Dingo: A Comprehensive AI Data, Model and Application Quality Evaluation Tool

Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights

[AAAI 2025] From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach

An implementation for MLLM oversensitivity evaluation

A comprehensive service for extracting document structure and content from images using advanced computer vision and vision-language models (VLM)

#3 Winner of Best Use of Zoom API at Stanford TreeHacks 2025! An AI-powered meeting assistant that captures video, audio and textual context from Zoom calls using multimodal RAG.

Flask app to interact with FastVLM using CPU only

Personalized Vision Language Models for Social Human-Robot Interactions

Pinokio script for installing the app slides2video

[NVIDIA ONLY] [RTX 50 Support] Image generation, image editing and free-form manipulation with a VLM (Minimum Requirements 12GB VRAM / 32GB RAM Recommended Requirements 24GB VRAM / 48GB RAM)

RealTime-VLM brings real-time VLM inference to the browser. It continuously captures webcam frames, sends image+text to an OpenAI-compatible API, and displays responses with sub-second latency. Works with local or hosted VLMs.

Real-time video captioning powered by FastVLM

This is the official implementation (code, data) of the paper "MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?""

[NVIDIA ONLY] Image generation, image editing and free-form manipulation with a VLM (Minimum Requirements 12GB VRAM / 32GB RAM Recommended Requirements 24GB VRAM / 48GB RAM)

AI-powered personal assistant with OpenAI & MERN stack. Chat, analyze images, secure subs—50% faster responses.

[NVIDIA ONLY] Gradio demo for Flux Kontext based on Diffusers with single and multiple images. (Minimum Requirements 12GB VRAM 48GB RAM / Recommended Requirements 24GB VRAM / 48GB RAM)

ScribblAI turns your chaotic doodles into photorealistic images using advanced AI — and your friends must guess what you were trying to draw. It's fast, fun, and full of AI magic!

We introduce the YesBut-v2, a benchmark for assessing AI's ability to interpret juxtaposed comic panels with contradictory narratives. Unlike existing benchmarks, it emphasizes visual understanding, comparative reasoning, and social knowledge.

YesBut Benchmark; Project page of paper Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions, accepted by NeurIPS 2024 (Oral).

[NVIDIA ONLY] End-to-end multimodal SVG generator capable of generating complex and detailed SVGs, from simple icons to intricate anime characters. (Minimum Requirements 12GB VRAM / 32GB RAM, Recommended Requirements 24GB VRAM / 24GB RAM)