Use the LoRA Library in Cinema Motion

The LoRA Library in Cinema Motion stores your trained avatars so you can apply them directly to AI video generation. WAN 2.2 is the only video model with a dedicated LoRA Library — the character stays consistent in the output without a reference image from Picture Lab.

Select WAN 2.2

Open Cinema Motion and choose WAN 2.2 from the model selector. This is the model with a dedicated LoRA Library control in the Cinema Motion bar.

Open the LoRA Library

Click LoRA Library. A panel opens on the left side with three tabs: Avatar, Style, and Product.

LoRA Library modal with Avatar, Style, and Product tabs open in Cinema Motion alongside the WAN 2.2 interface

Avatar — trained characters (people or consistent personas)
Style — trained visual styles
Product — trained product appearances

If you haven't trained anything yet, the tabs will show "No scenes found". See Train an avatar LoRA to create your first avatar.

Apply a LoRA

Click any trained avatar in the Avatar tab. Selecting an avatar closes the panel and activates the LoRA for the next generation. Write your prompt describing the scene, then click Generate. The character from your LoRA will appear in the generated video.

Reference the character naturally in your prompt — describe the scene and action, not the person's appearance. The LoRA handles consistency automatically.

Why video LoRAs are different

In Picture Lab, LoRAs generate a reference image that Cinema Motion then animates. That two-step process introduces variation at the animation stage. WAN 2.2 with a LoRA skips the intermediate image entirely — the character identity goes straight into the video model, giving more consistent results across multiple generations.