Muse Video Reference to Video

cURL

curl https://api.apipod.ai/v1/videos/generations \
  -H "Authorization: Bearer $APIPOD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "muse-video-r2v",
  "prompt": "A corgi surfing at sunset, cinematic, slow motion",
  "image_urls": ["https://cdn.example.com/ref-character.jpg", "https://cdn.example.com/ref-scene.jpg"],
  "duration": 10,
  "aspect_ratio": "16:9",
  "style_preset": "cinematic_realistic",
  "generate_audio": true
}'

import os
import requests

payload = {
  "model": "muse-video-r2v",
  "prompt": "A corgi surfing at sunset, cinematic, slow motion",
  "image_urls": ["https://cdn.example.com/ref-character.jpg", "https://cdn.example.com/ref-scene.jpg"],
  "duration": 10,
  "aspect_ratio": "16:9",
  "style_preset": "cinematic_realistic",
  "generate_audio": True
}

response = requests.post(
    "https://api.apipod.ai/v1/videos/generations",
    headers={
        "Authorization": f"Bearer {os.environ['APIPOD_API_KEY']}",
        "Content-Type": "application/json",
    },
    json=payload,
    timeout=60,
)
response.raise_for_status()
print(response.json())

package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "net/http"
    "os"
)

func main() {
    payload := map[string]any{}
    if err := json.Unmarshal([]byte(`{
  "model": "muse-video-r2v",
  "prompt": "A corgi surfing at sunset, cinematic, slow motion",
  "image_urls": ["https://cdn.example.com/ref-character.jpg", "https://cdn.example.com/ref-scene.jpg"],
  "duration": 10,
  "aspect_ratio": "16:9",
  "style_preset": "cinematic_realistic",
  "generate_audio": true
}`), &payload); err != nil {
        panic(err)
    }
    body, err := json.Marshal(payload)
    if err != nil {
        panic(err)
    }

    req, err := http.NewRequest(http.MethodPost, "https://api.apipod.ai/v1/videos/generations", bytes.NewReader(body))
    if err != nil {
        panic(err)
    }
    req.Header.Set("Authorization", "Bearer "+os.Getenv("APIPOD_API_KEY"))
    req.Header.Set("Content-Type", "application/json")

    resp, err := http.DefaultClient.Do(req)
    if err != nil {
        panic(err)
    }
    defer resp.Body.Close()
    fmt.Println(resp.Status)
}

use reqwest::Client;
use serde_json::json;
use std::env;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let payload = json!({
  "model": "muse-video-r2v",
  "prompt": "A corgi surfing at sunset, cinematic, slow motion",
  "image_urls": ["https://cdn.example.com/ref-character.jpg", "https://cdn.example.com/ref-scene.jpg"],
  "duration": 10,
  "aspect_ratio": "16:9",
  "style_preset": "cinematic_realistic",
  "generate_audio": true
});
    let response = Client::new()
        .post("https://api.apipod.ai/v1/videos/generations")
        .bearer_auth(env::var("APIPOD_API_KEY")?)
        .json(&payload)
        .send()
        .await?
        .error_for_status()?;

    println!("{}", response.text().await?);
    Ok(())
}

const response = await fetch("https://api.apipod.ai/v1/videos/generations", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.APIPOD_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify(
  {
    "model": "muse-video-r2v",
    "prompt": "A corgi surfing at sunset, cinematic, slow motion",
    "image_urls": ["https://cdn.example.com/ref-character.jpg", "https://cdn.example.com/ref-scene.jpg"],
  "image_urls": ["https://cdn.example.com/ref-character.jpg", "https://cdn.example.com/ref-scene.jpg"],
    "duration": 10,
    "aspect_ratio": "16:9",
    "style_preset": "cinematic_realistic",
    "generate_audio": true
  }
  ),
});

if (!response.ok) {
  throw new Error(`APIPod request failed: ${response.status} ${await response.text()}`);
}

console.log(await response.json());

{
  "code": 200,
  "message": "success",
  "data": {
    "task_id": "vid_task_01JEXAMPLE"
  }
}

POST

https://api.apipod.ai

videos

generations

cURL

curl https://api.apipod.ai/v1/videos/generations \
  -H "Authorization: Bearer $APIPOD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "muse-video-r2v",
  "prompt": "A corgi surfing at sunset, cinematic, slow motion",
  "image_urls": ["https://cdn.example.com/ref-character.jpg", "https://cdn.example.com/ref-scene.jpg"],
  "duration": 10,
  "aspect_ratio": "16:9",
  "style_preset": "cinematic_realistic",
  "generate_audio": true
}'

import os
import requests

payload = {
  "model": "muse-video-r2v",
  "prompt": "A corgi surfing at sunset, cinematic, slow motion",
  "image_urls": ["https://cdn.example.com/ref-character.jpg", "https://cdn.example.com/ref-scene.jpg"],
  "duration": 10,
  "aspect_ratio": "16:9",
  "style_preset": "cinematic_realistic",
  "generate_audio": True
}

response = requests.post(
    "https://api.apipod.ai/v1/videos/generations",
    headers={
        "Authorization": f"Bearer {os.environ['APIPOD_API_KEY']}",
        "Content-Type": "application/json",
    },
    json=payload,
    timeout=60,
)
response.raise_for_status()
print(response.json())

package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "net/http"
    "os"
)

func main() {
    payload := map[string]any{}
    if err := json.Unmarshal([]byte(`{
  "model": "muse-video-r2v",
  "prompt": "A corgi surfing at sunset, cinematic, slow motion",
  "image_urls": ["https://cdn.example.com/ref-character.jpg", "https://cdn.example.com/ref-scene.jpg"],
  "duration": 10,
  "aspect_ratio": "16:9",
  "style_preset": "cinematic_realistic",
  "generate_audio": true
}`), &payload); err != nil {
        panic(err)
    }
    body, err := json.Marshal(payload)
    if err != nil {
        panic(err)
    }

    req, err := http.NewRequest(http.MethodPost, "https://api.apipod.ai/v1/videos/generations", bytes.NewReader(body))
    if err != nil {
        panic(err)
    }
    req.Header.Set("Authorization", "Bearer "+os.Getenv("APIPOD_API_KEY"))
    req.Header.Set("Content-Type", "application/json")

    resp, err := http.DefaultClient.Do(req)
    if err != nil {
        panic(err)
    }
    defer resp.Body.Close()
    fmt.Println(resp.Status)
}

use reqwest::Client;
use serde_json::json;
use std::env;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let payload = json!({
  "model": "muse-video-r2v",
  "prompt": "A corgi surfing at sunset, cinematic, slow motion",
  "image_urls": ["https://cdn.example.com/ref-character.jpg", "https://cdn.example.com/ref-scene.jpg"],
  "duration": 10,
  "aspect_ratio": "16:9",
  "style_preset": "cinematic_realistic",
  "generate_audio": true
});
    let response = Client::new()
        .post("https://api.apipod.ai/v1/videos/generations")
        .bearer_auth(env::var("APIPOD_API_KEY")?)
        .json(&payload)
        .send()
        .await?
        .error_for_status()?;

    println!("{}", response.text().await?);
    Ok(())
}

const response = await fetch("https://api.apipod.ai/v1/videos/generations", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.APIPOD_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify(
  {
    "model": "muse-video-r2v",
    "prompt": "A corgi surfing at sunset, cinematic, slow motion",
    "image_urls": ["https://cdn.example.com/ref-character.jpg", "https://cdn.example.com/ref-scene.jpg"],
  "image_urls": ["https://cdn.example.com/ref-character.jpg", "https://cdn.example.com/ref-scene.jpg"],
    "duration": 10,
    "aspect_ratio": "16:9",
    "style_preset": "cinematic_realistic",
    "generate_audio": true
  }
  ),
});

if (!response.ok) {
  throw new Error(`APIPod request failed: ${response.status} ${await response.text()}`);
}

console.log(await response.json());

{
  "code": 200,
  "message": "success",
  "data": {
    "task_id": "vid_task_01JEXAMPLE"
  }
}

muse-video-r2v generates a clip that stays faithful to the things you care about. Instead of pinning a single frame, you hand Muse Video one to four reference images — a character, a product, a location — and it composes the shot around them, holding identity and material detail across the whole clip.

Model at a glance


Public model ID	`muse-video-r2v`
Input	text + image (1-4)
Output	video with audio
Duration	5, 10, 20, 30, 40, 50 or 60 seconds (default 5)
Resolution	720p
Aspect ratio	`16:9`, `9:16`, `1:1`, `4:3`, `3:4` (default `16:9`)
Billing	per second of output

Parameters

Parameter	Type	Default	Notes
`prompt`	string	—	Required, up to 4000 characters. Describe the action, not the references.
`image_urls`	string[]	—	Required, 1-4 public image URLs.
`duration`	integer	`5`	Must be one of 5, 10, 20, 30, 40, 50, 60.
`aspect_ratio`	string	`16:9`	Output framing, independent of the reference images.
`resolution`	string	`720p`	720p is the only supported tier.
`style_preset`	string	`none`	Same seven presets as text-to-video.
`generate_audio`	boolean	`true`	Set `false` to mute voices.

What each reference does

References	Best for
1 image	A single hero subject — one character or one product, in a new scene.
2-3 images	Subject plus environment, so the model doesn’t invent a backdrop.
4 images	Multi-angle subject consistency, e.g. four sides of a product or a character sheet.

Keep each reference focused on one thing. A photo that contains two competing subjects will pull the generated clip toward both.

Prompting

Describe what happens, not what the subject looks like — the references already carry appearance. Naming the shot and the motion is usually enough.

The character walks through a rain-soaked night market, neon reflections
on wet asphalt, camera tracks at shoulder height, shallow focus

If a reference is a product, state the action rather than the object: “a hand lifts the bottle”, not “a white glass bottle”. Adjectives about the reference tend to be reapplied as style changes.

Workflow

POST /v1/videos/generations with image_urls and a prompt.
Read data.task_id.
Poll GET /v1/videos/status/{task_id} until completed.
Download from data.result.

curl https://api.apipod.ai/v1/videos/generations \
  -H "Authorization: Bearer $APIPOD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "muse-video-r2v",
    "prompt": "The character walks through a rain-soaked night market, camera tracks at shoulder height",
    "image_urls": [
      "https://cdn.example.com/character-front.jpg",
      "https://cdn.example.com/night-market.jpg"
    ],
    "duration": 10,
    "aspect_ratio": "9:16",
    "style_preset": "cyberpunk_neon"
  }'

Reference requirements

Public HTTPS URLs only — expiring signed links and login-gated hosts fail at submission.
Use one image per subject. Character sheets, product cutouts and location plates all work well.
Real-person references should be well lit and front-facing; extreme crops lose identity detail.
Reference images do not add to the bill on this model: billing is duration × per-second price.

Authorizations

Authorization

string

header

required

Use your APIPod API key as a Bearer token in the Authorization header.

Body

application/json

model

string

required

Public APIPod model ID.

Allowed value: "muse-video-r2v"

prompt

string

required

Describe the video to generate. Required, up to 4000 characters.

Required string length: 1 - 4000

image_urls

string[]

required

Required. 1-4 reference images of characters, products or scenes the video should stay consistent with.

Required array length: 1 - 4 elements

Public image URL.

duration

enum<integer>

default:5

Video duration in seconds.

Available options:

5,

10,

20,

30,

40,

50,

60

aspect_ratio

enum<string>

default:16:9

Aspect ratio of the generated video.

Available options:

16:9,

9:16,

1:1,

4:3,

3:4

resolution

enum<string>

default:720p

Output resolution. MU Video currently supports 720p only.

Available options:

720p

style_preset

enum<string>

default:none

Visual style preset applied to the video.

Available options:

none,

cinematic_realistic,

2d_anime,

3d_xianxia,

american_comic,

cyberpunk_neon,

ecommerce_ugc

generate_audio

boolean

default:true

Whether to generate voice and sound. Set to false to mute voices.

Response

200 - application/json

Task accepted

Standard response for task submission

code

integer

required

data

Task Submit Data · object

required

Data content for task submission

Show child attributes

message

string

required

Images

Videos

Tasks

Muse Video Reference to Video

Model at a glance

Parameters

What each reference does

Prompting

Workflow

Reference requirements

Authorizations

Body

Response

​Model at a glance

​Parameters

​What each reference does

​Prompting

​Workflow

​Reference requirements

Authorizations

Body

Response

Model at a glance

Parameters

What each reference does

Prompting

Workflow

Reference requirements