|
|
|
--- |
|
base_model: stabilityai/stable-diffusion-xl-base-1.0 |
|
instance_prompt: Monkey smoking a cigarette |
|
tags: |
|
- text-to-image |
|
- diffusers |
|
- autotrain |
|
inference: true |
|
--- |
|
|
|
# README for Text-to-Image Model Fine-Tuned on Stable Diffusion 1.0XL for NFT-Genesis |
|
|
|
## Overview |
|
This project involves a text-to-image model fine-tuned on the Stable Diffusion 1.0XL architecture, specifically tailored for the NFT-Genesis project. The model is designed to generate high-quality, unique images based on textual descriptions, making it especially suited for creating digital art and Non-Fungible Tokens (NFTs). |
|
|
|
## Features |
|
- **Fine-Tuning on Stable Diffusion 1.0XL**: Leverages the advanced capabilities of the Stable Diffusion model for high-quality image generation. |
|
- **NFT-Genesis Specialization**: Optimized for creating images that are ideal for use in the NFT space, emphasizing uniqueness and artistic quality. |
|
- **Textual Description Input**: Generates images based on user-provided text descriptions, offering a high degree of creative control. |
|
- **High-Resolution Output**: Capable of generating images in high resolutions suitable for digital art applications. |
|
|
|
## Requirements |
|
- Python 3.6 or later |
|
- PyTorch 1.7.1 or later |
|
- PIL (Python Imaging Library) |
|
- Other dependencies listed in `requirements.txt` |
|
|
|
## Installation |
|
1. Clone the repository: |
|
```bash |
|
git clone [repository URL] |
|
cd [repository name] |
|
``` |
|
2. Install dependencies: |
|
```bash |
|
pip install -r requirements.txt |
|
``` |
|
|
|
## Usage |
|
To generate an image: |
|
```import requests |
|
import io |
|
from PIL import Image |
|
|
|
API_URL = "https://api-inference.huggingface.co/models/sarathAI/NFT-Genesis" |
|
headers = {"Authorization": "Bearer XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"} |
|
|
|
def query(payload): |
|
response = requests.post(API_URL, headers=headers, json=payload) |
|
return response.content |
|
|
|
image_bytes = query({ |
|
"inputs": "Formula 1 car", |
|
}) |
|
|
|
# Added: Check if the response is indeed image bytes |
|
if image_bytes.startswith(b'\xff\xd8'): # JPEG |
|
print("JPEG image detected") |
|
elif image_bytes.startswith(b'\x89PNG\r\n\x1a\n'): # PNG |
|
print("PNG image detected") |
|
else: |
|
print("The response might not be an image or is in an unrecognized format.") |
|
|
|
# Attempt to open the image |
|
try: |
|
image = Image.open(io.BytesIO(image_bytes)) |
|
image.save("output_image.jpg") |
|
print("Image saved as output_image.jpg. Please open this file to view the image.") |
|
except IOError: |
|
print("Cannot open the image. The file might be corrupted or in an unsupported format.") |
|
|
|
|
|
``` |
|
|
|
## Configuration |
|
- **Model Parameters**: Adjust model parameters in the `config.py` file to tweak performance and output quality. |
|
- **Custom Datasets**: To further fine-tune the model, you can use custom datasets by following the instructions in `dataset/README.md`. |
|
|
|
## Contributing |
|
Contributions to the project are welcome. Please follow the guidelines in `CONTRIBUTING.md` for submitting pull requests or reporting issues. |
|
|
|
## License |
|
This project is licensed under [specify license type], as found in the LICENSE file. |
|
|
|
## Acknowledgements |
|
- Original Stable Diffusion 1.0XL Team for the base model architecture. |
|
- Contributors and community members who have offered valuable insights and improvements. |
|
|
|
## Disclaimer |
|
This model is intended for creative and artistic purposes. Users are responsible for the ethical use of the technology and ensuring that generated content respects copyright and other legal considerations. |
|
|