Installing SkyworkUniPic requires a basic Python environment and GPU support, here are the detailed steps:
- clone warehouse: by ordering
git clone https://github.com/SkyworkAI/UniPicCloning Project Warehouse. - Creating a Virtual Environment: Create a Python 3.10.14 environment using Conda with the command
conda create -n unipic python=3.10.14The - Installation of dependencies: Run
pip install -r requirements.txtInstall the required libraries. - Download model weights: Download the pre-training weights via Hugging Face with the command
huggingface-cli download Skywork/Skywork-UniPic-1.5B --local-dir checkpoint --repo-type modelThe - Setting environment variables: Add the project path to the environment variable with the command
export PYTHONPATH=./:$PYTHONPATHThe
Once you have completed the above steps, you can run tasks such as text to generate images or image editing.
This answer comes from the articleSkyworkUniPic: An Open Source Model for Unified Processing Image Understanding and GenerationThe
May not be reproduced without permission:AI productivity tools " How to install and run SkyworkUniPic in local environment?
English 
简体中文 
日本語 
Deutsch 
Português do Brasil