Directory
Published directory entries matching your search.
Detextify is a Python library that removes unwanted pseudo-text from images generated by generative AI models. It runs text detection on an image, masks the detected text boxes and in-paints the masked regions until the image is text-free, either locally or through existing APIs.
SD.Next is an open-source web interface for generating and editing images and video with diffusion models. It supports text-to-image, image-to-image, text-to-video and image-to-video workflows, and also offers captioning, tagging, upscaling, interpolation and colorization. It runs on NVIDIA, AMD, Intel, Apple Silicon or CPU setups, and includes a queue for scheduling tasks.
Aphantasia is a collection of text-to-image tools built on the CLIP model and the Lucent library, with FFT/DWT/RGB parameterizers for no-GAN generation. It grew out of the artwork of the same name and offers text-to-image and text-to-video generation.
joliGEN is an integrated framework for training custom generative AI image-to-image models. It implements GAN, diffusion and consistency models for paired and unpaired image-to-image translation, including domain and style adaptation that preserves semantics such as image and object classes and masks. A server with REST API is provided for deployment, and documentation includes quickstarts and dataset guidance.
Flux is the official inference repository for FLUX.1 models from Black Forest Labs. It contains minimal inference code for running image generation and editing with the open-weight models, including text-to-image, in/out-painting, structural conditioning and image variation variants. The repository is distributed under the Apache-2.0 license.
Zim is a graphical text editor used to maintain a collection of wiki pages. Each page can contain links to other pages, simple formatting, and images. Pages are stored in a folder structure and can have attachments. All data is stored in plain text files with wiki formatting. Plugins provide additional functionality, such as a task list manager and version control support.
Shap-E is OpenAI's official code and model release for generating conditional 3D implicit functions. It generates 3D objects conditioned on text or images, with example notebooks for text-to-3D and image-to-3D sampling. It is released under the MIT license and installs with pip.
ascii-image-converter is a cross-platform command-line tool that converts images into ASCII art and prints them to the console. It supports braille art and accepts JPEG, PNG, BMP, WEBP, TIFF and GIF input. It is available on Windows, Linux and macOS.
gImageReader is a Gtk/Qt front-end to tesseract-ocr. It imports PDF documents and images from disk, scanning devices, clipboard and screenshots, can process multiple images and documents at once, and recognizes text as plain text or hOCR documents. Recognized text is shown next to the image and can be post-processed with spellchecking.
Scikit-Image is an open-source Python library for image processing. Hosted on GitHub, the project provides installation resources, license information, and documentation for users, and accepts community contributions to the codebase.
Butterfly is an open-source, cross-platform note-taking app built around an endless workspace for placing notes, sketches, diagrams, images and documents. It supports handwriting, typed text and Markdown, shapes and lines, and imports of PDFs, SVGs and image files. Content can be exported as PDF, SVG, images or portable Butterfly files. Files can be stored locally, and the app works offline.
MarkItDown is a lightweight Python utility for converting various files to Markdown for use with LLMs and related text analysis pipelines. It preserves document structure and content as Markdown, including headings, lists, tables, and links, and supports formats such as PDF, PowerPoint, Word, Excel, images, audio, HTML, and ZIP files.
Text Grab is a Windows tool that captures text with OCR, cleans it up and sends the result to the clipboard or an editor. All OCR runs on the device, with no internet connection, cloud service or per-use cost. It offers multiple capture modes, post-grab cleanup and spreadsheet-style editing, and can run as a background process with global hotkeys.
Big Sleep is a command line tool for text-to-image generation that combines OpenAI's CLIP with a BigGAN generator. It lets users generate images from natural language prompts via the dream command, train on multiple phrases and penalize unwanted prompts.
Easydiffusion is an AI Image Generation project hosted on GitHub that provides a browser-based user interface for generating images from text prompts and input images, designed for one-click setup with no technical knowledge required.
An offline AI application for phones and Macs that supports chat, image generation, vision, Whisper speech-to-text, tool calling and local-network servers. It runs on CPU, GPU or NPU, requires no account or API key, and keeps data on the device. A paid Pro tier adds voice mode, custom personas and draft-and-approve actions.
ruDALL-E is a project for generating images from text in Russian. The repository provides a pip-installable package and an example pipeline that uses ruDALL-E models, ruCLIP for image selection and Real-ESRGAN for super resolution.
Stable Dreamfusion is a software project that supports text-to-3D and image-to-3D generation, as well as mesh exportation, using NeRF and diffusion model technology. Its public repository includes update logs and links to Colab notebooks for user access.
DeepAA is a repository of convolutional neural networks that generate ASCII art. It is described as under construction and was accepted by the NIPS 2017 Workshop on Machine Learning for Creativity and Design. Users edit an image path in output.py, run the script with a grayscale line image, and converted images are output to output/.
ImageScanOCR is an application that recognizes text from images and PDF files using the Windows OCR API, converting images to editable plain text. Users can edit, copy and save results as plain text files, use batch processing, and rotate images. It supports multiple OCR languages when the Windows language pack is installed and can process OCR offline.
A GitHub repository compiling tools, ideas, prompt engineering resources, Colabs, models and helpers for prompt designers working with AI art and image synthesis. The list covers Dalle2, MidJourney, StableDiffusion and open source tools, and includes sections on commercial and free hosted tools, prompt engineering, post-processing and communities.
This GitHub repository hosts the official implementation of the CVPR 2022 research paper "HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing". The repository contains resources related to the paper's work on StyleGAN inversion for real image editing.
Open-source project that creates or edits images with generative AI and text-based controls.
Open-source project that creates or edits images with generative AI and text-based controls.
