OmniSVG: from text and images to generate SVG vector graphics open source project
General Introduction OmniSVG is an open source project focused on generating high-quality vector graphics (SVG) through a multimodal model. It utilizes pre-trained visual-linguistic models to support SVG generation from textual descriptions or image input, covering a wide range of scenarios from simple icons to complex anime characters. Item ...
Napkins.dev: uploading wireframes to generate front-end code based on Llama4
General Introduction Napkins.dev is a free open source project, the core function is to allow users to upload interface screenshots or wireframes to automatically generate runnable front-end code. Users only need to provide a design drawing , the tool will be through the Llama 4 model (by Together ...
EmemeAI: Interactive Platform for Creating and Exporting 3D Virtual AI Characters
General Introduction EmemeAI is a platform that helps users create 3D AI characters. You can upload 3D models in VRM format, set the character's personality, and generate virtual characters that can chat and move automatically. These characters can not only talk to you, but also generate expressions and actions according to the context.E...
Agent-Wiz: Analyzing AI Intelligentsia Workflows and Security Risks
General Introduction Agent-Wiz is an open source Python command line tool designed for developers, researchers and security teams. It can extract complex workflows from mainstream AI intelligences frameworks such as LangGraph, CrewAI, AutoGen, etc., to generate...
Orion: Xiaomi's Open Source End-to-End Autonomous Driving Reasoning and Planning Framework
Comprehensive Introduction Orion is an open source project developed by Xiaomi Labs, focusing on end-to-end (E2E) autonomous driving technology. It solves the problem of insufficient causal reasoning in complex scenarios of traditional autonomous driving approaches through visual language modeling (VLM) and generative planners.Orion integrates long...
ReCamMaster: Rendering Tool for Generating Multi-View Videos from a Single Video
General Introduction ReCamMaster is an open source video processing tool, the core function is to generate new camera views from a single video. Users can specify the camera track and re-render the video to get a dynamic picture with different angles. It is developed by a team of Zhejiang University and Racer Technology, based on text-to...
BrowseComp: OpenAI Launches New Benchmark for Evaluating Information Retrieval Capabilities on the AI Web
Recently, OpenAI released a new benchmark test called BrowseComp, designed to assess the ability of AI agents in Internet browsing. The benchmark consists of 1,266 questions covering a wide range of domains, from scientific discovery to pop culture, and requires the agent to...
WiseBIM AI: 2D architectural drawings quickly converted into 3D BIM models
Comprehensive Introduction WiseBIM AI is an artificial intelligence-based Revit plugin focused on quickly converting 2D architectural drawings into 3D BIM models. It is developed by the French company WiseBIM SAS and can automatically recognize elements such as walls, doors, windows, floor slabs, etc. in drawings, generating...
SimplAI: A Platform for Enterprises to Rapidly Build Intelligent AI Applications
General Introduction SimplAI is a platform designed for organizations to help users rapidly build, deploy and manage secure AI agents and automated workflows. It provides an easy-to-use tool, SimplAI Studio, that allows teams to develop A...
Tarsier: an open source video comprehension model for generating high-quality video descriptions
Comprehensive Introduction Tarsier is a family of open-source video-language models developed by ByteDance for generating high-quality video descriptions. It consists of a simple structure: the CLIP-ViT processes video frames, combined with a Large Language Model (LLM) to analyze...