Wan 2.2 LoRA text-to-video turns a written scene into a 5 or 8 second clip on Alibaba's Wan 2.2 A14B model, at 480p or 720p in landscape 16:9 or portrait 9:16. Load up to three of your own LoRAs on the high-noise pass, the low-noise pass or both, with no filter on the prompt, the weights or the result.
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
cabin-fire-vintage-lora A single-file style LoRA in loras at scale 1, with its trigger words opening the prompt. Against the same prompt and seed without it, the LoRA pulled the whole clip into dark brown film tones and changed the woman's face.
- 510531
- 720p
- 16:9
- Output5s
cabin-run-followcam-lora A paired camera LoRA: the high-noise file in high_noise_loras, the low-noise file in low_noise_loras, both at 1, with its trigger word first in the prompt. The same prompt and seed without the pair gave a clearly different clip, which is the check that both files loaded.
- 510532
- 720p
- 16:9
- Output5s
porch-swing-storm-vintage-lora Portrait 9:16 with the Vintage Cinematic LoRA at 0.7, lower than the fireside clip: the faces stay clearer and the brown film tone is lighter.
- 530533
- 720p
- 9:16
This example starts at $0.048 per output second. The Playground updates the estimate when you change the settings.