Models / Alibaba
Video

Wan 2.7 Image-to-Video

Image-to-video generation with first/last frame control and 3x3 grid workflows

About model

On Together AI, Wan 2.7 Image-to-Video costs $0.10 per video.

Wan 2.7 Image-to-Video animates still images and supports first-frame, first-and-last-frame, and video continuation workflows, along with 3x3 grid-to-video generation and audio-video synchronization, producing 720P or 1080P outputs up to 15 seconds.

Duration

2-15s

Supported generation length

Control

Workflows

First/last frame & continuation

Audio-Video

Sync

Synchronized generation

Model key capabilities
  • Advanced Controls: First-frame, last-frame, and video continuation workflows
  • Audio-Video Sync: Supports audio-video synchronized generation
  • Storyboarding: Supports 3x3 grid-to-video generation
  • API usage

    • cURL
    • Python
    • Typescript

    Endpoint:

    Wan-AI/wan2.7-i2v

    curl --request POST \
      --url https://api.together.ai/v2/videos \
      --header "Authorization: Bearer $TOGETHER_API_KEY" \
      --header "Content-Type: application/json" \
      --data '{
        "model": "Wan-AI/wan2.7-i2v",
        "prompt": "some penguins building a snowman"
      }'
    
    from together import Together
    
    client = Together()
    
    # Create a video generation job
    job = client.videos.create(
        prompt="A serene sunset over the ocean with gentle waves",
        model="Wan-AI/wan2.7-i2v"
    )
    
    import Together from "together-ai";
    
    const together = new Together();
    
    async function main() {
      // Create a video generation job
      const job = await together.videos.create({
        prompt: "A serene sunset over the ocean with gentle waves",
        model: "Wan-AI/wan2.7-i2v"
      });
    
  • Model card

    Architecture Overview:
    • Image-to-video (I2V) generation model
    • Advanced Controls: Supports first-frame, first-and-last-frame, and video continuation workflows
    • Audio-Video Sync: Enables synchronized generation via audio inputs
    • 720P and native 1080P output

    Performance Characteristics:
    • Supports 2-15 second generation

    ‍

  • Prompting

    Together AI API Access:
    • Access Wan 2.7 Image-to-Video via Together AI APIs using the endpoint Wan-AI/wan2.7-i2v
    • Authenticate using your Together AI API key in request headers
    • Available on Together AI serverless infrastructure

    ‍

  • Applications & use cases

    Creative Production:
    • Audio-video synchronized generation
    • First-frame, last-frame, and continuation workflows
    • Storyboard-driven 3x3 grid-to-video generation

    ‍

  • Model provider
    Alibaba
  • Type
    Video
  • Main use cases
    Image-to-Video
  • Resolution/Duration
    720p, 1080p / 2-15s
  • Deployment
  • Price

    $0.10 / video

  • Input modalities
    Text
    Image
    Video
    Audio
  • Output modalities
    Video
  • Category
    Video