Alibaba Wan 2.7 image-to-video, from a single still
Wan 2.7 is Alibaba's image-to-video model: upload a still and describe the motion you want out of it. Like HappyHorse it requires an image, and it takes a negative prompt, which is the practical lever for keeping unwanted movement out of a shot.
Plan limits apply on top of these — see pricing.
Written for this model in particular. Open one in the composer and edit it from there.
“Slow push in on the subject, background falling out of focus, everything else held still”
Try this prompt“Wind moving through the trees behind the subject while the subject stays motionless”
Try this prompt“The camera cranes up and back to reveal the wider room”
Try this promptLong-form AI video with reference control and native audio
ByteDance4K AI video with a lockable camera and multi-subject references
ByteDanceThe cheapest way to test a video idea before committing credits
GoogleGoogle's flagship video model, with synchronized audio and zero data retention
GoogleVeo 3.1 quality at lower latency, for iterating on a shot
Black Forest LabsBlack Forest Labs' first video model, with a fast draft mode
50 free credits on sign-up, no credit card required.