DeepSeek Harness plugin: a workspace file browser with a per-format preview (rendered Markdown, a JSON tree, 24 syntax grammars, images), shown as a Conversation View tab beside Chat and Trajectory
Official MCP server of the Conv2pdf API: an AI assistant converts Office documents, images, e-books and web pages to PDF, and merges, splits, compresses, protects or converts the PDFs of your computer. Hosted in the EU (France).
Discover and call 400+ practical APIs through seven MCP tools. Search OCR, image, audio, web, math, conversion, and geodata utilities for free, then pay per call with x402 USDC on Base—no account or API key.
IronPDF Engine binary files for windows x64
ImageMagick 7.1.2-36 compiled for browser WebAssembly by WASM Zoo, with Consumer API v1 and bundled runtime assets.
iPhone Photos-style full-screen image viewer for the DSH conversation: zoom from thumbnail, pinch/double-tap zoom, momentum pan, swipe between images, swipe down to close; annotate an image and drop it into the chat box.
Use your ChatGPT account to bring Codex models into DSH: choose models and thinking effort, chat with images, use tools and skills, approve local tasks, answer interactive questions, continue and compact long conversations, check quota and Token history,
Native Rust bindings for PDF conversion, audio, WebRTC, grep, clipboard, image processing, syntax highlighting, PTY, and shell operations via N-API
The most powerful PDF toolkit for n8n — HTML to PDF, sign PDF, OCR, extract tables, merge/split, compress, convert to Excel/Word/PPTX, and 30+ more operations
Ask for a picture and get one: a generate_image tool for the conversation model, backed by your provider's image model, and an Images panel that shows everything it drew as a gallery you can browse, enlarge and download.
Display DSH read_image results as complete inline previews and a keyboard/touch image gallery, with native-resolution zoom and session-authorized loading. 在 DSH 对话中完整预览图片,支持多图切换、键盘与触控缩放。
Image processing utilities for resizing, cropping, format conversion, and optimization with social media aspect ratios
JavaScript Comprehensive tool library, including full screen, copy and paste functions
Serves assets (images and other files) from the local file system or cloud storage (e.g. S3), with on-the-fly image transformation (resize, crop, format conversion) and result caching.
Compression and conversion of images for gulp using sharp.
An MCP server for generating blog cover images using Google Gemini AI, with WebP conversion and Qiniu / Aliyun OSS CDN upload
A TypeScript wrapper for the qemu-img command-line utility, enabling programmatic disk image creation, conversion, inspection, and management.
A unified plugin to prepare MDAST trees for DOCX conversion using mdast2docx.
Native Rust bindings for PDF conversion, audio, WebRTC, grep, clipboard, image processing, syntax highlighting, PTY, and shell operations via N-API
Official JavaScript / TypeScript SDK for the snapWONDERS API — steganography (hide & reveal), forensic media analysis, and format conversion.
In-chat preview for produced files in DeepSeek Harness Web: click a produced-file chip to render Markdown (server-side markdown-it + highlight.js), images, or plain text right in the conversation; system-app open and reveal-in-folder stay one click away.
Convert html to html/image using electron
Blazing-fast, zero-dependency uploader for CloudKu. Supports auto-conversion, chunked uploads, and TypeScript. Easily upload images, videos, audio, and documents via Node.js.
Bitmap image to hairline vector and point cloud conversions
Enhance Markdown-to-DOCX conversion with Mermaid and mindmap diagram support using this plugin for @m2d/core. Converts code blocks into SVG images with customizable Mermaid config.
A Genshin Impact Columbina (哥伦比娅) themed plugin for DeepSeek Harness (Web and Desktop): preset/custom background images with a translucent mask, per light/dark scheme palettes, and a special glow for the active conversation title.
DeepSeek Harness plugin: keeps the images you pasted or attached in the composer, per session — they are mirrored locally and put back when you return to that conversation or the composer remounts, and forgotten once the message is sent or you remove them
Enhance Markdown-to-DOCX conversion with Mermaid and mindmap diagram support using this plugin for @m2d/core. Converts code blocks into SVG images with customizable Mermaid config.
Convert chat conversations and responses between OpenAI, Anthropic and Gemini. Tool calls, images, audio, documents and roles handled. Zero dependencies.
WhatsApp-Claude-GPT is a WhatsApp chatbot that supports multiple AI providers for chat, optional image generation/editing, and voice (speech-to-text and text-to-speech). It’s built for natural, contextual conversations and can now also handle reminders an
DeepSeek Harness plugin that shares selected conversation messages as a PNG card.
DeepSeek vision bridge for the dsh web GUI: route image attachments to a vision model (pi-ai / llama.cpp Qwen3-VL) and continue the conversation with the text description on a text-only LLM (DeepSeek)
Show local images or short videos in the current DeepSeek Harness conversation card, with click-to-preview and a download link. Works over local and remote connections.
GeoTIFF reader support for @thi.ng/pixel
Decode camera RAW files, inspect metadata, extract thumbnails, and render images in Node.js.
The measurable image + document toolkit for JavaScript. On flat art -- logos, icons, UI, screenshots, pixel art -- the SVG is bit-exact: SSIM 1.0000, zero differing pixels, verified by rendering it back. On photographs it leads potrace, imagetracerjs and
Provider-neutral AI service abstractions upstream Effect lacks — reranker, classifier, TTS, STT, image, moderation, voice conversion — each shaped like effect/ai.
Automated conversion of media-image/
Core engine to convert extended MDAST to DOCX. Supports plugins for footnotes, images, lists, tables, and more. Designed for seamless Markdown-to-DOCX conversion.
JSON & API-based declarative and extensible image processing trees/pipelines
A webpack loader to automagically bring your website images to a whole new level of responsiveness!
n8n node to integrate with ComfyUI stable diffusion workflows for image to video conversion
Native Rust bindings for PDF conversion, audio, WebRTC, grep, clipboard, image processing, syntax highlighting, PTY, and shell operations via N-API