Google Gemini Omni 1.1 Flash Reference To Video API Documentation

Google Gemini Omni 1.1 Flash Reference To Video API Documentation

Playground

Gemini Omni 1.1 Flash Reference-to-Video creates short AI videos with synchronized audio from a text prompt plus optional image and video references, supporting resolutions from 360P to 4K for character-consistent clips, visual reference guidance, social content, marketing videos, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Gemini Omni 1.1 Flash Reference-to-Video generates synchronized audio and video from a prompt plus reference media. Use reference images for subject, character, product, or environment guidance, and add short reference videos when motion, camera behavior, or scene rhythm matters.

Why Choose This?

• Multimodal reference guidance
  Combine reference images and short reference videos to guide the final result.

• Character and context consistency
  Preserve recognizable subjects, visual identity, and scene context while generating a new video.

• Motion and camera guidance
  Use reference videos to communicate gestures, action, pacing, or camera movement that may be difficult to describe with text alone.

• Synchronized audio
  Generate video and matching audio together in one workflow.

• Draft-to-production workflow
  Start with 360p for faster testing, then move to 1080p or 4k for higher-quality delivery.

• Flexible output formats
  Supports both 16:9 and 9:16 for landscape and vertical video creation.

Parameters

How to Use

1. Add reference media — Upload reference images, reference videos, or both.
2. Write your prompt — Describe the target scene, action, camera behavior, and the role of each reference.
3. Choose aspect ratio — Use 16:9 for landscape video or 9:16 for vertical content.
4. Select resolution — Use 360p for quick testing, 720p for standard output, or 1080p / 4k for higher-quality delivery.
5. Set duration — Choose a duration from 3 to 10 seconds.
6. Submit — Generate the final video with synchronized audio.

Pricing

Pricing is based on generated video duration and selected resolution.

Example Costs

Best Use Cases

• Reference-guided video generation — Create videos that follow specific people, products, objects, or environments.
• Character-consistent scenes — Keep visual identity more stable across generated shots.
• Motion transfer and camera guidance — Use reference videos for action, gesture, pacing, or shot behavior.
• Marketing and social content — Combine brand visuals, products, and motion references into short-form videos.
• Creative prototyping — Quickly test prompt-plus-reference workflows before final production.

Pro Tips

• Use clear, relevant reference images when identity or appearance matters.
• Use reference videos when motion, pacing, or camera behavior is important.
• In the prompt, clearly describe what each reference should influence.
• Avoid mixing too many conflicting references in one request.
• Start at 360p for iteration, then re-run at a higher resolution for final output.
• Keep reference videos short and focused on the motion you want to guide.

Notes

• prompt is required.
• At least one reference input should be provided through images or reference_videos.
• images supports up to 10 inputs.
• reference_videos supports up to 3 inputs, and each video must be at most 3 seconds.
• The model generates synchronized audio together with the video.

Related Models

• Gemini Omni 1.1 Flash Text-to-Video — Generate videos directly from text prompts with synchronized audio.
• Gemini Omni 1.1 Flash Image-to-Video — Animate a start image into a video with optional last-frame guidance.
• Gemini Omni 1.1 Flash Video Edit — Edit existing videos with prompt instructions.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "duration": 8
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/google/gemini-omni-1.1-flash/reference-to-video" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters