Directory
Published directory entries matching your search.
StylePile is a prompt generation helper script and extension for AUTOMATIC1111/stable-diffusion-webui and compatible forks. It mixes and matches elements that affect the style of generated results, with elements placed in a specific order and given strength values. It appears under the Scripts dropdown in txt2img and img2img.
Authors A.I. is an analytical AI tool for fiction authors that provides manuscript review services. Its AI tool Marlowe analyzes novels in minutes to deliver developmental feedback on plot arcs, pacing, character development, and other craft elements, comparing works to bestsellers. It does not generate or rewrite text, and is used by more than 40,000 authors.
C3.js is a D3-based reusable chart library. It wraps the code required to construct entire charts, gives classes to elements for custom styling, and provides APIs and callbacks to access chart state and update charts after rendering.
GPThemes is a Chrome and Firefox extension that modifies the ChatGPT web interface. It offers custom accent colors, adjustable chat and chatbox widths, typography controls for font family, size, line height and letter spacing, toggleable message bubbles, and light, dark and AMOLED themes. It also provides a distraction-free view that hides elements such as the header, footer and upgrade chip, an expandable prompt box, and a floating theme switcher. The extension is available for Firefox for Android and Cromite.
IOPaint is a free, open-source and fully self-hostable image inpainting and outpainting tool powered by AI models. It can erase unwanted objects, add or replace elements in images, generate text, and generate new pixels around images to enlarge them, with various models available for different tasks.
Lucy Text To Image is a Hugging Face Space created by tonyassi that generates realistic dress images using Stable Diffusion. Users input a dress description, select preferences including color, features, occasion, and garment type, and the tool builds a prompt to produce the image, with optional element swapping functionality.
Napkin AI is a tool that turns pasted text into visuals such as flowcharts, mind maps, infographics, diagrams, data charts and slides, without design skills. Users generate visuals from their text, then adjust colors and elements. Visuals can be exported as .ppt, .png, .pdf or .svg. A free plan offers 500 AI credits per week, and pricing lists Plus at $9 per person per month.
Paintings by Style on WikiArt is a webpage that catalogs artworks by art style, with styles ranging from Gothic to Impressionism. It defines art style as the distinctive visual elements, techniques, and methods of an artwork, which typically correspond to an art movement or the school or group its creator is associated with.
Paper2Audio is a free text-to-speech service designed for reading digital documents aloud. It supports PDFs, EPUBs, web articles, and other common document formats, uses natural AI voices for accurate reading, and includes no ads or paywalled voice features. The tool correctly processes figures, tables, and mathematical content, and skips extraneous page elements like inline references and endnotes to focus on relevant content.
SVGo is a Go language library for SVG generation. It supports common SVG elements including shapes, lines, text, paths, images, and gradients, and is hosted as an open-source project on GitHub.
A documentation page about glitching PNG images. It covers the format's checksum system, the transcode process, filters, and other elements that influence the appearance of glitches, noting that PNG's CRC32 checksum makes simple binary edits fail.
TokenVerse is a method for multi-concept personalization that uses a pre-trained text-to-image diffusion model. It can disentangle complex visual elements and attributes from a single image and combine concepts extracted from multiple images, supporting objects, accessories, materials, pose and lighting. It uses a DiT-based text-to-image model and learns modulation-space directions for each word.
