Update README.md
Browse files
README.md
CHANGED
|
@@ -13,12 +13,12 @@ tags:
|
|
| 13 |
license: creativeml-openrail-m
|
| 14 |
---
|
| 15 |
|
| 16 |
-
# LoRA text2image fine-tuning - Oil Canvas Style
|
| 17 |
|
| 18 |
-
## Model Description
|
| 19 |
This model is a fine-tuned version of the Stable Diffusion v1.5 model using Low-Rank Adaptation (LoRA) techniques to generate images in an oil canvas painting style, specifically focusing on the Impressionism genre. The model is designed to produce vibrant, brushstroke-rich images with a joyful and community-focused theme.
|
| 20 |
|
| 21 |
-
## Model Details
|
| 22 |
- **Base Model:** Stable Diffusion v1.5 (`runwayml/stable-diffusion-v1-5`)
|
| 23 |
- **Fine-Tuning Method:** LoRA (Low-Rank Adaptation)
|
| 24 |
- **Training Data:** Custom oil canvas style dataset collected from Kaggle, focused on Impressionism artworks (`Eunju2834/img_captioning_oilcanvas_style`,`Eunju2834/oil_impressionism_style`)
|
|
@@ -30,7 +30,7 @@ This model is a fine-tuned version of the Stable Diffusion v1.5 model using Low-
|
|
| 30 |
- Scheduler: Cosine
|
| 31 |
- Seed: 2024
|
| 32 |
|
| 33 |
-
## Usage
|
| 34 |
```python
|
| 35 |
from diffusers import StableDiffusionPipeline
|
| 36 |
import torch
|
|
@@ -51,7 +51,7 @@ image = pipe(prompt, negative_prompt=neg_prompt, num_inference_steps=30, guidanc
|
|
| 51 |
image.save('oil_impressionism_park_stroll.png')
|
| 52 |
```
|
| 53 |
|
| 54 |
-
## Example Results
|
| 55 |
The model generates images like the ones below, showcasing an oil painting style with vibrant colors and Impressionist influences.
|
| 56 |
<p style="display: flex; justify-content: center;">
|
| 57 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/64bad345f671da974eeb1ba3/SfjQLeVKie31DZSB23jrq.png" width="250px" />
|
|
@@ -61,11 +61,11 @@ The model generates images like the ones below, showcasing an oil painting style
|
|
| 61 |
|
| 62 |
|
| 63 |
|
| 64 |
-
## Limitations and Biases
|
| 65 |
- The model is optimized for oil canvas style images and may not generalize well to other artistic styles.
|
| 66 |
- Potential biases may exist due to the specific nature of the training dataset (e.g., Impressionism artworks).
|
| 67 |
|
| 68 |
-
## License
|
| 69 |
CreativeML Open RAIL-M
|
| 70 |
|
| 71 |
|
|
|
|
| 13 |
license: creativeml-openrail-m
|
| 14 |
---
|
| 15 |
|
| 16 |
+
# 🎨 LoRA text2image fine-tuning - Oil Canvas Style
|
| 17 |
|
| 18 |
+
## 📄 Model Description
|
| 19 |
This model is a fine-tuned version of the Stable Diffusion v1.5 model using Low-Rank Adaptation (LoRA) techniques to generate images in an oil canvas painting style, specifically focusing on the Impressionism genre. The model is designed to produce vibrant, brushstroke-rich images with a joyful and community-focused theme.
|
| 20 |
|
| 21 |
+
## 🔍 Model Details
|
| 22 |
- **Base Model:** Stable Diffusion v1.5 (`runwayml/stable-diffusion-v1-5`)
|
| 23 |
- **Fine-Tuning Method:** LoRA (Low-Rank Adaptation)
|
| 24 |
- **Training Data:** Custom oil canvas style dataset collected from Kaggle, focused on Impressionism artworks (`Eunju2834/img_captioning_oilcanvas_style`,`Eunju2834/oil_impressionism_style`)
|
|
|
|
| 30 |
- Scheduler: Cosine
|
| 31 |
- Seed: 2024
|
| 32 |
|
| 33 |
+
## 🚀 Usage
|
| 34 |
```python
|
| 35 |
from diffusers import StableDiffusionPipeline
|
| 36 |
import torch
|
|
|
|
| 51 |
image.save('oil_impressionism_park_stroll.png')
|
| 52 |
```
|
| 53 |
|
| 54 |
+
## 🖼️ Example Results
|
| 55 |
The model generates images like the ones below, showcasing an oil painting style with vibrant colors and Impressionist influences.
|
| 56 |
<p style="display: flex; justify-content: center;">
|
| 57 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/64bad345f671da974eeb1ba3/SfjQLeVKie31DZSB23jrq.png" width="250px" />
|
|
|
|
| 61 |
|
| 62 |
|
| 63 |
|
| 64 |
+
## ⚠️ Limitations and Biases
|
| 65 |
- The model is optimized for oil canvas style images and may not generalize well to other artistic styles.
|
| 66 |
- Potential biases may exist due to the specific nature of the training dataset (e.g., Impressionism artworks).
|
| 67 |
|
| 68 |
+
## 📜 License
|
| 69 |
CreativeML Open RAIL-M
|
| 70 |
|
| 71 |
|