https://github.com/rupeshs/lcm-openvino-converter

LCM OpenVINO model converter
https://github.com/rupeshs/lcm-openvino-converter

Last synced: 4 months ago
JSON representation

LCM OpenVINO model converter

• Host: GitHub
• URL: https://github.com/rupeshs/lcm-openvino-converter
• Owner: rupeshs
• Created: 2023-11-12T15:40:22.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-03-27T03:16:17.000Z (over 2 years ago)
• Last Synced: 2024-05-02T01:39:04.587Z (about 2 years ago)
• Language: Python
• Size: 2.93 KB
• Stars: 12
• Watchers: 3
• Forks: 1
• Open Issues: 2
• Metadata Files:
  • Readme: Readme.md

Awesome Lists containing this project

README

          
# StableDiffusion Model to LCM OpenVINO converter

Create a venv and install the requirements.

`pip install -r requirements.txt`

or run `install.bat`

activate the environment

`env/Scripts/activate`

LCM conversion is a two step process.

1. Create LCM-LoRA baked in model and replace the scheduler with LCM

`python lcm-convert.py --no-half --model Lykon/dreamshaper-7 --huggingface --name rupeshs/LCM-dreamshaper-7 --upload`

2. Convert to OpenVINO using `optimum-cli`

`optimum-cli export openvino --model "rupeshs/LCM-dreamshaper-7" "LCM-dreamshaper-v7-openvino`

Thanks [Disty0](https://github.com/Disty0) for the conversion script.

This models can be used with [FastSD CPU](https://github.com/rupeshs/fastsdcpu)