|
--- |
|
license: mit |
|
--- |
|
|
|
# SDv1.5 Patterns1K LoRA Usage Guide |
|
|
|
## Introduction |
|
`SDv1.5 Patterns1K LoRA` is a fine-tuned model based on Stable Diffusion v1.5, specifically optimized for generating patterns from the Patterns-1K dataset. Using LoRA (Low-Rank Adaptation) technology, the model has been adapted to produce higher-quality patterns relevant to the dataset. |
|
|
|
## Usage Instructions |
|
|
|
### 1. Download Stable Diffusion v1.5 Weights |
|
Before you begin, ensure you have downloaded the pre-trained weights for Stable Diffusion v1.5. You can download the weights from the [official Stable Diffusion repository](https://huggingface.co/runwayml/stable-diffusion-v1-5). |
|
|
|
### 2. Prepare LoRA Weights |
|
We have trained LoRA weights for the Patterns-1K dataset. You can download the trained LoRA weights from the following links: |
|
- LoRA weights after 1 epoch: [1epoch_lora.safetensors](link) |
|
- LoRA weights after 100 epochs: [100epoch_lora.safetensors](link) |
|
|
|
### 3. Test the Model |
|
After downloading the weights, you can use the `test_lora.py` script to test the model's performance. Follow these steps: |
|
|
|
#### Install Dependencies |
|
Ensure you have the following Python libraries installed: |
|
```bash |
|
pip install diffusers transformers torch |
|
``` |
|
|
|
### 4. Run the Test Script |
|
To test the model with the LoRA weights trained for 1 epoch: |
|
```bash |
|
python test_lora.py |
|
``` |
|
The param `lcm_speedup` decide use lcm speed up or not. |
|
|
|
#### View the Results |
|
The generated images will be saved to the specified paths: |
|
|
|
Results after 1 epoch: `1epoch_test_results.png` |
|
|
|
Results after 100 epochs: `100epoch_test_results.png` |
|
|
|
Here are the example results: |
|
-  |
