How do I specify the opening and closing frames?

Upload both images in playback order. Use a single opening frame to animate one image.

How long can a two-frame transition be?

Up to 10 seconds with an end frame. Regular generation supports 3–15 seconds.

When should I use reference mode?

Use it to guide the subject, scene or look. Use frames when you need a specific opening or ending composition.

Can I edit lighting in a source clip?

Upload the clip in video edit mode and describe the change. The result follows the source duration.

Do I need an audio track?

Generated video includes synchronized sound. Describe dialogue, ambience or sound cues in the prompt.

Which resolutions can I choose?

Use 360p to check timing, then choose 720p, 1080p or 4K when the selected shot needs a larger output.

Can I generate vertical video?

Choose 9:16 and prepare frames that leave space for subject movement.

Which video files can I reference?

Add a reference image first. An optional MP4 reference clip can be up to 10 seconds.

Why does a reference video change the credit quote?

Video input adds usage. Duration and output resolution also affect the displayed quote.

What should I check before downloading?

Watch the transition at playback speed, inspect the last frame and listen for the intended audio cues.

Gemini Omni 1.2 Flash

Gemini Omni 1.2 Flash is relevant to video ideas that begin with more than plain text: reference images, existing footage and successive change requests. Design a short shot plan and compare how well motion and scene context survive each requested revision.

Generation mode

Text-to-Video / Image-to-Video / Reference-to-Video / Video-to-Video

Duration

3s / 4s / 5s / 6s / 7s / 8s / 9s / 10s / 11s / 12s / 13s / 14s / 15s

Resolution

360p / 720p / 1080p / 4k

Aspect ratio

auto / 16:9 / 9:16

Reference image

10 · JPEG / PNG / WebP · 20 MB

Reference video URL

MP4 · 200 MB

Prompt (max)

20000

About

What this model is for

Generation mode

Plan a transition from two frames

Set the opening and ending compositions, then describe the subject or camera movement between them.

Choose frames or flexible references

Use frames for specific endpoints and reference mode for subject, setting or visual style.

Include sound cues in the shot brief

Describe where dialogue, ambience or footsteps should fall. Generated video includes synchronized sound.

Revise an existing clip

Use video edit to change a setting, light or object while following the source clip’s duration.

Check timing before increasing resolution

Regular generation supports 3–15 seconds. Inspect movement at 360p before selecting a larger output.

Review the shot in context

Check where the shot starts and ends and whether the audio fits the cut, then download the keeper.

How to use

01 · Plan a useful first test

Describe subject movement, camera direction, visual continuity and intended clip purpose.

Text-to-Video / Frames to video / Reference-to-Video / Video Edit

02 · Settings

Use one opening image or two ordered frames. With an end frame, the limit is 10 seconds. Generated video includes synchronized sound.

Duration · 3–15 s · Resolution · 360p / 720p / 1080p / 4K · Aspect ratio · 16:9 / 9:16

03 · Generate / Download

The generator shows the site credits for your settings before you submit.

Inspect motion continuity, object consistency, camera stability, reference fidelity and audio if present. A promotional clip does not establish the result of your prompt or a guaranteed generation time.

What to make

Transitions between shots

Connect a closed box to a product reveal with two frames and a planned camera move.

Short scenes with synchronized sound

Build a café scene and describe when the door bell or footsteps should sound.

FAQ

Gemini Omni 1.2 Flash · Frequently asked questions

Gemini Omni 1.2 Flash FAQ

Explore more AI video models

Veo 3.1 Quality

New

Veo 3.1 offers Lite, Fast and Quality variants where available. Choose text-to-video, image-to-video or video-to-video in supported modes; reference-to-video supports up to 3 images and requires Fast at 16:9. Available aspect options are Auto, 16:9 and 9:16. The interface has no duration or resolution selector. Check the displayed credit cost before generating.

Try now

Wan 2.6

New

Wan 2.6 supports text-to-video, image-to-video and video-to-video. It offers 5-, 10- and 15-second duration options, 720p and 1080p resolutions, and multi-shot generation.

Try now

Sora 2

The standard Sora model. It is designed for efficient video generation and can be used for storyboards, social clips and creative iterations.

Try now

Vidu Q4

New

Animate one first-frame image or use up to 15 reference images. Choose 540p–4K and a duration of 3–16 seconds for image animation or 1–16 seconds for references. Synchronized audio is optional. Reference audio must be MP3 and 3–12 seconds long.

Try now

Kling 4.0

New

Create 3–30-second videos from text, first and last frames, or visual references. Choose 720p or 1080p and review motion, sound and credits before developing your next edit.

Try now

Kling 2.6

Kling 2.6 is designed for complex motion and interactions. Use it to explore dynamic character movement, objects interacting and fluid camera moves.

Try now

Gemini Omni 1.2 Flash

Choose your settings below to create with this model.

Generate