minimaxiH3 Get access
QwenImage-to-videoVendor content policy applies

Wan-2.7 Image-to-video

Animates images into videos with first-frame, first-and-last-frame, video continuation, and audio-driven modes.

$0.15per secondStarting price at the base resolution and quality tier.
$1.20Typical 8-second clip at the base tier. Longer or higher-resolution outputs scale with duration and tier.
Pay per useBilled per request from your balance. No subscription, no minimum.
Sample output · prompt: “A deep canyon split by massive cracks begins to glow as powerful light erupts from within the fissures, beams of radiant energy shooting upward, dust swirling through the air, the camera slowly rising through the canyon,…”

What it does

Wan-2.7 Image-to-video, in practice.

Alibaba WAN 2.7 Image-to-Video animates images into videos with multiple generation modes: first-frame, first-and-last-frame, video continuation, and audio-driven animation.

  • Multiple animation modes: Start from a single image, control both start and end frames, or extend an existing video clip.
  • Audio-driven generation: Provide a driving audio file to generate lip-synced or action-matched video content.
  • Multi-shot support: Generate multi-shot narratives with natural transitions and scene variety.
  • Up to 15 seconds: Generate videos from 2 to 15 seconds at 720P or 1080P resolution.
  • Super Resolution options: Choose `1080P-SR` or `1440P-SR` when you need a sharper final video with cleaner edges and improved texture detail.
  • Creators who want to bring still images to life with motion and sound.

Run Wan-2.7 Image-to-video

from $0.15/sec
Drop an image hereor click to choose a fileFiles stay in your project. Nothing is trained on.
resolution
Invite code opens Chat with this model loaded. No code yet? Join the waitlist — we count which models people ask for.

Parameters

What you can set.

ParameterWhat it doesOptions
promptText prompt describing the desired video content. Maximum length is 5000 characters.
negative_promptText describing elements to exclude from the video. Maximum length is 500 characters.
imageFirst-frame image URL for image-based generation modes. The video starts from this image. Supported formats: JPEG, JPG, PNG (transparent channel not supported), BMP, WEBP. Width and height must each be between 240 and 8000 pixels. Aspect ra
last_imageLast-frame image URL for end-frame control. Use it with `image` to generate a start-to-end transition, or with `video` to continue a clip toward a target ending frame. Supported formats: JPEG, JPG, PNG (transparent channel not supported), B
videoVideo clip URL for video continuation modes. The model extends the content of this clip. `last_image` can be added for end-frame control. Supported formats: mp4, mov. Duration: 2–10 seconds. Maximum file size: 100 MB.
audioDriving audio URL for image-based generation modes. The model uses this audio to drive lip-sync or action-matched video generation. Supported only with `image`, or with `image` and `last_image`. Supported formats: wav, mp3. Duration: 2–30 s
resolutionOutput video resolution. The video aspect ratio follows the input image or video. Higher resolution increases cost.720P 1080P
durationVideo duration in seconds. Longer duration increases cost.default 5
prompt_extendWhether to use AI to enhance the prompt for better video quality. Increases generation time.default True
seedRandom seed for video generation. Range: 0 to 2147483647. Use -1 for a random seed.default -1

Sample prompt

The prompt behind the sample.

A deep canyon split by massive cracks begins to glow as powerful light erupts from within the fissures, beams of radiant energy shooting upward, dust swirling through the air, the camera slowly rising through the canyon, cinematic lighting, epic scale, ultra-realistic.
resolution: 1080Pduration: 5prompt_extend: Truewatermark: seed: -1

FAQ

Short answers.

How much does Wan-2.7 Image-to-video cost?

Pricing starts at $0.15 per second of video at the base resolution; higher resolutions and longer durations cost more. An 8-second clip at the base tier is about $1.20. Usage is billed per request from your balance — no subscription.

Does Wan-2.7 Image-to-video run uncensored here?

No. Qwen applies its own content policy to this model regardless of where it is called from. For a route without an extra platform filter use Uncensored MiniMax H3; this page lists Wan-2.7 Image-to-video for everything else it does well.

What does Wan-2.7 Image-to-video take as input?

It is a image-to-video model. Animates images into videos with first-frame, first-and-last-frame, video continuation, and audio-driven modes.

How do I use it?

Enter an invite code to open Chat with the model loaded, or join the waitlist. We open seats in batches and track which models are requested most.

Related

Models people compare with this one.

Run Wan-2.7 Image-to-video.

Invite code opens Chat with the model loaded. No code — join the waitlist and we will count the request.

Get access Browse models