Happy Horse 1.0 is now on ModelsLab

Try Now
Skip to main content
Available now on ModelsLab · Video Generation

WAN 2.7 Image To VideoImages Animate Instantly

Try WAN 2.7 Image To VideoAPI Documentation

Control Video Generation Precisely

Three Modes

First Last Frame Control

Animate from start image, guide with end frame, or extend videos using WAN 2.7 Image To Video model.

High Resolution

720P 1080P Output

Produce videos at 1280x720 or 1920x1080 resolutions with WAN 2.7 Image To Video API.

Audio Sync

Optional Audio Guidance

Synchronize generation with WAV/MP3 audio inputs via wan 2.7 image to video capabilities.

Examples

See what WAN 2.7 Image To Video can create

Copy any prompt below and try it yourself in the playground.

Cityscape Dawn

“Aerial view of futuristic city skyline at dawn, smooth camera pan over skyscrapers with golden light reflecting on glass towers, cinematic atmosphere, high detail architecture, 1080p, 5 seconds.”

Ocean Waves

“Serene ocean waves crashing on rocky shore, slow motion water spray, dramatic sunset sky with clouds, realistic physics, professional cinematic style, 720p, 8 seconds.”

Mountain Timelapse

“Timelapse of snow-capped mountains under changing skies, clouds rolling over peaks, vibrant colors, steady camera zoom, nature documentary aesthetic, 1080p, 10 seconds.”

Product Reveal

“Sleek metallic watch rotating on reflective surface, soft studio lighting highlighting engravings and texture, slow 360 degree spin, luxury product shot, 1080p, 6 seconds.”

For Developers

A few lines of code.
Video from image. One call.

ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.

  • Serverless: scales to zero, scales to millions
  • Pay per second, no minimums
  • Python and JavaScript SDKs, plus REST API
API Documentation 
import requests


response = requests.post(
    "https://modelslab.com/api/v7/video-fusion/image-to-video",
    json={
  "key": "YOUR_API_KEY",
  "prompt": "15-second cinematic shot of a lone post-apocalyptic soldier in armor and gas mask walking straight toward the camera along a cracked, dusty road between rows of rusted abandoned cars, holding a rifle and tattered flag, slow forward camera movement, smoke and dust drifting from ruined buildings in the background, warm orange sunset light, debris blowing slightly in the wind, realistic gritty atmosphere.",
  "duration": "15",
  "init_image": "https://assets.modelslab.ai/generations/0613c459-6ad7-4ddd-bd8c-65d4c4bde296.jpg",
  "resolution": "720p"
}
)
print(response.json())

FAQ

Common questions about WAN 2.7 Image To Video

Read the docs

WAN 2.7 Image To Video generates MP4 videos from images in first-frame, first+last-frame, or continuation modes. Supports 720P/1080P resolutions and 2-15 second durations. Includes optional audio guidance and prompt expansion.

Provide image URL, prompt, optional last image or audio via WAN 2.7 Image To Video API. Select resolution and duration for output. Model expands prompts automatically for detailed results.

Outputs at 720P (1280x720) or 1080P (1920x1080). Default is 1080P. Choose based on quality needs with wan 2.7 image to video model.

Yes, upload MP4/MOV video (2-10s, max 100MB) for continuation. Combines with prompts and audio using WAN 2.7 Image To Video alternative features.

Provide WAV/MP3 audio (2-30s, max 15MB) to guide motion sync. Enhances WAN 2.7 Image To Video video generation workflows.

Offers first/last frame control, video extension, and audio sync not common in alternatives. Delivers sharp 1080p with character consistency via wan 2.7 image to video api.

Ready to create?

Start generating with WAN 2.7 Image To Video on ModelsLab.

Try WAN 2.7 Image To VideoAPI Documentation