README.md

metadata

title: 1Prompt1Story
app_file: app.py
sdk: gradio
sdk_version: 4.44.1

🔥 One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

     

Key Features • How To Use • License • Citation

Key Features

• Consistent Identity Image Generation.
• Gradio Demo.
• Consistory+ Benchmark: contains 200 prompt sets, with each set containing between 5 and 10 prompts, categorized into 8 superclasses: humans, animals, fantasy, inanimate, fairy tales, nature, technology.
• Benchmark Generation Code.

How To Use

To clone and run this application, you'll need Git and Node.js (which comes with npm) installed on your computer. From your command line:

# Clone this repository
$ git clone https://github.com/byliutao/1Prompt1Story

# Go into the repository
$ cd 1Prompt1Story

### Install dependencies ###
$ conda create --name 1p1s python=3.10
$ conda activate 1p1s
# choose the right cuda version of your device
$ conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia 
$ conda install conda-forge::transformers 
$ conda install -c conda-forge diffusers
$ pip install opencv-python scipy gradio=4.44.1 sympy==1.13.1
### Install dependencies ENDs ###

# Run sample code
$ python main.py

# Run gradio demo
$ python app.py

# Run Consistory+ benchmark
$ python -m resource.gen_benchmark --save_dir ./result/benchmark --benchmark_path ./resource/consistory+.yaml

Note If you're using Linux Bash for Windows, see this guide or use node from the command prompt.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Citation

If our work assists your research, feel free to give us a star ⭐ or cite us using:

arixv