Oryx is a multimodal large-scale language model (MLLM) jointly developed by Tsinghua University, Tencent, and Nanyang Technological University. It utilizes two core innovations to process visual data: the pre-trained OryxViT model and a dynamic compression module. OryxVi...
I2VEdit is an advanced video editing framework that uses an image-to-video diffusion model to enable first-frame guided video editing. Users only need to edit the first frame of the video, and I2VEdit can automatically apply the edits to the entire video.
HouseCrafter, an advanced technology developed by Northeastern University and Stability AI, automatically converts 2D floor plans into 3D interior scenes. Based on a network-scale image-trained 2D diffusion model, it generates consistent multi-view...
The AMD-135M is AMD's first Small Language Model (SLM), offering a balance between performance and resource consumption for specific use cases. Based on the LLaMA2 model architecture, it is trained on the AMD Instinct MI250 accelerator, based on 67 billion...
JoyHallo is an open-source AI digital human model from JD.com, designed specifically for Mandarin Chinese. It can generate realistic speaking videos based on audio. It is particularly well-suited for handling complex lip movements and intonation in Mandarin and has the ability to generate videos across languages.
Seed-VC is a zero-sample voice conversion technology that achieves high-quality audio output and timbre similarity based on context learning. Users do not need specific training; they only need to provide 1 to 30 seconds of reference speech samples to achieve voice mapping...
Phidias is an advanced 3D content generation model that introduces the concept of Retrieval-Enhanced Generation (RAG) to the field of 3D modeling. The model can assist in generating new content based on user-provided 3D reference models or those retrieved from large databases...
Movie Gen is an AI video generation tool launched by Meta. It can generate and edit videos based on text prompts and add synchronized audio. The technology includes creating high-definition videos up to 16 seconds long, adding audio to existing videos, editing...
Mini-LLaVA is a lightweight multimodal large language model jointly developed by research teams from Tsinghua University and Beijing University of Aeronautics and Astronautics. It can handle image, text, and video inputs, achieving efficient multimodal data processing. Min...
MemoryScope is a long-term memory system designed for chatbots with large language models (LLMs). By building a framework, it enables the chatbot to remember basic user information, habits, and preferences, providing a personalized interactive experience...
CogView3 is an open-source AI image generation model jointly developed by Tsinghua University and Zhipu AI, employing relay diffusion technology. The model generates images in stages, first creating low-resolution images, and then upscaling them to high resolution using relay super-resolution technology...
RTranslator is an open-source, free, offline real-time translation application designed specifically for Android devices. It is based on advanced AI technologies, including Meta's NLLB translation model and OpenAI's Whisper speech recognition...
Molmo 72B is an open-source, multimodal AI model developed by the Allen Institute for Artificial Intelligence (Ai2), specifically designed for processing and understanding image and text data. Based on the Qwen2-72B model, it uses OpenAI's CLIP as its visual...
ProX (Programming Every Example) is a framework designed to improve the quality of pre-trained data for large language models. Unlike traditional methods that rely on human experts to formulate rules, ProX treats data cleaning as a programming problem...
OutofFocus is an AI-powered image editing tool that uses the Grado platform to provide users with an intuitive interface for image editing. Its core function is to accept text prompts from the user and process them using natural language processing...
TeleChat2-115B is a large-scale language model developed by the China Telecom Artificial Intelligence Research Institute (TeleAI), belonging to the Xingchen Semantic Large Model series. It is trained using domestically produced computing power and employs a high-quality Chinese and English language dataset with 10 trillion tokens...
GroundingBooth is an advanced text-to-image customization framework developed by a research team from Washington University in St. Louis, Adobe, and Purdue University. It is based on a text-to-image alignment module and a masking cross-attention layer...
Markmap is a tool that converts Markdown text into mind maps. Based on Markdown's syntax, it generates visual mind maps in real time, helping users intuitively organize and display information. Markmap is lightweight...
OLMoE (Open Mixture-of-Experts Language Models) is a large-scale, fully open-source language model based on a Mixture-of-Experts (MoE) architecture. OLMoE is pre-trained on 5 trillion tokens and has a total of 7 billion...
WebDesignAgent is an automated web design tool that uses AI technology to help users easily create websites. Users provide a simple text description or upload an image, and WebDesignAgent generates fully functional and beautifully designed websites...
ChatMLX is a high-performance macOS chat application based on Large Language Models (LLMs), using the MLX framework to interact with data. The application utilizes natural language processing technology to allow users to converse with data, supporting text-based...
CDial-GPT is a large-scale Chinese short text dialogue dataset, LCCC, and a pre-trained dialogue generation model based on the dataset, developed by a research team at Tsinghua University. The LCCC dataset undergoes a rigorous cleaning process and includes a basic version (LCCC-base...
RD-Agent is an open-source automated research and development (R&D) tool developed by Microsoft Research Asia. It leverages AI technology to drive data-driven AI R&D processes, focusing on simplifying model and data development. RD-Agent...
FLUX 1.1 Pro, codenamed "Blueberry," is the latest upgraded AI image generation model from Black Forest Labs. It offers up to 6 times faster generation speeds than its predecessor while maintaining image timeliness and diversity. FLUX 1.1 aims to...