Alibaba Wan 2.7 Video Extend

Alibaba Wan 2.7 Video Extend

Playground

Alibaba WAN 2.7 Video Extend extends existing videos with optional last frame control and audio support, supporting 720p/1080p output. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Wan 2.7 Video Extend

Wan 2.7 Video Extend continues an existing video clip with new AI-generated footage, seamlessly picking up from where the original ends. Upload a source video, describe what should happen next, and optionally provide an audio track — the model generates a natural, motion-consistent extension at 720p or 1080p.

• Need to edit a video? Try Wan 2.7 Video Edit
• Need to generate from an image? Try Wan 2.7 Image-to-Video

Why Choose This?

• Seamless video continuation Extends your existing clip with new AI-generated footage that matches the original motion, style, and scene context.

• Prompt-guided extension Describe what should happen next — direct the action, atmosphere, and narrative of the extended segment.

• Audio input support Upload an audio track to guide the rhythm and pacing of the extended video.

• Negative prompt support Specify what to avoid in the extension for more precise output control.

• Prompt expansion Enable enable_prompt_expansion to let the model automatically enrich and optimize your prompt before generation.

• Resolution options Generate extensions at 720p or 1080p to match your delivery requirements.

Parameters

How to Use

1. Upload your video — provide the source clip to extend via URL or drag-and-drop.
2. Write your prompt — describe what should happen next in the scene. Use the Prompt Enhancer for better results.
3. Upload audio (optional) — provide an audio URL to synchronize the extension.
4. Add negative prompt (optional) — specify elements you want to exclude from the extended footage.
5. Select resolution — 720p for standard output, 1080p for higher-quality results.
6. Set duration — choose the total length of the output video in seconds (2–15s).
7. Enable prompt expansion (optional) — let the model automatically enrich your prompt.
8. Set seed (optional) — fix the seed to reproduce a specific result in future runs.
9. Submit — generate, preview, and download your extended video.

Pricing

Billing Rules

• 720p: $0.10 per second
• 1080p: $0.15 per second (1.5× base rate)
• Duration range: 2–15 seconds

Best Use Cases

• Short Film & Narrative — Extend key scenes to develop story beats without reshooting.
• Social Media Content — Lengthen clips to hit optimal duration for Reels, TikTok, and Shorts.
• Marketing & Advertising — Extend product or campaign videos to fill longer ad slots.
• Creative Exploration — Explore alternate continuations of the same source clip with different prompts.
• Audio-Visual Projects — Synchronize extended footage to a music track or voiceover.

Pro Tips

• Be specific about what should happen next — camera movement, subject action, and environmental changes.
• Use negative_prompt to prevent the extension from repeating or contradicting the source footage.
• Enable prompt expansion for shorter or less detailed prompts to get richer output automatically.
• Use 720p to test your extension direction before committing to a 1080p final render.
• Fix the seed once you find a direction you like to iterate consistently.

Notes

• Both video and prompt are required fields; all other parameters are optional.
• Duration range: 2–15 seconds for the total output video length.
• Ensure video and audio URLs are publicly accessible if using links rather than direct uploads.
• Please ensure your content complies with Alibaba’s usage policies.

Related Models

• Wan 2.7 Video Edit — Prompt-driven video editing with multi-image reference support.
• Wan 2.7 Image-to-Video — Animate a reference image into a cinematic video clip.
• Wan 2.7 Text-to-Video — Generate video from text prompts without existing footage.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/alibaba/wan-2.7/video-extend" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "resolution": "720p",
    "duration": 5,
    "enable_prompt_expansion": false,
    "seed": -1
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"