Skip to documentation
Let’s build
PUBLIC TECHNICAL PREVIEW Production access and integration details are agreed during onboarding.
Amora Docs/Custom Character LoRA

DEVELOPER DOCUMENTATION

Custom Character LoRA

One character identity across scenes and content formats.

Custom Character LoRA gives a character a dedicated visual identity that can be used across a content workflow. The service is available with a platform deployment or as a standalone project.

One character, any scene

The aim is a recognizable face and body across scenes, outfits and lighting. The character gallery shows Amora in four different settings.

A trained identity is one component of the generation workflow. Model choice, reference inputs, scene prompts and review still affect the final result.

Example training dataset

A character dataset can use approximately 50 curated images, for example:

Frame typeExample share
Portrait50%
Full body30%
Mid-body upwards20%

Vary angles, lighting, expressions and composition while keeping the intended identity consistent. The final dataset and training approach are tailored to your character and selected model.

Service workflow

  1. Agree the character brief and intended uses.
  2. Prepare an AI-designed or approved creator-based reference set.
  3. Curate the dataset and review identity consistency.
  4. Train and evaluate the dedicated character model.
  5. Configure generation recipes for agreed scene types.
  6. Connect the approved workflow to your content operations.

Content applications

Use the character identity in photo sets, generated clips, paid-content catalogs and social-content workflows. Video generation may require a reference image produced by the character workflow rather than accepting a LoRA directly.

Request Custom Character LoRA.

Building something personal?

Talk to our team about your architecture, character and launch.

Discuss your integration ↗