oztrkoguz / VisQueryPDF
It automatically describes images in PDF files and generates questions from these descriptions. With its advanced RAG structure, it directs these questions directly to PDF text content, providing comprehensive information extraction and analysis.
☆10Updated 2 months ago
Related projects: ⓘ
- This project aims to compare different Retrieval-Augmented Generation (RAG) frameworks in terms of speed and performance.☆9Updated last month
- This project offers a user-friendly interface that allows users to easily create stories and enrich them with visuals. It supports creati…☆23Updated 3 months ago
- Image identification with Kosmos2 model, drawing and cutting bbox with object detection☆17Updated last month
- ☆20Updated 2 months ago
- Few-Shot Prompting - Chain-of-Thought (CoT) Prompting - Hallucinations - Self-Consistency - Generated Knowledge Prompting - Tree of …☆25Updated 10 months ago
- ☆10Updated 4 months ago
- ☆20Updated 3 months ago
- ☆52Updated 5 months ago
- Custom nodes for using Flux models with fal API☆34Updated last month
- Summarize webpages from specified URLs using the LangChain framework and the ChatOllama model☆89Updated 2 months ago
- ☆10Updated 7 months ago
- Overlay text on an image in ComfyUI with font/alignment/placement customization☆39Updated last month
- Dream Interpreter inside ComfyUI☆72Updated last month
- ☆50Updated last year
- a node for AuraSR☆22Updated 2 months ago
- ☆17Updated 9 months ago
- ☆21Updated 3 weeks ago
- ☆35Updated 3 months ago
- ComfyUI InstructIR☆64Updated 3 months ago
- Flux Prompt Generator provides a flexible and customizable prompt generator for generating detailed and creative prompts for image genera…☆82Updated 3 weeks ago
- ComfyUI custom node for filtering tags based on categories such as pose, gesture, action, emotion, expression, camera, angle, sensitive, …☆25Updated last month
- ☆16Updated last year
- A prompt helper☆59Updated last month
- A Python toolkit for image clustering using deep learning, PCA, and K-means, with support for GPU and CPU processing. Simplify your image…☆31Updated 4 months ago
- create interpolation pose images between two image,☆52Updated 3 weeks ago
- ☆72Updated 3 weeks ago
- The successful integration of Qwen2-VL-Instruct into the ComfyUI platform has enabled a smooth operation, supporting (but not limited to)…☆43Updated 2 weeks ago
- ☆43Updated 6 months ago
- a comfyui node for automatic generate image label for running lora or dreambooth training on flux series models☆47Updated 3 weeks ago
- Unofficial implementation of AnyText for ComfyUI(EXP)☆52Updated 3 months ago