Qwen2 is a new generation of large language models open-sourced by the Alibaba Cloud Tongyi Qianwen team. This series covers five scale models ranging from 0.5B to 72B, adding high-quality data from 27 languages to the existing Chinese and English models, significantly improving...
Follow-Your-Emoji is a portrait animation framework based on a diffusion model, developed by researchers from the Hong Kong University of Science and Technology, Tencent Hunyuan, and Tsinghua University. It uses a diffusion model to add target expression sequences to reference portraits, achieving animation...
ToonCrafter is an open-source cartoon animation video interpolation tool developed by researchers from Tencent AI Lab, the Chinese University of Hong Kong, and City University of Hong Kong. It breaks through the limitations of the linear motion assumption in traditional cartoon animation production, employing innovative...
Artificial intelligence startup Stability AI has announced the official open-source release of its latest text-to-image generation model—Stable Diffusion 3 Medium (SD3 Medium). Stable Diffusion 3 Medium includes 20...
MimicBrush is an AI image editing and fusion framework developed by researchers from Alibaba, the University of Hong Kong, and Ant Group. It allows users to specify the areas to be edited on a source image through simple operations and provides a framework that includes...
Hallo is an AI-powered lip-syncing portrait image animation technology jointly proposed by researchers from Fudan University, Baidu, ETH Zurich, and Nanjing University. It can generate realistic and dynamic images based on voice audio input...
Unique3D is an open-source framework from Tsinghua University for converting single images into 3D models. By combining multi-view diffusion models and normal diffusion models, along with an efficient multi-level upsampling strategy, it can convert single images into 3D models...
The QinYue Big Model is an AI-powered music creation model jointly developed by Tencent AI Lab and Tencent TME Tianqin Lab. This model can directly generate stereo audio or... by inputting Chinese or English keywords, descriptive phrases, or audio.
Diffutoon is an AI framework developed by researchers from Alibaba and East China Normal University that transforms videos into cartoon/anime styles. Based on a diffusion model, its editable cartoon coloring technology can convert realistic videos into anime-style animation...
ExVideo, developed by researchers from Alibaba and East China Normal University, is a post-tuning technique for video synthesis models. It extends the temporal scale of existing video synthesis models to generate longer videos. The team is based on Stable V...
Toucan TTS is a text-to-speech synthesis toolkit developed by the Institute for Natural Language Processing (IMS) at the University of Stuttgart, Germany. It supports over 7,000 languages, including various dialects and variants, and offers multi-speaker speech synthesis, speech recognition, and more.
MOFA-Video is an open-source model for controllable image-to-video generation developed by researchers from Tencent AI Lab and the University of Tokyo. This technology utilizes a generative motion field adaptor to animate images and generate videos.
CriticGPT is a new artificial intelligence model released by OpenAI, built on GPT-4, specifically designed to review and identify errors in code generated by large language models (such as ChatGPT). CriticGPT relies heavily on human feedback...
Gemma 2 is a next-generation open-source artificial intelligence model released by Google's DeepMind, available in versions with 9 billion and 27 billion parameters. This model is characterized by its superior performance, efficient inference speed, and broad hardware compatibility, enabling it to work with various hardware...
MimicMotion is a high-quality human motion video generation framework developed by Tencent researchers. It utilizes confidence-aware pose guidance technology to ensure high-quality video frames and smooth temporal transitions. Furthermore, MimicMotion...
FreeAskInternet is a free and open-source native AI search engine that integrates advanced large language models (LLMs) such as GPT-3.5 and the SeerXNG meta-search engine to provide users with search and intelligent answer generation services.
Fish Speech is an open-source text-to-speech (TTS) tool developed by Fish Audio, supporting Chinese, English, and Japanese. Trained on approximately 150,000 hours of multilingual data, it achieves near-human-level speech synthesis results...
Moshi is an end-to-end real-time audio multimodal AI model developed by the French AI research lab Kyutai. It possesses the abilities to hear, speak, and see, and can simulate 70 different emotions and styles of communication. As a benchmark...
EchoMimic is an open-source AI digital human project launched by Alibaba's Ant Group, giving static images vivid voice and expressions. It uses deep learning models combined with audio and facial landmarks to create highly realistic dynamic portrait videos. ...
MimicMotion is an AI video generation framework developed by Tencent in collaboration with Shanghai Jiao Tong University. Users only need to provide an image and a reference video to generate realistic human motion videos with a single click, suitable for various genres such as dance and sports...
FunAudioLLM is an open-source speech model project launched by Alibaba Tongyi Labs, comprising two models: SenseVoice and CosyVoice. SenseVoice excels in multilingual speech recognition and emotion detection, supporting over 50 languages...
Chameleon is a hybrid multimodal model released by FAIR (Facebook AI Research), the artificial intelligence research team at Meta (Facebook's parent company), capable of understanding and generating arbitrary sequences of images and text. It possesses...
Mem0 is an open-source memory enhancement tool for large language models, enabling AI to possess long-term, adaptive memory. Through its adaptive memory system, AI can remember user preferences and interactions across applications, providing coherent and continuous...
STORM AI is an open-source AI writing tool developed by Stanford University. It can convert a topic into a long article/research paper in seconds, is completely free, and is an alternative to Perplexity Pages. STORM AI utilizes...