Wan 2.7 Image to Video Serverless API

Animate any image into a cinematic video up to 1080P and 15 seconds with audio sync, first/last frame control, and multi-modal input.

~415.22s
$0.625 - $0.938 per generation
PlaygroundAPI
Pricing
 1import requests
 2import json
 3
 4url = "https://api.segmind.com/v1/wan2.7-i2v"
 5headers = {
 6    "x-api-key": "YOUR_API_KEY",
 7    "Content-Type": "application/json"
 8}
 9
10data = {
11    "prompt": "A gentle breeze moves across the serene lakeside at golden hour, ripples shimmering on the glassy water, pine trees swaying softly, snow-capped mountain in the background, cinematic motion, 4K",
12    "negative_prompt": "blur, distortion, artifacts, watermark, text",
13    "resolution": "720P",
14    "duration": 5
15}
16
17response = requests.post(url, headers=headers, json=data)
18
19if response.status_code == 200:
20    result = response.json()
21    print(json.dumps(result, indent=2))
22else:
23    print(f"Error: {response.status_code}")
24    print(response.text)

API Endpoint

POSThttps://api.segmind.com/v1/wan2.7-i2v

Parameters

promptrequired
string

Describe the motion, action, and scene you want generated. Use specific verbs and cinematic cues for best results — e.g., 'camera slowly pans left as wind moves through the trees'.

Default: "A gentle breeze moves across the serene lakeside at golden hour, ripples shimmering on the glassy water, pine trees swaying softly, snow-capped mountain in the background, cinematic motion, 4K"
audio_urloptional
string (uri)

A publicly accessible audio file URL. The model syncs character motion and lip movement to the audio — useful for voiceover, dialogue, or music-driven animations.

Default: null
durationoptional
integer

Length of the generated video in seconds (2–15). Use shorter durations for quick previews; longer durations for cinematic clips or full scenes.

Default: 5
imageoptional
string (uri)

The first frame of the video — the model animates outward from this image. Works with still photos, illustrations, or AI-generated images.

Default: "https://segmind-resources.s3.amazonaws.com/input/wan27-i2v-input.png"
last_frameoptional
string (uri)

The ending frame of the video. When used alongside First Frame, the model generates a smooth transition between both images — ideal for morph sequences or scene transitions.

Default: null
negative_promptoptional
string

Describe elements to suppress in the output. Common values: 'blurry, distorted hands, watermark, low quality, flickering'.

Default: "blur, distortion, artifacts, watermark, text"
resolutionoptional
string

Output resolution. Use 720P for faster, lower-cost generation; use 1080P for final delivery or high-detail scenes.

Default: "720P"
Allowed values :
"720P""1080P"
seedoptional
integer

Set a fixed seed to reproduce the same output. Leave empty for random generation; useful for A/B testing prompts with a consistent starting point.

Default: null

Response Type

Returns: Video

Common Error Codes

The API returns standard HTTP status codes. Detailed error messages are provided in the response body.

400

Bad Request

Invalid parameters or request format

401

Unauthorized

Missing or invalid API key

403

Forbidden

Insufficient permissions

404

Not Found

Model or endpoint not found

406

Insufficient Credits

Not enough credits to process request

429

Rate Limited

Too many requests

500

Server Error

Internal server error

502

Bad Gateway

Service temporarily unavailable

504

Timeout

Request timed out