fwwrsd/wan-lora-0987-94411003

WAN 2.1 LoRA — 0987

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/wan-lora-0987-94411003/resolve/main/lora.safetensors

ComfyUI Setup

1. Download lora.safetensors → place in ComfyUI/models/loras/
2. Use WAN LoRA Loader node
3. Set trigger word: 0987

Load Directly from URL (ComfyUI)

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

https://huggingface.co/fwwrsd/wan-lora-0987-94411003/resolve/main/lora.safetensors

No download needed — ComfyUI caches it automatically.

Download via Command Line

# wget
wget https://huggingface.co/fwwrsd/wan-lora-0987-94411003/resolve/main/lora.safetensors -O lora_0987.safetensors

# curl
curl -L https://huggingface.co/fwwrsd/wan-lora-0987-94411003/resolve/main/lora.safetensors -o lora_0987.safetensors

# huggingface-cli
huggingface-cli download fwwrsd/wan-lora-0987-94411003 lora.safetensors

Recommended Settings

Parameter	Image-to-Video	Text-to-Video
LoRA Strength (motion)	0.3 — 0.4	0.3 — 0.4
LoRA Strength (identity)	0.85 — 0.95	0.85 — 0.95
CFG Scale	0.52	1.0
Steps	30 — 50	30 — 50
Sampler	euler / dpmpp_2m	euler / dpmpp_2m

Trigger word: 0987 — include in your prompt to activate the LoRA.

Training Details

Parameter	Value
Base Model	Wan-AI/Wan2.1-I2V-14B-720P
Training Method	Musubi Tuner (dual-mode: high + low noise)
LoRA Rank	16
Learning Rate	0.00005
LR Scheduler	cosine with 5% warmup
Optimizer	adamw + LoRA+ (ratio=4)
Training Steps	~1500
Epochs	125
Resolution	1024px
Dataset Size	12 images
Captions	Yes (AI-generated, WAN-style)
Precision	fp16 (LoRA) + fp8 (base model)
Preset	quick
Created	2026-02-27
GPU	NVIDIA 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 on RunPod