README.md

---
license: mit
base_model: OnomaAIResearch/Illustrious-xl-early-release-v0
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- gradients-on-demand
inference: true
---

# LoRA Model for Illustrious-xl-early-release-v0

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

## Model Details

- **Base Model**: OnomaAIResearch/Illustrious-xl-early-release-v0
- **LoRA Rank**: 128
- **LoRA Alpha**: 128
- **Training Framework**: Kohya SS
- **Precision**: bfloat16

## Training Configuration

- **Learning Rate**: 2e-5
- **Batch Size**: 8
- **Epochs**: 50
- **Optimizer**: AdamW8Bit
- **LR Scheduler**: Cosine with Restarts
- **Resolution**: 1024x1024

## Usage

You can use this LoRA with any SDXL-compatible interface:

### With Diffusers

```python
from diffusers import DiffusionPipeline
import torch

# Load base model
pipe = DiffusionPipeline.from_pretrained(
    "OnomaAIResearch/Illustrious-xl-early-release-v0",
    torch_dtype=torch.float16,
    variant="fp16",
    use_safetensors=True
)
pipe.to("cuda")

# Load LoRA weights
pipe.load_lora_weights("dada22231/ba2b5d89-3688-448e-9197-d9fd377c4f5a")

# Generate image
prompt = "your prompt here, lora style"
image = pipe(
    prompt,
    num_inference_steps=20,
    guidance_scale=7.5,
).images[0]
```

### With ComfyUI

1. Download the .safetensors file
2. Place it in `ComfyUI/models/loras/`
3. Use the "Load LoRA" node in your workflow

### With Automatic1111

1. Download the .safetensors file
2. Place it in `stable-diffusion-webui/models/Lora/`
3. Use `<lora:ba2b5d89-3688-448e-9197-d9fd377c4f5a:1>` in your prompt

## Training Data

This model was trained on a custom dataset as part of the Gradients on Demand subnet.

## License

This model is licensed under the MIT License.