muapi Logomuapi Logo
muapi Logomuapi Logo

Gemini Omni Image to Video: Image-to-Video

Animate images into video with Gemini Omni — native synchronized audio, dialogue, and music. Try free — pay per generation, no subscription. Gemini Omni Image to Video — animate one or more reference images with a text prompt. Unified reasoning across modalities preserves subject identity and generates synchronized audio natively.

Interactive model controls

Gemini Omni Image to Video — animate one or more reference images with a text prompt. Unified reasoning across modalities preserves subject identity and generates synchronized audio natively.

📝

Overview

About this model

Gemini Omni Image to Video animates one or more reference images with a text prompt using Google's natively multimodal any-to-any model. Subject identity is preserved across frames while synchronized audio — dialogue, ambient sound, and music — is generated natively in the same forward pass. It supports 4, 6, 8, or 10 second clips at 360p, 720p, 1080p, or 4K, in either 16:9 or 9:16 aspect ratio, and is billed per second of output video.

1Product animation: Bring product photos to life with motion and ambient sound for social or advertising use.
2Character animation: Animate a character reference image with a prompt describing their action and setting.
3Storyboarding: Convert concept art into short video previews with narration and sound design.
4Social content: Turn still images into engaging vertical or widescreen clips for TikTok, Reels, or Shorts.
💰

Pricing & Value

Cost analysis

muapi$0.039–$0.39 per second of output (by resolution)

Billed per second of output video: $0.039/s at 360p, $0.13/s at 720p, $0.195/s at 1080p, $0.39/s at 4K. Synchronized audio included at no extra charge.

Fal.aiComparable per-second pricing

Same underlying model (google/gemini-omni-flash/v1.1/image-to-video).

ReplicateNot available

Gemini Omni Image to Video is not currently available on Replicate.

** Competitor pricing is estimated based on similar model architectures and usage tiers.

⚙️

Technical Details

Configuration schema

Promptstring

Text description of the desired motion and scene. Gemini Omni supports rich multimodal prompts including camera direction, dialogue, and ambient audio cues.

Default ValueThe suitcase opens by itself and tiny landscapes start unfolding out of it—mountains, forests, oceans, entire cities. Each world expands outward onto the platform, growing larger and larger while miniature weather systems form above them.
Reference Imagesarray

Upload 1–7 reference images for the video. Maximum 20 MB each.

Default Valuehttps://cdn.muapi.ai/assets/gemini-omni-image-to-video.jpg
Duration (seconds)Enum (4 options)

Duration of the generated video in seconds.

Default Value8
ResolutionEnum (4 options)

Output video resolution. Billed per second of output: $0.039/s at 360p, $0.13/s at 720p, $0.195/s at 1080p, $0.39/s at 4K.

Default Value1080p
Aspect RatioEnum (2 options)

Output video aspect ratio.

Default Value16:9
Audio IDsarray

Up to 3 voice profile IDs returned by the Gemini Omni Audio endpoint.

Default Value-
Seedint

Random seed (0–2147483647). Fix for reproducibility; results may still vary due to model stochasticity.

Default Value0
Character IDsarray

Up to 3 character IDs from Gemini Omni Character to feature in the video.

Default Value-
📖

Implementation Guide

Developer documentation

How to Use Gemini Omni Image to Video

  1. Upload reference images Provide 1–5 images via image_urls. Each image acts as a visual anchor. The model preserves subject identity across frames.

  2. Write a motion and scene prompt Describe what happens in the video — motion, setting, lighting, and audio cues. Example: 'The subject slowly turns to face the camera as golden-hour light sweeps across the scene, leaves rustling in the breeze.'

  3. Choose duration and resolution Pick 4, 6, 8, or 10 seconds. Choose 360p for a fast, low-cost draft, 720p / 1080p for standard output, or 4K for higher resolution.

  4. Pick an aspect ratio

    • 16:9 — widescreen, cinematic
    • 9:16 — vertical, mobile-first

  5. Submit and poll POST to /api/v1/gemini-omni-image-to-video and poll GET /api/v1/predictions/{request_id}/result until status is completed.

  6. Example request

    curl -X POST https://api.muapi.ai/api/v1/gemini-omni-image-to-video \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "The subject slowly turns to face the camera as golden-hour light sweeps across the scene.",
    "image_urls": ["https://example.com/reference.jpg"],
    "duration": 8,
    "resolution": "1080p"
  }'
❓

Common Questions

Frequently asked

How many reference images can I provide?

Between 1 and 5 images. Each image counts as 1 unit toward the 7-unit capacity (videos use 2, character IDs use 1).

Does it preserve the subject's appearance across frames?

Yes — Gemini Omni Image to Video is designed to maintain subject identity and appearance from the reference images throughout the generated clip.

Is audio generated automatically?

Yes — synchronized dialogue, ambient sound, and music are generated natively alongside the video in the same forward pass.

What video durations and resolutions are supported?

4, 6, 8, or 10 seconds, at 360p, 720p, 1080p, or 4K — each billed per second of output video.

Can I control the aspect ratio?

Yes — choose 16:9 for widescreen or 9:16 for vertical/mobile-first output.