Updated

Google DeepMind

Gemini Omni Flash 1.1

Google DeepMind's Gemini Omni Flash 1.1: video with first and last frame control, up to 4K.

Create with Gemini Omni Flash 1.1View pricing

What is Gemini Omni Flash 1.1?

Gemini Omni Flash 1.1 is the update to Google DeepMind's Gemini Omni Flash video model, launched on August 27, 2026.

Like Gemini Omni 1.0, it reads text, images and video together and makes one clip with sound. The addition on Flashloop is first and last frame control, so you can pin how a shot starts and ends.

On Flashloop it renders 4, 6, 8 or 10 seconds at 720p, 1080p or 4K in 16:9 or 9:16, with native audio on every clip. You can attach up to 7 reference images or up to 3 saved characters, or one reference video of up to 10 seconds for video-to-video edits. Frames and references cannot be combined in one generation.

Google's launch post also describes longer scene extension and 360p previews. Flashloop does not offer either, so plan around 10 seconds per clip. Video editing and extension are blocked in the EEA, Switzerland and the UK under Google's API policy. For the original model, see Gemini Omni.

Provider
Google DeepMind
Length
10 seconds
Resolution
720p, 1080p, 4K
Aspect ratios
16:9, 9:16
Audio
Native audio

What you can do with Gemini Omni Flash 1.1

  • First and last frame

    set a start image and an optional end image and the model fills the motion between them

  • Native audio

    sound is generated with the picture on every render

  • Reference images

    up to 7 per generation, or up to 3 saved characters

  • Video-to-video

    attach one clip of up to 10 seconds to edit or rework it

  • Up to 4K output, at 16:9 or 9:16

Prompts to try with Gemini Omni Flash 1.1

“Start on the first frame, a closed wooden door in a quiet hallway. End on the last frame, the same door open onto a sunlit garden. The camera pushes forward slowly as the door swings open, with the sound of a latch and birdsong. A single continuous shot, 6 seconds, 16:9.”

Try this prompt

Where Gemini Omni Flash 1.1 fits best

  • Camera moves between two frames

    Give a start frame and an end frame and let the model build the move between them.

  • Travel and landscape footage

    Short 4K scenes of coastlines, lakes and beaches with generated sound.

  • Product reveals

    Start on a close detail, end on the full product and get a clean transition with audio.

  • Reworking an existing clip

    Attach a clip of up to 10 seconds and describe the change you want.

  • Vertical and landscape from one brief

    Render the same scene in 16:9 for web and 9:16 for social.

How Gemini Omni Flash 1.1 compares

Gemini Omni Flash 1.1 compared with other video models on Flashloop
ModelLengthTop resolutionAspect ratiosNative audio
Gemini Omni Flash 1.110 seconds4K16:9, 9:16Yes
Veo 3.18 seconds1080p16:9Yes
Kling 3.015 secondsPro (1080p)16:9, 9:16, 1:1No
Kling 3.0 Turbo15 seconds1080p16:9, 9:16, 1:1No
Kling 4.0Coming soon30 secondsTo be confirmedTo be confirmedYes

Good to know before you generate

  • First and last frames cannot be combined with reference images, characters or a reference video in the same generation
  • Clips cut between shots unless the prompt asks for a single scene, per Google's documentation
  • Clips run 4, 6, 8 or 10 seconds on Flashloop
  • Video input is limited to one clip of up to 10 seconds
  • Google blocks video editing and extension in the EEA, Switzerland and the UK under its API policy
  • Flashloop offers 16:9 and 9:16 only

Start creating with Gemini Omni Flash 1.1

Create with Gemini Omni Flash 1.1

  1. Select Gemini Omni Flash 1.1

    Open Flashloop and choose Gemini Omni Flash 1.1 from the model selector in the video creator.

  2. Enter your prompt

    Describe what you want to see in your video.

  3. Generate and download

    Hit generate and your video will be ready in seconds. Download or share directly.

Questions about Gemini Omni Flash 1.1

What is new in Gemini Omni Flash 1.1?

Google launched it on August 27, 2026. On Flashloop the difference from Gemini Omni 1.0 is first and last frame control. Durations, resolutions and reference limits are otherwise the same.

Can I set a start and an end frame?

Yes. Add a first frame and, if you want, a last frame, and the model animates the move between them. A generation with frames cannot also use reference images, characters or a reference video.

Does Gemini Omni Flash 1.1 generate audio?

Yes. Audio is generated natively with the video and is always on.

What durations, resolutions and aspect ratios does it support?

4, 6, 8 or 10 seconds, at 720p, 1080p or 4K, in 16:9 or 9:16.

How many references can I use?

Up to 7 reference images, up to 3 saved characters, and one reference video of up to 10 seconds for video-to-video edits.

Does the duration setting apply when I attach a video?

No. With a reference video attached, the model picks the clip length itself, up to 10 seconds.

Why does my clip cut between shots?

Google's documentation says the model makes multi-shot clips by default. Ask for a single scene or one continuous shot in the prompt to get a single take.

Can I use it in the EEA, Switzerland or the UK?

Google blocks video editing and extension in those regions under its API policy. That limit applies to video-to-video edits.

More video models on Flashloop

Browse all models