Skip to main content

A CLI tool for generating high-quality image-text pairs for AI training

Project description

GenIText: Generative Image-Text Automated package

Demonstration video of GenIText tool

Overview

This repository is independently developed as a felxible framework to generate high-quality Image-Text pairs for finetuning Image-Generation models, such as Stable Diffusion, DALL-E, and other generative models. By leveraging open-source captioning models, GenIText automates the process of generating diverse captions for corresponding images, ensuring that the text data is well-suited for downstream applications such as style-specific generations or domain adaptation. This framework is designed to complement contemporary repositories or modules in the field, offering an additional option for flexibility and automation to create customized datasets.

GenIText will become distributable as a CLI tool once package is ready for testing across systems. Please support in any way you see fit!

Table of Contents

Installation

GenIText is available as a Python package and can be installed easily using pip.

To install GenIText, simply run:

pip install genitext

After installation, you can verify that the CLI tool is accessible by running:

genitext --help

To initiate the CLI tool, run:

genitext

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

genitext-0.1.4.tar.gz (18.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

genitext-0.1.4-py3-none-any.whl (25.7 kB view details)

Uploaded Python 3

File details

Details for the file genitext-0.1.4.tar.gz.

File metadata

  • Download URL: genitext-0.1.4.tar.gz
  • Upload date:
  • Size: 18.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.0

File hashes

Hashes for genitext-0.1.4.tar.gz
Algorithm Hash digest
SHA256 6055c81604f06a39d2feac8d23892f3e6879e431c8ab126ca5f5ae7b9aefb2e8
MD5 7bc407d935ba95e487f254f49d7d458b
BLAKE2b-256 b379768fe2b5b4e40d16673d3aae9046975eb163c472ed1e055be7bed5930737

See more details on using hashes here.

File details

Details for the file genitext-0.1.4-py3-none-any.whl.

File metadata

  • Download URL: genitext-0.1.4-py3-none-any.whl
  • Upload date:
  • Size: 25.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.0

File hashes

Hashes for genitext-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 94e0f7316d337964ec33975f6e0f1f40c5b50cb9a44ce76ac5d1d0011b115635
MD5 aac1f151e0152429811802b7ec5ca9d4
BLAKE2b-256 98bb7fcf1fc0395a6661082359ccd59d82d9d0ef942548a1399b0d4c0ee6e379

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page