Jubjub Pro – Photorealistic Character LoRA for Z-Image Turbo

Jubjub Pro is a character LoRA trained for Z-Image Turbo, designed for photorealistic character generation with consistent facial identity.

The training dataset includes different camera angles, facial expressions, hairstyles, outfits, lighting conditions, backgrounds, and portrait compositions to provide good flexibility while maintaining the character's recognizable facial features.

Recommended Settings

• Trigger word: jubjub
• Recommended LoRA strength: 0.6–0.8
• Suggested starting strength: 0.7
• Base model: Z-Image Turbo

Recommended Use

Works best with realistic and photorealistic Z-Image Turbo checkpoints. LoRA strength can be adjusted depending on the checkpoint, prompt, and desired identity strength.

The showcase images demonstrate the character across different poses, expressions, outfits, lighting conditions, and environments. Generation results may vary depending on checkpoint and generation settings.