Omni Reference API: AI Image-to-Video

Omni Reference API Reference

Endpoint

POST https://api.muapi.ai/api/v1/seedance-2.0-omni-reference

Submit a job with your MuApi API key in the x-api-key header, then poll https://api.muapi.ai/api/v1/predictions/{request_id}/result until status is completed.

Parameters

Name	Type	Required	Description
prompt	string	Yes	Video description. Use @image1…@image9 to reference images, @video1…@video3 for videos, @audio1…@audio3 for audio. To use a character sheet, reference it with @character:<request_id> (from a completed Seedance 2 Character generation). To use a trained Omni Reference character, reference it with @omni-character:<character_id> where character_id is the value returned by Omni Reference Train Character (e.g. char_1775422630065_4vbana). Both methods can be combined in the same prompt. Multiple characters are supported. Example: '@omni-character:char_1775422630065_4vbana walking through a neon-lit city at night'.
images_list	array	No	Up to 9 reference image URLs (JPEG/PNG/WebP). Each Nth image corresponds to @imageN in the prompt.
video_files	array	No	Up to 3 reference video clip URLs (MP4, max 15s each). Each Nth video corresponds to @videoN in the prompt.
audio_files	array	No	Up to 3 reference audio clip URLs (MP3/WAV, total max 15s). Each Nth audio corresponds to @audioN in the prompt.
aspect_ratio	string	No	Output video aspect ratio.Options: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16Default: "16:9"
quality	string	No	Generation quality. 'high' uses the standard model ($0.30/sec output + $0.09/sec per input video second). 'basic' uses the fast model (~2x speed, $0.21/sec output + $0.063/sec per input video second). Video reference inputs incur an additional 30% surcharge based on their combined duration.Options: high, basicDefault: "high"
duration	int	No	Video duration in seconds (4–15).Default: 5

cURL example

REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/seedance-2.0-omni-reference \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"<prompt>"}' | jq -r .request_id)

curl -s https://api.muapi.ai/api/v1/predictions/$REQUEST_ID/result -H "x-api-key: $MUAPI_API_KEY"

Python example

import os, time, requests

API = "https://api.muapi.ai/api/v1"
headers = {"x-api-key": os.environ["MUAPI_API_KEY"]}

r = requests.post(f"{API}/seedance-2.0-omni-reference", headers=headers, json={"prompt":"<prompt>"})
request_id = r.json()["request_id"]

while True:
    res = requests.get(f"{API}/predictions/{request_id}/result", headers=headers).json()
    if res["status"] == "completed":
        print(res["outputs"]); break
    if res["status"] == "failed":
        raise RuntimeError(res.get("error"))
    time.sleep(3)

Full docs and agent/MCP integration: llms.txt. Get an API key at muapi.ai/access-keys.