pdf-extractor-llm

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

Open-source platform for extracting structured data from documents using AI.

[ECCV 2026] A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.

PDF转Markdown/Word 软件MinerU最新版免安装一键启动整合包

Apply realistic sensor noise, analog artifacts, and camera metadata to AI-generated images using this custom ComfyUI node suite for research and photorealism.

Run MiniMax-H3 video plus synchronized audio in 4 sampling steps using the Turbo LoRA, with drop-in nodes for ComfyUI workflows.

Integrate Boogu-Image pipelines into ComfyUI with custom nodes for text-to-image, image editing, and fast inference.

AI-powered Form Response Extractor for paper forms, scanned documents, PDFs, and images. Convert handwritten and printed forms into structured JSON using OpenAI, Anthropic, Ollama, and SurveyJS Form Library. Open-source alternative to enterprise IDP tools like Rossum or FlexiCapture.

LLM-PDF-Parser is a FastAPI-based application that extracts text from PDFs and images and uses NuExtract LLM to extract specific fields based on a given JSON template.

`pdf2struct` extracts structured JSON from PDF documents.

🎥 Control 3D camera angles with ease using ComfyUI-qwenmultiangle, featuring an interactive viewport and formatted prompt outputs for multi-angle image generation.

🎥 Enhance video consistency with comfyUI-LongLook, ensuring smooth motion and prompt accuracy for 81+ frame generations in Wan 2.2.

A small web app that finds relevant documents and produces query-focused summaries using Gemini. Supports PDF upload with one-time multimodal preprocessing into per-page Markdown + metadata.

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

🎥 Control a virtual camera to adjust azimuth, elevation, and zoom for generating alternate views of images with Qwen's multi-angle model.

Interactive demo for AI Form Response Extractor by SurveyJS. AI-powered form data extraction for paper forms, scanned documents, PDFs, and images. Convert handwritten and printed forms into structured JSON using OpenAI, Anthropic, Ollama, and SurveyJS Form Library.

Add Video Delta Net hybrid attention to MiniMax-H3 in ComfyUI, replacing quadratic long-range attention with constant-cost recurrent state for efficient video generation.

🖼️ Segment characters in images with ComfyUI using a Vision LLM agent, enhancing your projects with detailed and high-quality masks.

Build a minimalist, stylish brand mall template using uni-app, Vue2, and Tuniao UI for quick e-commerce and fashion store front development.

Study and verify the U24 Yang-Mills mass gap with open data, code, and tests for coupling spectra, Wilson loops, and bounds