This post goes over how to perform AI image generation with diffused CLI.

Prerequisites

Install Python:

brew install python

Install pipx:

brew install pipx

CLI

Install the CLI:

pipx install diffused

Text-to-image:

diffused segmind/tiny-sd "red apple"

Image-to-image:

diffused OFA-Sys/small-stable-diffusion-v0 "cat wizard" --image=https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png

Inpainting:

diffused kandinsky-community/kandinsky-2-2-decoder-inpaint "black cat" --image=https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png --mask-image=https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint_mask.png

Show the help message and exit:

diffused --help # diffused -h

Script

Create a virtual environment:

python3 -m venv .venv

Activate the virtual environment:

source .venv/bin/activate

Install the package:

pip install diffused

Generate an image with model and prompt:

# script.py
from diffused import generate

images = generate(model="segmind/tiny-sd", prompt="red apple")
images[0].save("apple.png")

Run the script:

python script.py

Open the image:

open apple.png

See the API documentation.

Resources

• For more models, see Hugging Face.
• The package is open source and on GitHub.