CoolFace
Modelpublic

fwwrsd/xzbs_woman-zimage-base-lora

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face
0likes9downloads
Model Card

WAN 2.1 LoRA — xzbs_woman

A personalized LoRA (Low-Rank Adaptation) trained on WAN 2.1 14B for generating video content with a specific identity. Works with both Image-to-Video and Text-to-Video WAN 2.1 pipelines.

Trained using dual-mode Musubi Tuner (high + low noise models → single LoRA file).

Quick Start

Direct Download URL

https://huggingface.co/fwwrsd/xzbs_woman-zimage-base-lora/resolve/main/lora.safetensors

ComfyUI Setup

  1. 1.Download lora.safetensors → place in ComfyUI/models/loras/
  2. 2.Use WAN LoRA Loader node
  3. 3.Set trigger word: xzbs_woman

Load Directly from URL (ComfyUI)

Many LoRA loader nodes support loading directly from a HuggingFace URL:

https://huggingface.co/fwwrsd/xzbs_woman-zimage-base-lora/resolve/main/lora.safetensors

No download needed — ComfyUI caches it automatically.

Download via Command Line

bash
# wget
wget https://huggingface.co/fwwrsd/xzbs_woman-zimage-base-lora/resolve/main/lora.safetensors -O lora_xzbs_woman.safetensors

# curl
curl -L https://huggingface.co/fwwrsd/xzbs_woman-zimage-base-lora/resolve/main/lora.safetensors -o lora_xzbs_woman.safetensors

# huggingface-cli
huggingface-cli download fwwrsd/xzbs_woman-zimage-base-lora lora.safetensors

Recommended Settings

ParameterImage-to-VideoText-to-Video
LoRA Strength (motion)0.3 — 0.40.3 — 0.4
LoRA Strength (identity)0.85 — 0.950.85 — 0.95
CFG Scale0.521.0
Steps30 — 5030 — 50
Samplereuler / dpmpp_2meuler / dpmpp_2m

Trigger word: xzbs_woman — include in your prompt to activate the LoRA.

Training Details

ParameterValue
Base ModelWan-AI/Wan2.1-I2V-14B-720P
Training MethodMusubi Tuner (dual-mode: high + low noise)
LoRA Rank16
Learning Rate1e-4
LR Schedulercosine with 5% warmup
Optimizeradamw + LoRA+ (ratio=4)
Training Steps~unknown
Epochsunknown
Resolution1024px
Dataset Sizeunknown images
CaptionsNo (photos only)
Precisionfp16 (LoRA) + fp8 (base model)
Presetstandard
Created2026-06-30
GPUNVIDIA H200 SXM 141GB

Architecture

This is a dual-mode LoRA trained with --timestep_boundary 875:

  • —High-noise model (timesteps > 875): Handles initial structure and motion
  • —Low-noise model (timesteps ≤ 875): Handles fine details and identity

Both models are trained simultaneously and packed into a single .safetensors file. Compatible with any WAN 2.1 workflow that supports LoRA.

License

Apache 2.0 — free for personal and commercial use.

Trained with [NanoBanana LoRA Bot](https://t.me/LoraDatasetBot) on RunPod