# Wan-2.2 Video Canonical page: https://fuser.studio/models/wan-2-2-video Wan 2.2 Video in Fuser generates video at up to 720p from text, images or video, with Lite (5B) and Pro (14B) versions and a faster turbo mode. ## Specs | Spec | Value | | --- | --- | | Versions | Lite (5B), Pro (14B) | | Inputs | Prompt (text), Image Prompt (image), End Image (image), Video Prompt (video), Negative Prompt (text) | | Output | video | | Resolution | 480p, 580p, 720p | | Aspect ratios | 16:9, 9:16, 1:1 | | Cost | 69–2,667 credits per run | Naturalistic, film-graded clips with camera moves that read as intentional, from a quick draft to a final render, driven by a prompt, a still or footage Creator: Alibaba Group (Tongyi Lab / Wan-AI) [Roll the shot](https://app.fuser.studio) ## How Wan-2.2 Video works Write the shot the way a cinematographer would, or hand it a still. Draft on the fast tiers, then commit the keeper to Pro. ### Frame the shot Write a prompt in subject, action, camera, light order, or add a first frame and an optional end frame. ### Pick a tier and tune motion Choose Lite for drafts or Pro for finals, then set shift and guidance to steer how calm or energetic the move feels. ### Render and iterate Generate 81 to 121 frames at up to 720p, then rerun the keeper on Pro. ## What Wan-2.2 Video is good at Shot-language control, a two-stage Pro engine, first-to-last frame bridging and a ladder from quick drafts to final quality. ### Two-expert Pro refinement The Pro model hands layout and motion to one expert, then texture and lighting to a second, with about 14B parameters active per step. Choose Pro turbo for most text-to-video work: Pro-grade motion with only a slight loss of very fine detail. ### First-to-last frame keyframing On Pro image-to-video, set a start image and an end image and let the model bridge them. Keep both frames in the same scene, light and subject so the transition stays clean instead of morphing. ### Shift control for motion energy Shift runs from 1 to 10 with a default of 5. Try 3-4 for calm, controlled shots and 6-8 for energetic action, and stay below 9 on grounded scenes to avoid erratic movement. ### Fast drafts before the keeper Lite and distilled variants turn around quick concept clips to test prompt, framing and camera language. Draft at 480p, then render the keeper on Pro at 720p. ## Made with Wan-2.2 Video Short, film-lit clips that lean on light, haze, glass, steam and fabric: the textures and camera moves this model handles best. ### Macro liquid dynamics and glass refraction ### Architectural light study with volumetric shadows ### High-contrast choreography and volumetric illumination ### Tactile material physics and atmospheric steam ## What people build with Wan-2.2 Video Directors, photographers, brand editors, social creators and musicians reach for it when a few seconds of believable cinematic motion is the job. ### Directors previsualizing establishing shots Test dolly, orbit and aerial moves with cinematography vocabulary before a shoot or a pitch. Draft quickly on Lite or turbo, then render the chosen angle on Pro. ### Photographers animating stills Turn a sharp keyframe into a short clip that inherits its detail and lighting. Describe only the motion timeline, since the image already supplies the look. ### Brand teams editing existing footage Swap, add or remove objects in a clip with Pro video-to-video, stating what changes and what stays. Keep clips short and uncluttered so edits stay faithful to the source. ### Social creators drafting vertical clips Batch concept clips in 9:16 on Lite or distilled variants, find the idea that moves, then render the winner on Pro. ### Musicians building mood loops and visuals Create atmosphere shots for sleeves, teasers and stage visuals: haze, backlight and slow camera orbits that fit a track's tone. ## Wan 2.2 questions ### What's the difference between Lite and Pro? Lite (5B) is for fast drafts; Pro (14B) is for final quality. Lite is softer, less detailed and tends toward gentler motion. Pro gives better detail, prompt adherence and motion, and is the only tier that supports an end frame and video-to-video. ### Should I use turbo or standard Pro? Use turbo for most text-to-video and image-to-video work: it keeps Pro quality with only a slight loss of very fine detail. Standard Pro is slower, so reserve it for finals where fine detail matters most. Turbo isn't available for video-to-video. ### Which variant should I use to animate a still image? Pro image-to-video with turbo is the default for animating stills. Use standard Pro image-to-video for the highest-quality result or for first-to-last-frame transitions with an end image. Lite image-to-video is for quickly checking whether a motion idea works, but it has no end-frame support. ### How long can a Wan 2.2 clip be? Clips run 81 to 121 frames, which at 24 fps is about 3.4 to 5 seconds. Longer clips raise the chance of identity drift. If you need more than about 5 seconds of continuous action, this isn't the right model. ### Can Wan 2.2 add sound, dialogue or readable text? No. It is weak at legible on-screen text, synced dialogue and generated audio, and it isn't built for native 1080p or higher output. It's also a poor fit for tightly choreographed multi-person scenes, where identity drifts and unrequested actions appear. ### Who made Wan 2.2 and is it open? Wan 2.2 comes from Alibaba's Tongyi Lab (Wan-AI) and was released in July 2025 as an open-weight model under Apache 2.0, succeeding Wan 2.1. ## Try Wan-2.2 Video on Fuser Naturalistic, film-graded clips with camera moves that read as intentional, from a quick draft to a final render, driven by a prompt, a still or footage [Roll the shot](https://app.fuser.studio) ## Related models - [Kling 3.0 Video](https://fuser.studio/models/kling-3-0-video.md) - [MiniMax H3](https://fuser.studio/models/minimax-h3.md) - [Seedance 2](https://fuser.studio/models/seedance-2.md) - [Gemini Omni Video](https://fuser.studio/models/gemini-omni-video.md) - [Grok Imagine](https://fuser.studio/models/grok-imagine.md) - [Kling O3 Edit](https://fuser.studio/models/kling-o3-edit.md) Node reference: [Wan-2.2 Video docs](https://docs.fuser.studio/docs/nodes/video/wan-2-2-video.md) ## More articles - [Best Open-Source Video Models (2026): Wan 2.2, MiniMax H3, LTX-2.5](https://fuser.studio/articles/best-open-source-video-models.md)