Wan 2.7 API

Text to VideoImage to VideoReference to VideoVideo to Video

Advanced video generation and editing with text-to-video, image-to-video, reference-to-video, and video editing modes.

Mode

Generation mode: t2v, i2v, or r2v

Prompt

Text prompt (max 5000 chars). Required for T2V and R2V. For R2V, use "Image 1", "Video 1" identifiers.

Negative Prompt

What to avoid (max 500 chars)

Resolution

Output resolution

Duration

Output duration in seconds (2-15)

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 API offers

Text-to-video, image-to-video, and reference-to-video modes

Video editing with text prompts and reference images

Multiple aspect ratios and resolution options

Optional seed for reproducibility

REST API with JSON responses

Use cases

Primary

Marketing: generate video clips from text descriptions or reference images

Content creation: create social media videos with text-to-video

Character-driven shorts: reference-to-video with image and video references

Video editing: transform existing videos with text-guided editing

FAQ

Wan 2.7 supports text-to-video, image-to-video, reference-to-video, and video-to-video editing modes.

Wan 2.7 adds advanced editing capabilities and reference-to-video improvements over the 2.6 generation.