PixVerse 6 Transition API: AI Image-to-Video

PixVerse 6 Transition API Reference

Endpoint

POST https://api.muapi.ai/api/v1/pixverse-v6-transition

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 description of the transition or video content.
image_url	string	Yes	Upload starting image.
last_image	string	No	Upload ending image (optional).
aspect_ratio	string	No	Output video orientation.Options: 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2, 21:9Default: "16:9"
resolution	string	No	Video output quality.Options: 360p, 540p, 720p, 1080pDefault: "720p"
duration	int	No	Total length of the video.Default: 5
thinking_type	boolean	No	Enable enhanced thinking for more complex transitions.Default: false
style	string	No	Visual style of the generation.Options: anime, 3d_animation, clay, comic, cyberpunk
negative_prompt	string	No	What to avoid in the generation.
generate_audio_switch	boolean	No	Whether to generate background audio for the video.Default: false

cURL example

REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/pixverse-v6-transition \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"<prompt>","image_url":"https://example.com/your-image_url"}' | 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}/pixverse-v6-transition", headers=headers, json={"prompt":"<prompt>","image_url":"https://example.com/your-image_url"})
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.