Wan 2.7 - Image to Video

Animate images into video using Alibaba Cloud's Wan 2.7 model. A single multimodal input protocol covers three tasks, selected with promptObject.mode:

🖼️ first_frame - Animate a single image (optional driving audio for lip-sync)
🎬 first_last - Keyframe between a first and a last image
🎞️ continuation - Extend an existing video clip (optional target last frame)

Note: Image, video, and audio files must first be uploaded using the Asset API before processing. The imageUrl, imageTailUrl, videoUrl, and audioUrl parameters should contain the paths returned from the Asset API upload.

Endpoint

POSThttps://api.1min.ai/api/features

Request Headers

Field	Value
API-KEY	`<api-key>`
Content-Type	`application/json`

Request Parameters

Field Name	Type	Example	Description	Required
type	string	IMAGE_TO_VIDEO	Feature identifier	✔️
model	string	wan2.7-i2v	AI model to use	✔️
conversationId	string	IMAGE_TO_VIDEO	Conversation context	✔️
promptObject.prompt	string	The camera slowly pans across the room as the cat wakes up	Text description of the desired motion/scene. Max 5000 characters	✔️
promptObject.mode	string	first_frame	Generation mode: `first_frame`, `first_last`, or `continuation`. Determines which media fields below are required — see Mode-Specific Fields	✔️
promptObject.imageUrl	string	images/example.jpg	S3 path to the first-frame image, from Asset API upload. Required for `first_frame` and `first_last`. Cannot be provided together with `videoUrl`	Conditional
promptObject.imageTailUrl	string	images/end-frame.jpg	S3 path to the last-frame image, from Asset API upload. Required for `first_last`; optional target last frame for `continuation`; unused for `first_frame`	Conditional
promptObject.videoUrl	string	videos/source-clip.mp4	S3 path to the source video clip to extend, from Asset API upload. Required for `continuation`. Cannot be provided together with `imageUrl`	Conditional
promptObject.audioUrl	string	audio/driving-audio.mp3	S3 path to a driving audio track, from Asset API upload. Used as a lip-sync/timing source for `first_frame` and `first_last`; if omitted, Wan generates matching audio automatically. Ignored for `continuation`	❌
promptObject.resolution	string	720P	Output resolution: `720P` or `1080P`. Higher resolution costs more credits	✔️
promptObject.duration	number	5	Video duration in seconds. Integer from `2` to `15`. For `continuation`, the total duration includes the uploaded source clip. Credits are charged per second at the selected resolution	✔️
promptObject.prompt_extend	boolean	true	Enables prompt rewriting. When enabled, an LLM rewrites the input prompt to improve generation quality	❌
promptObject.negativePrompt	string	blurry, low quality	Text describing what to avoid in the video. Max 500 characters	❌
promptObject.seed	number	2026	Random seed for reproducible generation. Integer from `0` to `2147483647`. Omit for a random result	❌
promptObject.watermark	boolean	false	Whether to add an AI-generated watermark to the output video	❌

imageUrl and videoUrl are mutually exclusive — a request that sets both is rejected. At least one of imageUrl or videoUrl must be provided.

Mode-Specific Fields

`first_frame` - Animate a single image

Field Name	Required	Notes
promptObject.imageUrl	✔️	First frame to animate
promptObject.audioUrl	❌	Optional driving audio for lip-sync; auto-generated if omitted

`first_last` - Keyframe between two images

Field Name	Required	Notes
promptObject.imageUrl	✔️	First frame
promptObject.imageTailUrl	✔️	Last frame
promptObject.audioUrl	❌	Optional driving audio for lip-sync; auto-generated if omitted

`continuation` - Extend an existing video clip

Field Name	Required	Notes
promptObject.videoUrl	✔️	Source clip to extend (2-10s)
promptObject.imageTailUrl	❌	Optional target last frame to guide the continuation

Media Requirements

Images (imageUrl, imageTailUrl): JPEG, PNG (alpha channel not supported), BMP, or WEBP. Minimum 240x240px. Max 20MB.
Video (videoUrl, continuation mode only): MP4 or MOV. 2-10 seconds. Max 100MB. The source clip counts toward the duration total.
Audio (audioUrl): WAV or MP3. 2-30 seconds. Max 15MB. If longer than the video duration, only the leading portion is used; if shorter, the remaining video is silent (e.g. 3s audio with a 5s video produces 3s of sound followed by 2s of silence).

Code Examples

cURL
JavaScript
Python

curl --location 'https://api.1min.ai/api/features' \
--header 'API-KEY: <api-key>' \
--header 'Content-Type: application/json' \
--data '{
"type": "IMAGE_TO_VIDEO",
"model": "wan2.7-i2v",
"conversationId": "IMAGE_TO_VIDEO",
"promptObject": {
  "mode": "first_frame",
  "imageUrl": "images/2026_07_21_test-wan-first-frame.png",
  "prompt": "The perspective slowly rotates and zooms out, revealing the softly lit living room and the sleeping cat.",
  "resolution": "720P",
  "duration": 5,
  "prompt_extend": true,
  "negativePrompt": "abrupt cut, mismatched lighting"
}
}'

fetch('https://api.1min.ai/api/features', {
method: 'POST',
headers: {
  'Content-Type': 'application/json',
  'API-KEY': 'YOUR_API_KEY'
},
body: JSON.stringify({
  type: 'IMAGE_TO_VIDEO',
  model: 'wan2.7-i2v',
  conversationId: 'IMAGE_TO_VIDEO',
  promptObject: {
    mode: 'first_frame',
    imageUrl: 'images/2026_07_21_test-wan-first-frame.png',
    prompt: 'The perspective slowly rotates and zooms out, revealing the softly lit living room and the sleeping cat.',
    resolution: '720P',
    duration: 5,
    prompt_extend: true,
    negativePrompt: 'abrupt cut, mismatched lighting'
  }
})
})

import requests

url = "https://api.1min.ai/api/features"
headers = {
"Content-Type": "application/json",
"API-KEY": "YOUR_API_KEY"
}

data = {
"type": "IMAGE_TO_VIDEO",
"model": "wan2.7-i2v",
"conversationId": "IMAGE_TO_VIDEO",
"promptObject": {
  "mode": "first_frame",
  "imageUrl": "images/2026_07_21_test-wan-first-frame.png",
  "prompt": "The perspective slowly rotates and zooms out, revealing the softly lit living room and the sleeping cat.",
  "resolution": "720P",
  "duration": 5,
  "prompt_extend": True,
  "negativePrompt": "abrupt cut, mismatched lighting"
}
}

response = requests.post(url, headers=headers, json=data)

Example: First + Last Frame (Keyframe)

cURL
JavaScript
Python

curl --location 'https://api.1min.ai/api/features' \
--header 'API-KEY: <api-key>' \
--header 'Content-Type: application/json' \
--data '{
"type": "IMAGE_TO_VIDEO",
"model": "wan2.7-i2v",
"conversationId": "IMAGE_TO_VIDEO",
"promptObject": {
  "mode": "first_last",
  "imageUrl": "images/test-wan-first-frame.png",
  "imageTailUrl": "images/test-wan-last-frame.webp",
  "prompt": "A dreamlike dissolve effect merges the neon-lit alley with the plush living room, colors shifting from cool blue to warm teal.",
  "resolution": "1080P",
  "duration": 5,
  "seed": 2026,
  "prompt_extend": false
}
}'

fetch('https://api.1min.ai/api/features', {
method: 'POST',
headers: {
  'Content-Type': 'application/json',
  'API-KEY': 'YOUR_API_KEY'
},
body: JSON.stringify({
  type: 'IMAGE_TO_VIDEO',
  model: 'wan2.7-i2v',
  conversationId: 'IMAGE_TO_VIDEO',
  promptObject: {
    mode: 'first_last',
    imageUrl: 'images/test-wan-first-frame.png',
    imageTailUrl: 'images/test-wan-last-frame.webp',
    prompt: 'A dreamlike dissolve effect merges the neon-lit alley with the plush living room, colors shifting from cool blue to warm teal.',
    resolution: '1080P',
    duration: 5,
    seed: 2026,
    prompt_extend: false
  }
})
})

import requests

url = "https://api.1min.ai/api/features"
headers = {
"Content-Type": "application/json",
"API-KEY": "YOUR_API_KEY"
}

data = {
"type": "IMAGE_TO_VIDEO",
"model": "wan2.7-i2v",
"conversationId": "IMAGE_TO_VIDEO",
"promptObject": {
  "mode": "first_last",
  "imageUrl": "images/test-wan-first-frame.png",
  "imageTailUrl": "images/test-wan-last-frame.webp",
  "prompt": "A dreamlike dissolve effect merges the neon-lit alley with the plush living room, colors shifting from cool blue to warm teal.",
  "resolution": "1080P",
  "duration": 5,
  "seed": 2026,
  "prompt_extend": False
}
}

response = requests.post(url, headers=headers, json=data)

Example: Video Continuation

cURL
JavaScript
Python

curl --location 'https://api.1min.ai/api/features' \
--header 'API-KEY: <api-key>' \
--header 'Content-Type: application/json' \
--data '{
"type": "IMAGE_TO_VIDEO",
"model": "wan2.7-i2v",
"conversationId": "IMAGE_TO_VIDEO",
"promptObject": {
  "mode": "continuation",
  "videoUrl": "videos/wan2.7-i2v-video-continuation.mp4",
  "prompt": "The man looks down at the wooden box on the ground. He bends over, carefully opens the lid, and stares at the contents.",
  "resolution": "1080P",
  "duration": 14,
  "prompt_extend": true
}
}'

fetch('https://api.1min.ai/api/features', {
method: 'POST',
headers: {
  'Content-Type': 'application/json',
  'API-KEY': 'YOUR_API_KEY'
},
body: JSON.stringify({
  type: 'IMAGE_TO_VIDEO',
  model: 'wan2.7-i2v',
  conversationId: 'IMAGE_TO_VIDEO',
  promptObject: {
    mode: 'continuation',
    videoUrl: 'videos/wan2.7-i2v-video-continuation.mp4',
    prompt: 'The man looks down at the wooden box on the ground. He bends over, carefully opens the lid, and stares at the contents.',
    resolution: '1080P',
    duration: 14,
    prompt_extend: true
  }
})
})

import requests

url = "https://api.1min.ai/api/features"
headers = {
"Content-Type": "application/json",
"API-KEY": "YOUR_API_KEY"
}

data = {
"type": "IMAGE_TO_VIDEO",
"model": "wan2.7-i2v",
"conversationId": "IMAGE_TO_VIDEO",
"promptObject": {
  "mode": "continuation",
  "videoUrl": "videos/wan2.7-i2v-video-continuation.mp4",
  "prompt": "The man looks down at the wooden box on the ground. He bends over, carefully opens the lid, and stares at the contents.",
  "resolution": "1080P",
  "duration": 14,
  "prompt_extend": True
}
}

response = requests.post(url, headers=headers, json=data)

Interactive Playground

API Playground

https://api.1min.ai/api/features

AI Model *

Mode *

first_frame: animate one image. first_last: keyframe between two images. continuation: extend a video clip

First Frame Image *

Path to the first-frame image uploaded via Asset API

Motion Description *

Driving Audio (S3 path)

Optional lip-sync/timing audio uploaded via Asset API (WAV/MP3, 2-30s, up to 15MB)

Resolution *

Duration (seconds) *

Video duration in seconds (2-15). For continuation, includes the source clip

Enhance Prompt

Rewrite the prompt with an LLM to improve generation quality

Negative Prompt

Seed

Fixed seed for reproducible generation. Leave empty for random

Watermark

Add an AI-generated watermark to the output video

Generated cURL Command:

curl -X POST "https://api.1min.ai/api/features" \
  -H "API-KEY: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
  "type": "IMAGE_TO_VIDEO",
  "model": "wan2.7-i2v",
  "conversationId": "IMAGE_TO_VIDEO",
  "promptObject": {
    "mode": "first_frame",
    "imageUrl": "images/2026_07_21_test-wan-first-frame.png",
    "prompt": "The perspective slowly rotates and zooms out, revealing the softly lit living room and the sleeping cat.",
    "resolution": "720P",
    "duration": 5,
    "prompt_extend": true
  }
}'

Response

{
"aiRecord": {
  "uuid": "55a361d6-e126-4643-b928-f64634e278a6",
  "userId": "2f57c2a4-1fff-48e7-972f-3c1d6c59bced",
  "teamId": "eb48d89f-1bb7-4d82-9b25-481971a0e97a",
  "teamUser": {
    "teamId": "eb48d89f-1bb7-4d82-9b25-481971a0e97a",
    "userId": "2f57c2a4-1fff-48e7-972f-3c1d6c59bced",
    "userName": "John",
    "userAvatar": "https://lh3.googleusercontent.com/a/ACg8ocLqgsNsHRfmWF9d-E1RvJetVsEzxNOsOg-NXWNTpMxLDPJbwELI=s96-c",
    "status": "ACTIVE",
    "role": "ADMIN",
    "creditLimit": 100000000,
    "usedCredit": 17872338,
    "createdAt": "2025-11-25T11:04:08.620Z",
    "createdBy": "SYSTEM",
    "updatedAt": "2025-11-26T09:20:02.221Z",
    "updatedBy": "SYSTEM"
  },
  "model": "wan2.7-i2v",
  "type": "IMAGE_TO_VIDEO",
  "metadata": {
    "credit": 6300000,
    "duration": 14,
    "resolution": "1080P",
    "executionTime": 136.855
  },
  "rating": null,
  "feedback": null,
  "conversationId": null,
  "status": "SUCCESS",
  "createdAt": "2026-07-25T15:50:25.889Z",
  "aiRecordDetail": {
    "promptObject": {
      "mode": "continuation",
      "prompt": "The man looks down at the wooden box on the ground. He bends over, carefully opens the lid, and stares at the contents.",
      "duration": 14,
      "videoUrl": "development/videos/2026_07_25_22_50_09_316_wan2.7-i2v-video-continuation.mp4",
      "resolution": "1080P",
      "prompt_extend": true
    },
    "resultObject": [
      "development/videos/2026_07_25_22_52_35_715_748807.mp4"
    ],
    "responseObject": {}
  },
  "additionalData": null,
  "temporaryUrl": "https://s3.us-east-1.amazonaws.com/asset.1min.ai/development/videos/2026_07_25_22_52_35_715_748807.mp4?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=..."
}
}

Endpoint​

Request Headers​

Request Parameters​

Mode-Specific Fields​

first_frame - Animate a single image​

first_last - Keyframe between two images​

continuation - Extend an existing video clip​

Media Requirements​

Code Examples​

Example: First + Last Frame (Keyframe)​

Example: Video Continuation​

Interactive Playground​