Wan 2.1 LoRA text-to-video turns a prompt into a 5 or 10 second clip at 480p or 720p with up to three of your own LoRA files loaded on Alibaba's 14B model. Steps, guidance and flow shift are open, and nothing is filtered.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Output5s
gondola-velvet-mask No LoRA, the base model alone at 720p. A tracking shot alongside the gondola; she holds the camera with a long look while the lanterns slide past. The prompt also asked her to lift the mask away and she kept it on, so put the one action you need first and keep it simple.
- 210901
- 720p
- 16:9
- Output5s
bridge-ribbon-flat-color A Wan 2.1 flat-colour LoRA at 1 with its trigger words. The same prompt and seed without the LoRA came back as live-action footage of the couple; with it the moment is cel-shaded animation, and she unties his mask ribbon until their foreheads meet.
- 210903
- 720p
- 16:9
- Output10s
maskmaker-gold-brush No LoRA, 480p at the 10-second length (832 x 480). The workshop, the lantern and the brush dipping into gold paint hold steady for the whole clip. The prompt also asked him to paint a white mask and raise it beside his face; instead he wears a gold mask from the first frame, so keep to one simple action even at ten seconds.
- 211002
- 480p
- 16:9
This example starts at $0.24 per request. The Playground updates the estimate when you change the settings.