. 720P or 1080P. Landscape or portrait. 1–15 second clips. Selectable as Gemini Omni 1.1.
Scene extension (up to 10 seconds of prior context, 10-second increments to 40 seconds) and 4K upscaling are in the official write-up. They are not in the SunoMV transition UI on this page. Do not prompt this row as if they were.
Veo 3.1 Fast/Lite is a separate Google row with its own duration rules. MiniMax H3 Max is the cheap 480P/720P iteration row. Omni 1.1 is the first–last-frame HD row. Same picker, three jobs.
The model is already in the video picker. You do not apply for a key, and you do not leave the music-video flow to use it.
Open the create flow, choose Gemini Omni 1.1, set duration and 720P or 1080P, then landscape or portrait. That is the whole setup.
Describe the scene in text, start from a still, or pass a first frame and a last frame so the clip walks from one lyric picture to the next.
Drop each clip on the lyric timeline, preview vertical, square or widescreen, and export when the chorus finally cuts clean. Previewing the assembly is free.
Nothing to install. The model is already in the SunoMV video picker.
Open create, choose Gemini Omni 1.1, set 1–15 seconds and 720P (draft) or 1080P (keepers). Pick landscape or portrait to match the platform.
Write the scene, start from a still, or set a first frame and a last frame so two lyric pictures connect. Skip 4K and scene-extension prompts — they are not in this UI.
Lay the clips on the lyric timeline. Preview free, then export vertical, square or widescreen for TikTok, Reels, Shorts and YouTube.
No video model is universally better — only better fitted. These are the jobs this row is for.
First-and-last-frame is how you stop the singer's outfit from changing every line. Pin the end of shot A as the start of shot B.
Whip-pan, push-in, orbit: describe the move, or let two stills define the start and end. That is the shot Omni 1.1 is for — not a slideshow crossfade.
Board the song on MiniMax H3 Max at 480P. Restage two or three chorus shots here at 1080P so the export holds up on a phone in full screen.
Same picker. Different duration, quota and camera contract. Click through instead of guessing.
Video. First–last-frame HD shots, 1–15s, 720P/1080P, text or image in.
Video. Separate Google rows with their own duration rules. Prompting lives on the Veo guide, not here.
Video. Fast 5–15s shots at 480P/720P for iterating a full-song preview. Cheaper, not HD.
Gemini Omni 1.1 Flash is a text-to-video, image-to-video and first-last-frame video model Google announced on 27 August 2026. In SunoMV it is selected as omni and used to generate 1–15 second music-video shots at 720P or 1080P.
A first-and-last-frame shot is a generated clip whose opening picture and closing picture are supplied by the user. The model interpolates the motion in between, which is how consecutive lyric lines keep the same character, wardrobe and camera side across a cut.
Scene extension — continue a clip using up to 10 seconds of prior context, in 10-second increments up to 40 seconds — and 4K upscaling. Those are in the 27 August 2026 announcement. The SunoMV picker on this page offers 720P/1080P and first–last-frame, not those two.
Picker limits on this page match the SunoMV video-model list after the 27 August 2026 Omni 1.1 update. Timing is our own measured run, not a vendor marketing number.
Google announced Gemini Omni 1.1 Flash on 27 August 2026: first and last frame interpolation, 360p drafts, 1080p/4K upscaling, and scene extension with up to 10 seconds of prior context.
Google — Build with Gemini Omni 1.1 Flash ↗In SunoMV the selectable row is named Gemini Omni 1.1 (key omni): text-to-video, image-to-video, first-and-last-frame, 720P or 1080P, landscape or portrait, 250 credits per 5s at 720P (1080P is 1.5×).
SunoMV — video model picker (omni) ↗Our measured run, 27 August 2026: 360p first-and-last-frame. Submit 5.4s; generation 57s; end-to-end 60.4s. Sample clip stored from that run.
SunoMV — measured run 2026-08-27 ↗FAQ'S
Ask us anything!
First and last frame when the cut has to hold. 720P to iterate, 1080P to keep. Preview the full-song assembly free, then export for TikTok, Reels, Shorts and YouTube.
/icon.png){kind=icon}
