Spicy Omni Reference 4K API: AI Image-to-Video

Spicy Omni Reference 4K API Reference

Endpoint

POST https://api.muapi.ai/api/v1/seedance-2.5-spicy-omni-reference-4k

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	Text prompt describing the desired video, referencing the provided images, video clips, and audio as environment, motion, and mood cues.
images_list	array	No	Reference image URLs. Up to 30 images.
videos_list	array	No	Reference video URLs. Up to 10 clips.
audios_list	array	No	Reference audio URLs. Up to 10 files.
duration	int	No	The duration of the generated video in seconds.Default: 5
aspect_ratio	string	No	Aspect ratio of the output video.Options: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21Default: "16:9"
seed	int	No	Random seed for reproducible generation. Use -1 for random.
omni_reference_task_type	string	No	Hint for the omni-reference subtask type, so ratio/duration constraint mismatches are caught at submission time instead of failing asynchronously. auto lets the model infer the type from the prompt; reference has no special ratio/duration constraints; edit and extend both require ratio=adaptive (edit additionally requires duration=-1). The model still re-derives the actual task type from the prompt during processing, so a mismatch can still surface as an async error.Options: auto, reference, edit, extendDefault: "auto"
high_bitrate	boolean	No	Enable high bitrate mode for better visual fidelity. Produces larger files.Default: false

cURL example

REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/seedance-2.5-spicy-omni-reference-4k \
  -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-2.5-spicy-omni-reference-4k", 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.