What video settings can I control?

You can choose landscape or portrait aspect ratio, set a duration from 3 to 10 seconds, and request 360p, 720p, 1080p, or 4k resolution.

Does Gemini Omni 1.1 Flash generate audio with the video?

Yes. Gemini Omni 1.1 Flash can generate synchronized speech, music, sound effects, or ambient audio when those details are included in the prompt.

Example inputhover

prompt: "Create a 10-second horizontal fast-paced, high-energy product commercial for the each::labs "Orange C" Vitamin C Face Serum, a glass dropper bottle with amber serum, a shiny gold metallic cap, an orange rubber dropper bulb, and a white label, exactly as shown in the reference image. The bottle, cap, dropper, colors, and label must stay identical to the reference at all times and must not change.Set in the warm natural scene from the reference image: a wooden surface with soft linen drapery, fresh oranges, orange slices, orange blossoms and leaves around the bottle, in warm golden daylight.Energetic, premium, vibrant beauty-commercial mood with quick dynamic motion. No hands or people appear in the video at any point, the product moves on its own.Sequence: Punchy quick push-in toward the bottle as warm golden light flares and glints sharply across the gold cap and glowing amber serum. Rapid smooth orbit around the bottle, orange slices and blossoms flying past, juicy textures glistening, leaves swirling in a light breeze. Snap to a bold hero shot: the bottle standing tall and proud, sunlight flaring behind it, label crisp and clearly facing the camera. To finish: with no hands involved, the gold dropper cap rises smoothly on its own out of the bottle and stays fully visible in frame, keeping its exact same shiny gold color and orange dropper bulb. The dropper squeezes once and releases a single small drop of serum. The camera pushes in close as the drop falls in slow motion straight down into the open neck of the bottle, merging into the amber serum inside with a soft glossy ripple. The video ends on this close-up of the drop landing inside the bottle. A warm, confident female voiceover says over the video: "Orange C by each::labs. Pure vitamin C glow, in every drop."Style: warm, vibrant, high-energy premium skincare commercial. Bright golden daylight, strong light flares, shallow depth of field, creamy bokeh, glistening juicy orange textures, fast smooth camera motion, rich amber and orange tones. Photorealistic, 4K. No text on screen, no cuts, single continuous dynamic shot. The gold cap and orange dropper must keep their original colors the entire time. No hands, no people."
duration: "10s"
image_url
resolution: "720p"
aspect_ratio: "16:9"

Google | Gemini Omni 1.1 Flash | Image to Video

Video·gemini-omni-flash·by Google

Gemini Omni 1.1 Flash Image-to-Video animates a source image into a short AI video with prompt-guided motion, synchronized audio, portrait or landscape framing, and selectable resolution up to 4k.

Try it now →

API reference

Runtime (p50): 1m
Estimated price: Usage-based

Call the API

prediction.sh

curl -X POST \
  -H "Authorization: Bearer $EACHLABS_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
    "model": "google-gemini-omni-1-1-flash-image-to-video",
    "version": "0.0.1",
    "input": {
        "prompt": "Create a 10-second horizontal fast-paced, high-energy product commercial for the each::labs \"Orange C\" Vitamin C Face Serum, a glass dropper bottle with amber serum, a shiny gold metallic cap, an orange rubber dropper bulb, and a white label, exactly as shown in the reference image. The bottle, cap, dropper, colors, and label must stay identical to the reference at all times and must not change.Set in the warm natural scene from the reference image: a wooden surface with soft linen drapery, fresh oranges, orange slices, orange blossoms and leaves around the bottle, in warm golden daylight.Energetic, premium, vibrant beauty-commercial mood with quick dynamic motion. No hands or people appear in the video at any point, the product moves on its own.Sequence:\nPunchy quick push-in toward the bottle as warm golden light flares and glints sharply across the gold cap and glowing amber serum. Rapid smooth orbit around the bottle, orange slices and blossoms flying past, juicy textures glistening, leaves swirling in a light breeze.\nSnap to a bold hero shot: the bottle standing tall and proud, sunlight flaring behind it, label crisp and clearly facing the camera.\nTo finish: with no hands involved, the gold dropper cap rises smoothly on its own out of the bottle and stays fully visible in frame, keeping its exact same shiny gold color and orange dropper bulb. The dropper squeezes once and releases a single small drop of serum. The camera pushes in close as the drop falls in slow motion straight down into the open neck of the bottle, merging into the amber serum inside with a soft glossy ripple. The video ends on this close-up of the drop landing inside the bottle.\nA warm, confident female voiceover says over the video:\n\"Orange C by each::labs. Pure vitamin C glow, in every drop.\"Style: warm, vibrant, high-energy premium skincare commercial. Bright golden daylight, strong light flares, shallow depth of field, creamy bokeh, glistening juicy orange textures, fast smooth camera motion, rich amber and orange tones. Photorealistic, 4K. No text on screen, no cuts, single continuous dynamic shot. The gold cap and orange dropper must keep their original colors the entire time. No hands, no people.",
        "duration": "10s",
        "image_url": "https://cdn-us.eachlabs.ai/defaults/8eace99f6ad84b58bfd4ff48097a81c7.png",
        "resolution": "720p",
        "aspect_ratio": "16:9"
    },
    "webhook_url": ""
}' \
  https://api.eachlabs.ai/v1/prediction/

Documentation8 sections

Overview
Google | Gemini Omni 1.1 Flash | Image to Video Overview

Google | Gemini Omni 1.1 Flash | Image to Video turns a still image into a short, prompt-guided video with synchronized audio and a realistic motion structure. It is part of Google’s Omni family, which is positioned as a multimodal video model for creating and editing video from text, image, video, and audio references. The main differentiator is its combination of image conditioning, native audio generation, and high-end production controls, including scene extension, first-and-last-frame interpolation, and 4K upscaling. For teams using each::labs, this makes the model useful when a single reference image must become a polished motion asset without a separate editing pipeline.
Capabilities
Capabilities
- Animates a still image into a short video with prompt-guided motion.
- Generates synchronized audio alongside the visual output.
- Supports portrait and landscape framing.
- Offers higher-resolution output with 4K upscaling in the Omni 1.1 family.
- Extends scenes in 10-second increments for longer sequences.
- Supports first-and-last-frame interpolation for more controlled transitions.
- Works within a multimodal workflow that can use text, image, video, and audio references.
- Designed for faster prototyping and controlled video production.
Use cases
Use Cases for Google | Gemini Omni 1.1 Flash | Image to Video

Creators can turn illustrations, concept art, or character portraits into short motion clips. A useful prompt is: “Animate this character with subtle head movement, blinking, and a slow cinematic zoom.” This uses the model’s image conditioning and prompt-guided motion.

Marketers can convert product photos into short promotional loops with audio. A practical prompt is: “Make this product image feel premium with rotating highlights, slight camera drift, and polished ambient sound.” This benefits from synchronized audio and controlled framing.

Developers integrating the Google | Gemini Omni 1.1 Flash | Image to Video API can build automated content workflows for social clips or ad variants. Example prompt: “Use this source image as the anchor and generate a 9:16 motion clip with subtle motion and branded audio cues.”

Designers can test animated hero assets for landing pages. Example prompt: “Turn this mockup into a landscape video with gentle environmental motion, stable layout, and soft ambient sound.”
Tips & tricks
Tips and Tricks

Use concise prompts that separate subject motion, camera motion, and audio direction. For Google | Gemini Omni 1.1 Flash | Image to Video, describe what should stay stable in the image and what should move. If the scene has a clear subject, specify the first action in the opening second so the model has a stronger motion anchor. Use portrait framing for social-first assets and landscape framing for cinematic or website hero content. If you plan to iterate, generate a short first pass, then refine motion, timing, and atmosphere in the next prompt rather than overloading the first request.

Example prompts:

“Animate this product photo with subtle camera push-in, soft reflective highlights, and premium ambient audio.”

“Turn this character illustration into a cinematic portrait clip with hair movement, slow blinking, and gentle background motion.”

“Make this landscape image feel alive with drifting clouds, moving foreground grass, and a calm natural soundscape.”
Technical spec
Technical Specifications
- Input type: image plus prompt instruction, with support in the broader Omni workflow for text, image, video, and audio references.
- Output type: generated video with synchronized audio.
- Duration: Google’s Omni 1.1 documentation highlights scene extension in 10-second increments up to 40 seconds total for video workflows.
- Resolution: supports crisp 4K upscaling in the Omni 1.1 family.
- Framing: supports portrait and landscape output formats.
- Processing: Google describes faster prototyping, but does not publish a fixed average generation time in the available documentation.
- Architecture: multimodal video generation model within Google’s Omni family, designed for video creation and editing from references.
Things to be aware of
Things to Be Aware Of

The model performs best when the source image is clear, well-composed, and visually stable. Low-quality or heavily cluttered inputs can make motion look inconsistent. Users also often over-specify too many effects in one prompt, which can reduce coherence. Because the workflow is compute-intensive, 4K output and longer sequences may be more resource demanding than short drafts. If you need precise character continuity across complex actions, you may need multiple iterations rather than expecting a single prompt to solve everything.
Key considerations
Key Considerations

Google | Gemini Omni 1.1 Flash | Image to Video works best when you need controlled motion from a single source image, especially for product shots, characters, branded visuals, or storyboard frames. The model is strongest when the prompt clearly defines motion, camera behavior, and scene intent. It is a good fit when synchronized audio matters and when you want a result that can be extended or refined later. Because Google positions the Omni workflow around high-control production, it is better for structured video creation than for fully unconstrained experimentation. The main tradeoff is that higher-quality output and 4K upscaling imply more compute-heavy usage than simple still-image animation.
Limitations
Limitations

Google | Gemini Omni 1.1 Flash | Image to Video is not a general-purpose long-form video editor. Available information indicates short clips, with scene extension used to build longer outputs in increments. The model may struggle with highly complex multi-subject choreography, very fine text rendering, or scenes that require exact frame-perfect control. While it supports image-to-video generation and audio, published documentation in the available research does not provide a fixed average processing time or exhaustive output-format list.

Related models

4 models

Ltx v2.5 | Image to Video | Pro AI model preview

Ltx v2.5 | Image to Video | ProLTX

MiniMax H3 | Image-to-Video AI model preview

MiniMax H3 | Image-to-VideoMinimax

Ltx v2.5 | Image to Video | Fast AI model preview

Ltx v2.5 | Image to Video | FastLTX

Luma | Ray 3.2 | Image to Video AI model preview

Luma | Ray 3.2 | Image to VideoLuma

* FAQ

About Google | Gemini Omni 1.1 Flash | Image to Video

01 / 03

What inputs does Gemini Omni 1.1 Flash Image-to-Video use?

This model uses a text prompt and one source image URL. The image is used as the first frame, and the prompt describes how the scene should animate or sound.

Google | Gemini Omni 1.1 Flash | Image to Video