Wan-2.7 Image-to-video
Animates images into videos with first-frame, first-and-last-frame, video continuation, and audio-driven modes.
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/secParameters
What you can set.
| Parameter | What it does | Options |
|---|---|---|
prompt | Text prompt describing the desired video content. Maximum length is 5000 characters. | |
negative_prompt | Text describing elements to exclude from the video. Maximum length is 500 characters. | |
image | First-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_image | Last-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 | |
video | Video 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. | |
audio | Driving 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 | |
resolution | Output video resolution. The video aspect ratio follows the input image or video. Higher resolution increases cost. | 720P 1080P |
duration | Video duration in seconds. Longer duration increases cost. | default 5 |
prompt_extend | Whether to use AI to enhance the prompt for better video quality. Increases generation time. | default True |
seed | Random 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: -1FAQ
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