Overview
This Python project provides a simple command-line interface for interacting with the SDXL-Turbo model, showcasing two key functionalities:
Allows users to convert a text prompt into an image using the SDXL-Turbo model. Users are prompted to input a text prompt, and the script generates code snippets using the model to produce an image. The generated image is saved in the "output" directory.
Enables users to transform an existing image based on a text prompt using SDXL-Turbo. Users input a text prompt, and the script generates code snippets utilizing the model to transform an initial image. The resulting image is saved in the "output" directory.
The same SDXL-Turbo pipelines without the questions, so other programs can use them (DREAM paints her dreams with it):
python scripts/generate.py --prompt "a red fox in snow" --out fox.jpg
python scripts/generate.py --prompt "as a watercolour" --init in.jpg --out out.jpg
python scripts/generate.py --job job.json # many images, one model load
python scripts/generate.py --model stabilityai/sd-turbo ... # smaller: 4 GB GPU, 8 GB RAMA job file is {"prompt": "...", "keyframe": "key.jpg", "frames": [["in.jpg", "out.jpg"], ...], "strength": 0.5, "size": 512, "seed": 1}; each image is written as soon as it's done.
Environment Setup
python -m venv venv
source venv/bin/activate
pip install -r requirements.txtpython.exe -m pip install --upgrade pip
py -3.11 -m venv venv311
venv311\Scripts\activate
pip install -r requirements.txt
Minds — DREAM companion · TINA engineer · NINA caretaker · RIFT fleet hub · LYCEA training school
Robots — NORA · MILA · WHIP · KIDA-00 · KIDA-01 · IDA · ARM
Tools — CRUSH compression · Image-Generator · GloriosaAI · SynthWomb · PyVitals