Wan-2.7 Video-edit
Edits videos using text instructions, reference images, and style transfer with multi-modal input support.
What it does
Wan-2.7 Video-edit, in practice.
Wan 2.7 Video-edit edits an input video from text instructions and optional reference media. Use it for style transfer, subject-preserving edits, commercial polish, and short creative transformations.
- Video editing with text control: Provide a source video and describe the target look or action.
- Optional reference media: Add a single reference image, multiple reference images, or driving audio when the edit needs extra visual or motion guidance.
- Native output tiers: Choose `720P` or `1080P` for Wan 2.7 native video-edit output.
- Common aspect ratios: Supports 16:9, 9:16, 1:1, 4:3, and 3:4.
Run Wan-2.7 Video-edit
from $0.15/secParameters
What you can set.
| Parameter | What it does | Options |
|---|---|---|
prompt | Text instruction describing the desired edit. Maximum length is 5000 characters. | |
negative_prompt | Text describing elements to exclude from the video. Maximum length is 500 characters. | |
video | URL of the video to edit. Supported formats: mp4, mov. Duration: 2–10 seconds. Maximum file size: 100 MB. | |
images | Reference image URLs for style or content guidance. Up to 3 images. Supported formats: JPEG, JPG, PNG (transparent channel not supported), BMP, WEBP. Width and height must each be between 240 and 8000 pixels. Aspect ratio must be between 1: | |
resolution | Output video resolution. Higher resolution increases cost. | 720P 1080P |
ratio | Aspect ratio of the output video. When omitted, the output follows the input video's aspect ratio. | 16:9 9:16 1:1 4:3 3:4 |
duration | Output video duration in seconds. Set to 0 or omit to match the input video duration. When set to a positive value, the output is clipped from the start of the input video. Range: 2–10. | |
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.
Turn the source clip into a cinematic product shot with smooth camera movement and richer studio lighting.
negative_prompt: blurry, jittery, distorted text, low qualityresolution: 1080Pratio: 16:9duration: 5prompt_extend: Trueseed: -1FAQ
Short answers.
How much does Wan-2.7 Video-edit 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 Video-edit 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 Video-edit for everything else it does well.
What does Wan-2.7 Video-edit take as input?
It is a video-to-video model. Edits videos using text instructions, reference images, and style transfer with multi-modal input support.
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