Skip to content

Small python CLI for training a lora using Replicate.com's infrastructure. Requires an account with Replicate.

License

Notifications You must be signed in to change notification settings

tobias-varden/flux-lora-train-cli

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Flux LORA Training CLI

This is a command-line interface (CLI) tool for creating a Flux LORA (LoRA: Low-Rank Adaptation) using replicate.com. Flux LORA is a technique for fine-tuning a pre-trained model to learn a new concept.

Prerequisites

  • Python 3.6 or higher
  • A replicate.com account and API token
  • A GitHub account

Installation

  1. Clone this repository:
git clone https://github.com/your-username/flux-lora-train-cli.git
cd flux-lora-train-cli
  1. Install the required Python packages:
pip install -r requirements.txt
  1. Set your replicate.com API token as an environment variable:
export REPLICATE_API_TOKEN=your-api-token

Usage

python main.py owner model_name image_path token
  • owner: Your GitHub username.
  • model_name: The name for your LORA model.
  • image_path: The path to the zip file containing training images.
  • token: The token for the concept to be learned.

Example

python main.py my-github-username my-lora-model path/to/images.zip my-token

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

About

Small python CLI for training a lora using Replicate.com's infrastructure. Requires an account with Replicate.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages