Skip to main content
POST
/
vendors
/
mulerouter
/
v1
/
wan2.5-i2v-spark
/
generation
Create Generation Task
curl --request POST \
  --url https://api.mulerouter.ai/vendors/mulerouter/v1/wan2.5-i2v-spark/generation \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "<string>",
  "image": "<string>",
  "negative_prompt": "<string>",
  "audio": true,
  "audio_url": "<string>",
  "resolution": "720P",
  "duration": 5,
  "prompt_extend": true,
  "seed": 1073741823
}
'
{
  "task_info": {
    "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "status": "pending",
    "created_at": "2023-11-07T05:31:56Z",
    "updated_at": "2023-11-07T05:31:56Z"
  }
}
This is a fine-tuned model by MuleRouter based on the Wan2.5 Image-to-Video architecture. It offers improved quality and performance for specific use cases.

​
Overview

Generate videos from images using the wan2.5-i2v-spark model with optional audio generation.

​
Key Features

  • Image-to-video generation with auto sound or custom audio
  • Multiple resolution options (720P/1080P)
  • 5s or 10s duration
  • 24fps output
  • Fine-tuned for enhanced visual quality

​
Image Requirements

PropertyRequirement
FormatsJPEG, JPG, PNG (no transparency), BMP, WEBP
Dimensions[360, 2000] pixels for both width and height
File SizeMax 10MB
InputPublic URL or Base64 encoded data

​
Audio Features

​
Auto-generated Audio

  • Enabled by default
  • Automatically generates synchronized audio based on video content

​
Custom Audio

  • Supported formats: WAV, MP3
  • Duration: 3-30 seconds
  • Max file size: 15MB

​
Example Requests

​
Basic Image-to-Video

{
  "prompt": "The cat starts running forward",
  "image": "https://example.com/cat.jpg",
  "resolution": "720P",
  "duration": 5
}

​
With Custom Audio

{
  "prompt": "Scene becomes dynamic, clouds drifting",
  "image": "https://example.com/landscape.jpg",
  "audio_url": "https://example.com/ambient.mp3",
  "resolution": "1080P",
  "duration": 10
}

​
With Negative Prompt

{
  "prompt": "Character turns head and smiles",
  "image": "https://example.com/portrait.jpg",
  "negative_prompt": "shaking, distortion",
  "resolution": "720P",
  "duration": 5
}

​
Prompt Tips

For best results:
  • Describe the motion/story you want to see
  • Specify camera movements if needed
  • Include transition descriptions

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
prompt
string
required

Motion/story description for the video (max 2000 characters).

Maximum string length: 2000
​
image
string
required

First-frame image (URL or Base64). Supported formats: JPEG/JPG/PNG/BMP/WEBP, 360-2000px, ≤10MB.

​
negative_prompt
string

Negative prompt describing unwanted content (max 500 characters).

Maximum string length: 500
​
audio
boolean | null
default:true

Enable automatic audio generation. Set to false to force a silent output.

​
audio_url
string<uri> | null

Custom audio file URL (wav/mp3, 3-30s, ≤15MB). Overrides the audio flag.

​
resolution
enum<string>
default:720P

Output resolution tier:

  • 720P
  • 1080P
Available options:
720P,
1080P
​
duration
enum<integer>

Video duration in seconds (24 fps). Supported values 5 or 10.

Available options:
5,
10
​
prompt_extend
boolean
default:true

Enable intelligent prompt rewriting (slightly longer latency, better detail).

​
seed
integer

Random seed [0, 2147483647].

Required range: 0 <= x <= 2147483647

Response

202 - application/json

Accepted - Task created successfully

​
task_info
object