# Wan 2.7

> Wan 2.7 is available on Artifio.ai — a unified AI workspace with a single pay-as-you-go wallet.

- Canonical page: https://artifio.ai/models/wan-2-7-image-to-video
- Run it: https://artifio.ai/create/wan-2-7-image-to-video
- Modality: image to video
- Model brand: Wan
- Pricing: from about $0.080 per second (exact cost shown in the workspace before you confirm; varies with selected options)
- Typical generation time: ~300s (catalogue estimate)
- Full pricing table: https://artifio.ai/pricing/models

## About Wan 2.7

Wan 2.7 image-to-video (Wan2.7-i2v) is one of the four models in Alibaba's Wan2.7-Video release of April 2026. It animates a still image into a clip with synchronized audio, and the documented feature set goes beyond simple animation: it covers first-frame-to-video, first-and-last-frame-to-video, and video continuation, so an image can anchor the start of a shot, bookend it, or extend footage that already exists.

It is currently one of the stronger image-to-video systems in blind testing; as of July 2026 the Artificial Analysis image-to-video arena ranks it fourth with an Elo of 1098. On Artifio it sits in one workspace with 100+ other models, paid per generation.

## Features

- Animates a source image into 720p or 1080p video at 30 fps with generated audio.
- Any integer duration from 2 to 15 seconds.
- Three documented modes: first-frame-to-video, first-and-last-frame-to-video, and video continuation.
- Inherits the Wan 2.7 generation's natural-language direction over actions, style, and camera movement.
- Voice and sound generation with lip movements synced to dialogue, per the generation's release notes.

## What people use it for

- Turning product stills and key art into short animated spots with sound.
- Interpolating between a designed opening frame and closing frame for controlled shots.
- Extending an existing clip with the continuation mode instead of regenerating from scratch.
- Giving a portrait a spoken line with synced lips and voice.

## Reported strengths

- Fourth place on the Artificial Analysis image-to-video arena as of July 2026, a 198-point Elo jump over Wan 2.6 in the same listing.
- First-and-last-frame control gives more compositional authority than single-image animation.
- Native audio removes the separate sound design pass for simple clips.

## Reported limitations

- Resolution is capped at 1080p and clips at 15 seconds.
- It trails Seedance 2.0 on the image-to-video arena (Elo 1098 versus 1195 as of July 2026).
- The model is hosted-only; no Wan 2.7 weights have been published on the Wan GitHub organization.

## Sources

1. Alibaba unveils Wan2.7-Video to elevate creators from executors to directors (Alibaba Cloud): https://www.alibabacloud.com/blog/alibaba-unveils-wan2-7-video-to-elevate-creators-from-executors-to-directors_603009
2. Video generation, Alibaba Cloud Model Studio documentation (Alibaba Cloud): https://www.alibabacloud.com/help/en/model-studio/use-video-generation
3. Image to video leaderboard (Artificial Analysis): https://artificialanalysis.ai/video/leaderboard/image-to-video
4. Wan2.2: open and advanced large-scale video generative models (GitHub (Wan-Video)): https://github.com/Wan-Video/Wan2.2

---

About Artifio.ai: 100+ AI image, video, and audio models in one workspace with a single shared wallet — no per-model subscriptions. This is the markdown rendition of https://artifio.ai/models/wan-2-7-image-to-video for AI assistants and crawlers; the HTML page is canonical.