- text to image
- image to image
- instruct pix2piX
- interrogator captioning
- text to image
- image to image
- instruct pix2piX
- interrogator captioning
To install bleeding edge version of diffuzers, clone the repo and install it using pip.
git clone https://github.com/eclipse-tech/Img_Gen_Service
cd Img_Gen_Service
pip install -r requirements.txt
Installation using pip:
pip install diffuzers
To run the web app, run the following command:
streamlit run Home.py -- --device cuda, mps
For Lightning CUDA GPU based systems
streamlit run diffuzers/Home.py --server.address 0.0.0.0 --server.port 8800 -- --device cuda:0
To run the api, run the following command:
diffuzers api
or
uvicorn diffuzers.api.main:app --reload
Starting the API requires the following environment variables:
export X2IMG_MODEL=stabilityai/stable-diffusion-2-1
export DEVICE=cuda
If you want to use inpainting:
export INPAINTING_MODEL=stabilityai/stable-diffusion-2-inpainting
To use long prompt weighting, use:
export PIPELINE=lpw_stable_diffusion