Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,33 @@
|
|
1 |
-
---
|
2 |
-
license: mit
|
3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
---
|
4 |
+
|
5 |
+
# SDv1.5 Patterns1K LoRA Usage Guide
|
6 |
+
|
7 |
+
## Introduction
|
8 |
+
`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.
|
9 |
+
|
10 |
+
## Usage Instructions
|
11 |
+
|
12 |
+
### 1. Download Stable Diffusion v1.5 Weights
|
13 |
+
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).
|
14 |
+
|
15 |
+
### 2. Prepare LoRA Weights
|
16 |
+
We have trained LoRA weights for the Patterns-1K dataset. You can download the trained LoRA weights from the following links:
|
17 |
+
- LoRA weights after 1 epoch: [1epoch_lora.safetensors](link)
|
18 |
+
- LoRA weights after 100 epochs: [1epoch_lora.safetensors](link)
|
19 |
+
|
20 |
+
### 3. Test the Model
|
21 |
+
After downloading the weights, you can use the `test_lora.py` script to test the model's performance. Follow these steps:
|
22 |
+
|
23 |
+
#### Install Dependencies
|
24 |
+
Ensure you have the following Python libraries installed:
|
25 |
+
```bash
|
26 |
+
pip install diffusers transformers torch
|
27 |
+
```
|
28 |
+
|
29 |
+
### 4. Run the Test Script
|
30 |
+
To test the model with the LoRA weights trained for 1 epoch:
|
31 |
+
```bash
|
32 |
+
python test_lora.py
|
33 |
+
```
|