Loading...

LLaVa

LLaVA (Large Language and Vision Assistant) tool is an innovative large multimodal model designed for general-purpose visual and language understanding. It combines a vision encoder with a large language model (LLM), Vicuna, and is trained end-to-end. LLaVA demonstrates impressive chat capabilities, mimicking the performance of multimodal GPT-4, and sets a new…

ShotSolve

ShotSolve is a free macOS menubar app that uses GPT-4 Vision to solve questions based on a screenshot taken by the user. It integrates with OpenAI and offers advanced configuration options such as custom API Host, context limit, system instruction, and custom GPT parameters. It also features a native app with…