Kazumi character LoRA for Z-Image Turbo and full model

Model description

Kazumi Z-Image LoRA (Turbo + Full) This repo contains two LoRA files.

kazumi_zimage_turbo_lora_3000.safetensors — This LoRA is for Z-Image Turbo. It is intended for workflows that use the Turbo checkpoint (Tongyi-MAI/Z-Image-Turbo) with 4–8 steps and ModelSamplingAuraFlow.

kazumi_zimage_full_lora_3000.safetensors — This LoRA is for the full Z-Image model. It is intended for workflows that use the full Z-Image checkpoint (Tongyi-MAI/Z-Image) with 30–40 steps, without AuraFlow. Trigger word: kazumi. Suggested strength: 0.8–1.0 depending on the scene.

Trigger words

You should use kazumi to trigger the image generation.

Download model

Download them in the Files & versions tab.

Downloads last month: 23

Model tree for boyarkinn/kazumi_zimage_lora_3000

Base model

Tongyi-MAI/Z-Image-Turbo

Adapter

(882)

this model