Directory
Published directory entries matching your search.
VISE is a standalone open-source visual search application developed by the Visual Geometry Group in Oxford University's Department of Engineering Science. It enables visual search of large image collections using an image as a query. Installers are available for Windows 10, macOS, and Linux, with source code provided for compilation.
Yandex Images is an image search service operated by Yandex. It enables users to search for a range of image content including postcards, desktop screensavers, funny pictures, diagrams, and illustrated manuals, and allows users to get visual answers to their questions.
A collection of free open source intelligence and forensic tools for investigations. It provides links to third-party services for searching general web sources, email addresses, domains, IP addresses, Bitcoin addresses, images, usernames and social media, and includes a mail validation tool.
Image Mage is a client-side web tool for turning photos into styles such as comic book art, abstract paintings and pixel art. Processing happens in the browser, and the author states no access to uploaded images. It is free and open source, with no paywalls or premium options, and may be used for personal or commercial purposes.
Image Splitter is a small tool that splits images into square tiles, such as large Discord emojis. It is open source and provides a preview plus a download that includes a text file for displaying the emojis after upload.
PyTTI is a toolkit that facilitates image generation, animation, and manipulation through processes described as a human artist collaborating with AI assistants. The project states that users do not need to be deep learning experts or know coding to use the tools.
Pixsy is an image protection platform. It monitors the public internet for unauthorized use of user-uploaded images, provides filtering and search tools for detected matches, and supports takedown notices and compensation recovery for copyright infringement. The service also integrates with the US Copyright Office for official registration and handles legal cases on a no win, no fee basis.
TEXT-IMAGE.com generates text-images and ASCII art from pictures on a user's device. The converter accepts JPG, PNG, GIF, WEBP and BMP files and lets users choose the characters, their random or sequential order, image width and font size. The resulting HTML representation can be shared via a public link stored for five days.
A seven-week online class starting October 24th, 2022, that demystifies the text-to-image process and helps designers and artists gain control over the tools. It explores several significant options and the controversy of how these models gathered their training data. The class is geared toward people who have never used these tools or used them a little.
Bing image search for finding pictures, visual results, source pages, and related media.
adarsus helps inspect, hide, extract, redact, or convert image data for technical workflows.
A blog post by Matt Webb arguing that Adobe should make a boring app for prompt engineers. It discusses AI image synthesis tools like DALL-E 2, Imagen, and Midjourney, noting that prompt engineering is a new kind of expertise. The post describes Midjourney's Discord-only interface during its beta.
Angle Ref Search is a search tool focused on image and media content. It allows users to find openly licensed people photography and portrait references filtered by head direction, and share artwork that users create using those reference images.
Image forensics and steganography tool for analyzing hidden data, metadata, and visual layers.
Image forensics and steganography tool for analyzing hidden data, metadata, and visual layers.
Astria is an AI image production platform that creates ecommerce visuals and headshot products. It provides tools for training custom models, generating images, and delivering outputs, with additional offerings including API access, a Photoshop plugin, and style templates for headshots and ecommerce use cases.
Baidu image search for finding pictures, similar images, and visual content from Chinese web sources.
Background Generator is a free online image creator that generates unique background images using random algorithms and seven styles. Users can customize image size up to 4K, save as JPG or PNG with transparent or opaque backgrounds, and add text to generated images. It targets wallpapers, article illustrations, posters and commercial backgrounds.
Cartography of generative AI is a project presenting a mapped account of generative AI in multiple languages. It discusses how tools automate writing and image generation through examples and statistical models trained on datasets, and examines the extraction of internet content for training datasets and related controversies.
A free online tool that converts supplied text into an image file in GIF, JPEG or PNG format. Users choose text up to 500 characters, dimensions between 10 and 1500 pixels, font size from 6pt to 54pt, and foreground and background colors, then download the image or link to it. The site stores choices in a database and a cookie.
Convertmyimage is an online service for converting JPG and other image formats to PDF. It accepts formats including JPG, JPEG, PNG, GIF, BMP, TIF, TIFF and WMF, and offers settings for margins, page orientation, image size and rotation. Batch conversion, resizing and PDF to JPG conversion are also listed.
Image comparison tool for spotting visual differences between two pictures or screenshots.
A browser extension that finds and saves images displayed on the current tab. A toolbar button opens an image-filtering tool that filters by dimensions, image type, size in bytes and URL, with custom regular expressions for advanced filtering. It detects images loaded on the page, referenced in links, included in text, or used as CSS backgrounds, and supports deep searching of linked pages.
Dropmatico is a browser-based image workflow tool with two engines. The Single Image Editor renders one master image for each destination, while the Bulk Image Processor handles up to 16 images per session for a single destination. Processing runs locally via the Canvas 2D API, with no uploads, account or analytics. Presets cover 90+ destinations across 34 platforms.
