Z Image LoRA β€” 234

A personalized LoRA trained with Z Image pipeline for generating images with a specific identity.

Quick Start

Direct Download URL

https://huggingface.co/fwwrsd/zimage-lora-234-77458782/resolve/main/lora.safetensors

ComfyUI Setup

  1. Download lora.safetensors β†’ place in ComfyUI/models/loras/
  2. Use LoRA Loader node
  3. Set trigger word: 234

Download via Command Line

wget https://huggingface.co/fwwrsd/zimage-lora-234-77458782/resolve/main/lora.safetensors -O lora_234.safetensors

huggingface-cli download fwwrsd/zimage-lora-234-77458782 lora.safetensors

Recommended Settings

Parameter Value
LoRA Strength 0.7 β€” 1.0
CFG Scale 3.5
Steps 20 β€” 30

Trigger word: 234 β€” include in your prompt to activate the LoRA.

Training Details

Parameter Value
Training Method diffusion-pipe + DeepSpeed
LoRA Rank 16
Learning Rate 1e-4
Epochs unknown
Resolution 1024px
Dataset Size 58 images
Preset fast
Created 2026-02-28
GPU NVIDIA H200 SXM 141GB

License

Apache 2.0 β€” free for personal and commercial use.


Trained with NanoBanana LoRA Bot on RunPod

Downloads last month
13
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support