Photo to video that keeps the face
Animate a portrait from its first frame and the person still looks like themselves when they move, smile and wave.
AI Zombie Video2 photos · 15s · from 121 credits
Burning Bridges AI1 photo · 15s · from 121 credits
Wipe Me Down Dance AI1 photo · 13s · from 105 credits
AI Vampire Transformation1 photo · 5s · from 21 credits
La Tormenta de Arena AI2 photos · 15s · from 121 credits
AI Witch Transformation1 photo · 5s · from 21 creditsWan 3.0 is the successor to Wan 2.7. It turns a prompt, a starting photo or a set of reference images into video with steady faces and natural movement, adds an optional soundtrack, and now goes all the way down to 480p for cheap drafts — or up to 1080p for the final cut.
Three input modes, one model
Write a prompt only, upload a first frame (and optionally a last frame), or switch to reference mode with up to 10 images.
Tell Wan 3.0 what moves and how the camera behaves — "he smiles and waves at the camera, gentle breeze".
480p, 720p or 1080p; any length from 2 to 15 seconds; audio on or off at the same price.
Your MP4 is saved to your library as soon as it is ready.
Animate a portrait from its first frame and the person still looks like themselves when they move, smile and wave.
Reference mode combines characters, outfits and locations from up to 10 images in one shot.
Wan 3.0 adds 480p at 20 credits per second — half the price of 720p, ideal for testing ideas.
Switch on audio to get ambience and effects generated with the video, at no extra cost.
20 / 40 / 80 credits per second at 480p / 720p / 1080p.
Durations start at 2 seconds, so a quick 480p test costs just 40 credits.
Credits are returned automatically if a generation fails.
20 / 40 / 80 credits per second at 480p / 720p / 1080p, audio included at no extra cost. Failed generations are refunded automatically.
480p drafts to 1080p finals, with optional sound. Pay per second.