muapi Logomuapi Logo
muapi Logomuapi Logo

Gemini Omni 1.1 Flash Reference to Video: Image-to-Video

Generate video with Gemini Omni 1.1 Flash, referencing multiple images and short video clips by tag in your prompt. Try free — pay per generation. Gemini Omni 1.1 Flash Reference to Video — generate video referencing up to 7 images and up to 3 short reference video clips (each up to 3 seconds), addressed by tag directly in the prompt.

Interactive model controls

Gemini Omni 1.1 Flash Reference to Video — generate video referencing up to 7 images and up to 3 short reference video clips (each up to 3 seconds), addressed by tag directly in the prompt.

📝

Overview

About this model

Gemini Omni 1.1 Flash Reference to Video generates a new video from a prompt that directly addresses reference media by tag — up to 7 reference images and up to 3 short reference video clips (each at most 3 seconds), cited in the prompt as <IMAGE_REF_0>, <VIDEO_REF_0>, and so on, in the order the URLs are listed. This lets a single prompt combine multiple distinct visual and motion references without a rigid quota system. For a single-video editing workflow instead, see Gemini Omni 1.1 Flash Video Edit. For text-to-video with reference images, voice, and character IDs, see Gemini Omni 1.1 Flash. For keyframe-driven image-to-video, see Gemini Omni 1.1 Flash Image to Video.

1Multi-reference composition: Combine several reference images and clips into one new scene, addressed individually in the prompt.
2Style and motion transfer: Reference a short clip's motion alongside a still image's subject or style.
3Consistent recurring elements: Reuse the same set of reference images and clips across multiple generations for visual continuity.
4Rapid concept exploration: Test how different reference combinations affect the generated scene.
5Final delivery at 4K: Render an approved concept at higher resolution once the reference combination is set.
💰

Pricing & Value

Cost analysis

muapi$0.048–$0.48 per second of output (by resolution)

Pay-per-generation, no subscription. Combine up to 7 reference images and 3 short reference video clips in one call.

Fal.aiComparable per-second pricing

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

ReplicateNot available

Gemini Omni 1.1 Flash Reference to Video is not listed on Replicate.

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

⚙️

Technical Details

Configuration schema

Promptstring

The text prompt describing the video. Reference media is addressed in the prompt in list order, e.g. <IMAGE_REF_0>, <VIDEO_REF_0>.

Default ValueA cat inspired by <IMAGE_REF_0> walks through the setting in <VIDEO_REF_0>.
Reference Imagesarray

URLs of reference images to incorporate into the video, referenced in the prompt as <IMAGE_REF_0>, <IMAGE_REF_1>, etc.

Default Value-
Reference Videosarray

Up to 3 reference video clips, each at most 3 seconds long, referenced in the prompt as <VIDEO_REF_0>, <VIDEO_REF_1>, etc.

Default Value-
Aspect RatioEnum (2 options)

Output video aspect ratio.

Default Value16:9
ResolutionEnum (4 options)

Output resolution. Billed per second of generated video: $0.048/s at 360p, $0.16/s at 720p, $0.24/s at 1080p, $0.48/s at 4K.

Default Value720p
Duration (seconds)int

Duration of the generated video, in seconds.

Default Value8
📖

Implementation Guide

Developer documentation

How to Use Gemini Omni 1.1 Flash Reference to Video

  1. Gather your reference media Up to 7 reference images (image_urls) and up to 3 reference video clips (reference_video_urls, each at most 3 seconds long).

  2. Write a prompt that addresses each reference by tag Reference media is addressed in the prompt in list order: the first image is <IMAGE_REF_0>, the second <IMAGE_REF_1>, and so on; the first video is <VIDEO_REF_0>, etc. Example: 'A cat inspired by <IMAGE_REF_0> walks through the setting in <VIDEO_REF_0>.'

  3. Choose duration, resolution, and aspect ratio Duration is 3–10 seconds (default 8). Resolution is billed per second: $0.048/s at 360p, $0.16/s at 720p, $0.24/s at 1080p, $0.48/s at 4K.

  4. Submit and poll

    curl -X POST https://api.muapi.ai/api/v1/gemini-omni-flash-1-1-reference-to-video \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A cat inspired by <IMAGE_REF_0> walks through the setting in <VIDEO_REF_0>.",
    "image_urls": ["https://example.com/cat.jpg"],
    "reference_video_urls": ["https://example.com/setting.mp4"],
    "resolution": "1080p"
  }'

    Then poll GET /api/v1/predictions/{request_id}/result until status is completed.

  5. Prompt tips

    • Keep the tag order matched to the URL list order — <IMAGE_REF_0> is always the first image_urls entry.
    • Describe how each reference should be used (subject, setting, motion) rather than just naming the tag.
    • Reference videos longer than 3 seconds should be trimmed before submitting.
❓

Common Questions

Frequently asked

What is Gemini Omni 1.1 Flash Reference to Video?

It generates a new video from a prompt that addresses reference images and short reference video clips by tag — `<IMAGE_REF_0>`, `<VIDEO_REF_0>`, etc. — combining up to 7 images and 3 video clips in one request.

How do the reference tags work?

Reference media is addressed in the order the URLs are listed: the first `image_urls` entry is `<IMAGE_REF_0>`, the second is `<IMAGE_REF_1>`, and so on; the first `reference_video_urls` entry is `<VIDEO_REF_0>`, etc. Use these tags directly in the `prompt` text.

How long can reference videos be?

Each reference video clip must be at most 3 seconds long, and up to 3 reference videos can be provided per request.

How is this priced?

Billed per second of generated video by resolution: $0.048/s at 360p, $0.16/s at 720p, $0.24/s at 1080p, and $0.48/s at 4K. A 10-second 1080p clip costs $2.40.

How is this different from Gemini Omni 1.1 Flash Video Edit?

Video Edit takes one source video and a single edit instruction, returning a restyled version of that same clip. Reference to Video instead generates a new video from a prompt that draws on multiple reference images and clips addressed by tag.