Jessica is an experimental character LoRA trained directly on Tongyi-MAI Z-Image-Turbo.

Jessica is a fully synthetic adult character and is not based on any real person. All training images were generated using AI models.

The LoRA is designed to preserve Jessica’s facial identity and body proportions across close-up portraits, medium shots, full-body compositions, different camera angles, expressions, outfits, environments and lighting conditions.

The training dataset contains 69 AI-generated images, including portraits, lifestyle photographs, full-body references and 14 nude/anatomical body references. Clothing, pose, framing, lighting and background were described separately in the captions to keep the character flexible and promptable.

This is an experimental release, so results may vary depending on the selected checkpoint, prompt, sampler and LoRA strength.

Feedback and shared generations are welcome.