Wan 2.7 Video Edit API

Edit or style-transfer videos using Wan 2.7 with optional reference images

·Features·FAQ

Documentation

Wan 2.7 Wan 2.7 Edit

Prompt

Text prompt describing the desired edit (max 5000 chars)

Input Video *

Video to edit (MP4/MOV, 2-10s, max 100MB)

0/1

Click or drag & dropMP4, WEBM, MOV · Max 100MB

Reference Images

Up to 4 reference images for style/content transfer (JPEG, JPG, PNG, BMP, WEBP, max 20MB each)

0/4

Click or drag & dropPNG, JPG, WEBP, GIF · Max 20MB

Negative Prompt

What to avoid (max 500 chars)

Resolution

Output resolution

Duration

Output duration in seconds (2-10). Omit to keep input duration.

Aspect Ratio

Force output aspect ratio. Omit to match input video.

Audio Setting

Audio handling: auto (model decides) or origin (keep original)

Prompt Extend

LLM-based prompt rewriting. Improves short prompts but adds latency.

Watermark

Add "AI Generated" watermark in lower-right corner

Seed

Random seed for reproducibility (0-2147483647)

Output

Your generated video will appear here

Features

What Wan 2.7 Video Edit API offers

Edit or style-transfer existing videos using text prompts

Optional reference images for guided editing

Multiple aspect ratios and resolution options

Optional seed for reproducibility

REST API with JSON responses

Use cases

Built for

Primary

Style transfer: apply artistic styles to existing video footage

Video enhancement: improve or transform video content with text guidance

Brand adaptation: restyle footage to match brand aesthetics

Creative exploration: experiment with different edit directions on the same source

FAQ

About Wan 2.7 Video Edit API

Wan 2.7 Video Edit lets you transform or style-transfer existing videos using text prompts and optional reference images.

The base model generates new videos from scratch. Video Edit takes an existing video as input and modifies it according to your text prompt and references.