README.md

---
base_model: zenless-lab/sdxl-anything-xl
tags:
- stable-diffusion-xl
- sdxl
- lora
- diffusers
- art
- style
license: other
language:
- en
---

# LoRA Model

This is a LoRA (Low-Rank Adaptation) model trained on SDXL.

## Model Details
- **Base Model**: zenless-lab/sdxl-anything-xl
- **Training Method**: LoRA
- **LoRA Rank**: 64
- **Optimizer**: Prodigy

## Usage

```python
from diffusers import DiffusionPipeline
import torch

# Load pipeline
pipe = DiffusionPipeline.from_pretrained(
    "zenless-lab/sdxl-anything-xl",
    torch_dtype=torch.float16
).to("cuda")

# Load LoRA weights
pipe.load_lora_weights("dada22231/b426e506-75a2-4d9a-8952-22652d903752")

# Generate image
prompt = "your prompt in lora style"
image = pipe(prompt).images[0]
```

## Training Details
- Trained with AI Toolkit
- Mixed precision: bf16
- Batch size: 12