Wan 3.0 – Image to Video
Image-to-Video model by Alibaba — China.
Turn a still frame into a finished shot with synced audio, anywhere from 2 to 30 seconds. An optional end frame lets you decide where the shot lands.
Wan 3.0 is Alibaba's image-to-video model, and it holds motion and character identity together well across longer takes than most models allow. It is a strong pick when you want a full shot rather than a short loop: pick the clip length, pick the frame shape or keep the one your source image already has, and let it generate dialogue and ambience along with the picture.
Practical specs for planning a generation in LORY. These details come from the model contract we use when routing a request.
Try Wan 3.0 – Image to Video on LORY
Start with free welcome credits — no subscription, and we never ask for payment info during your trial. Pay only when you decide to top up.
Wan 2.5 Preview – Image to Video
Image-to-video with 5s/10s outputs up to 1080p. Includes audio support.
Wan Pro – Image to Video
Wan 2.1 Pro image-to-video: ~6s 1080p @30fps from a source image.
HappyHorse-1.0 – Reference to Video
Shape a single video shot from several reference images with Happy Horse 1.0. It works well when you want tighter control over characters, styling, or scene details while still generating one finished clip with synced audio.
MiniMax H3 Max – Image to Video
Top-ranked image-to-video model with native audio, first and last frame control, and strong prompt adherence.
Grok Imagine – Reference to Video
Build a single video shot from several reference images with Grok Imagine. It is a strong choice when you want to combine subject, setting, and style references in one clip, with synced audio included.
Veo 3.1 Lite – Image to Video
Animate a single image into a short Veo 3.1 Lite clip with optional native audio.