import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Comfy-Org/z_image", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("fwwrsd/anitraxxe-zimage-lora")
prompt = "anitraxxe"
image = pipe(prompt).images[0]
Z Image LoRA — anitraxxe
A personalized identity LoRA trained on Z Image using diffusion-pipe + DeepSpeed.
Trigger Word
Use anitraxxe in your prompt to activate this LoRA.
Quick Start
Direct Download (for ComfyUI / wget / curl)
https://huggingface.co/fwwrsd/anitraxxe-zimage-lora/resolve/main/anitraxxe_lora.safetensors
ComfyUI
- Download
anitraxxe_lora.safetensors→ place inComfyUI/models/loras/ - Add a LoRA Loader node, select
anitraxxe_lora.safetensors - Include
anitraxxein your prompt
Command Line
# huggingface-cli (recommended)
huggingface-cli download fwwrsd/anitraxxe-zimage-lora anitraxxe_lora.safetensors
# wget
wget "https://huggingface.co/fwwrsd/anitraxxe-zimage-lora/resolve/main/anitraxxe_lora.safetensors" -O anitraxxe_lora.safetensors
Recommended Settings
| Parameter | Value |
|---|---|
| LoRA Strength | 0.7 — 1.0 |
| CFG Scale | 3.5 |
| Steps | 20 — 30 |
Available Checkpoints
This repo contains 2 epoch checkpoints — try different epochs to find the best balance of identity fidelity vs flexibility.
| Epoch | File | Note | Link |
|---|---|---|---|
| 10 | anitraxxe_epoch10.safetensors |
Download | |
| 17 | anitraxxe_epoch17.safetensors |
⭐ Best | Download |
anitraxxe_lora.safetensors is a copy of the best (final) checkpoint — epoch 17.
Download Specific Epoch
# Download epoch 17 (best)
wget https://huggingface.co/fwwrsd/anitraxxe-zimage-lora/resolve/main/anitraxxe_epoch17.safetensors
# Download any epoch — replace N with epoch number
huggingface-cli download fwwrsd/anitraxxe-zimage-lora anitraxxe_epoch<N>.safetensors
Training Details
| Parameter | Value |
|---|---|
| Base Model | Comfy-Org/z_image |
| Training Method | diffusion-pipe + DeepSpeed |
| LoRA Rank | 16 |
| Learning Rate | 1e-4 |
| Total Epochs | unknown (best: 17) |
| Resolution | 1024px |
| Dataset Size | 58 images |
| Preset | test |
| Created | 2026-03-06 |
License
Apache 2.0 — free for personal and commercial use.
Trained with NanoBanana LoRA Bot on RunPod
- Downloads last month
- 5