⚡ Self-hostable YesCaptcha-compatible captcha solver built with FastAPI, Playwright, and OpenAI-compatible multimodal models.
[CVPR 2025 Oral] OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels
A curated collection of resources focused on the Mechanistic Interpretability (MI) of Large Multimodal Models (LMMs). This repository aggregates surveys, blog posts, and research papers that explore how LMMs represent, transform, and align multimodal information internally.
Local-first Chrome extension that turns images into generator-ready prompts.
The PyVisionAI Official Repo
This is an official repository for "Harnessing Vision Models for Time Series Analysis: A Survey".
A hands-on collection of computer vision projects for everyone.
A zero-dependency Python tool to resolve relative Markdown links and inline images as Base64 strings for RAG and Multimodal LLMs.
Generative AI document analysis on Amazon Bedrock AgentCore: a Strands agent routes pages through 27 vision specialists via an MCP Gateway, then correlates results into a structured, accessibility-oriented document tree. Eight-model registry (Anthropic, Amazon, OpenAI), specialist wizard, scripted CDK deployment, React UI on ECS with Cognito.
A2Mamba: Attention-augmented State Space Models for Visual Recognition
Implementation of VisionLLaMA from the paper: "VisionLLaMA: A Unified LLaMA Interface for Vision Tasks" in PyTorch and Zeta
PoC Code for PerfCam: Digital Twinning for Production Lines Using 3D Gaussian Splatting and Vision Models
A simple to use package to call various model providers such as openai, anthropic, and others with utmost reliability, security, and performance.
we generate captions to the images which are given by user(user input) using prompt engineering and Generative AI
A small VLM that sees everything
Enhance your skills in prompt engineering for vision models. Learn to effectively prompt, fine-tune, and track experiments for models like SAM, OWL-ViT, and Stable Diffusion 2.0 to achieve precise image generation, segmentation, and object detection.
DART (Diffusion-Autoregressive Recursive Transformer) is a novel hybrid architecture that combines diffusion-based and autoregressive approaches for text generation.
Dataset for PerfCam: Digital Twinning for Production Lines Using 3D Gaussian Splatting and Vision Models
Implementation of Midas from [Towards Robust Monocular Depth Estimation] in Pytorch and Zeta
A SillyTavern extension allowing your characters to see the world you're building
To associate your repository with the vision-models topic, visit your repo's landing page and select "manage topics."