abab-video-1 is MiniMax's first AI-powered high-definition video generation model. It supports generating high-definition videos with a maximum resolution of 1280x720 and a frame rate of 25fps, featuring cinematic camera movement effects and the ability to quickly generate videos based on text descriptions...
abab-music-1 is a large-scale end-to-end AI music generation model launched by MiniMax. It supports multi-functional end-to-end music generation, capable of synthesizing various music forms, including instrumental and a cappella pieces, while also supporting accompaniment and vocals...
FineVideo, developed by Hugging Face, is a large-scale multimodal video dataset focused on complex tasks in video understanding, such as sentiment analysis, storytelling, and media editing. FineVideo contains over 43,000 Y...
Void is an open-source text editor built on Visual Studio Code, integrating AI technology to enhance the programming experience. Void supports code auto-completion, inline editing, AI-driven code search, and direct interaction with large language models...
Draw an Audio is a video-to-audio generation system developed by researchers from the Institute of Automation, Chinese Academy of Sciences, and Meituan-Dianping. It automatically generates matching sound effects based on video content, similar to Foley art direction in filmmaking...
CogVideoX-5B-I2V is an open-source image-to-video model from Zhipu AI, generating videos from a single image and text prompts. The model employs a 3D causal variational autoencoder and expert-adaptive LayerNorm technology, enabling it to output...
RapidPages is an open-source integrated development environment (IDE) focused on rapidly generating UI components for React and Tailwind CSS using AI technology. Based on natural language processing, it allows users to create UI components simply by describing their desired interface...
Ovis 1.6 is a multimodal large-scale model launched by Alibaba's international AI team. It has achieved excellent results on OpenCompass, a leading comprehensive benchmark for multimodal computing, especially ranking first in overall score among models with fewer than 3 billion parameters...
Gummy is an end-to-end speech translation model launched by Tongyi Lab at the 2024 Yunqi Conference. The model can generate speech recognition and translation results in real-time streaming, supporting languages including Chinese, English, Cantonese, Japanese, Korean, French, German, etc.
The cogvlm2-llama3-caption model is a video description generation model based on the CogVLM2 architecture. The model is used to understand video content and automatically generate text titles or subtitles that describe the video content.
3DTopia 2.0 is a large-scale 3D object generation model jointly developed by the Shanghai Artificial Intelligence Laboratory and Nanyang Technological University. The model employs the innovative primitive-based 3D representation method PrimX...
StoryMaker is an open-source text-to-image generation tool from Xiaohongshu, focusing on helping creators maintain consistency in their personas across continuous image content. Based on the Stable Diffusion XL model and LoRA technology, it ensures...
CogVideoX-Fun is an AI video generation package based on CogVideoX and modified with EasyAnimate. It offers more flexible generation conditions and supports text-to-video, image-to-video, and video-to-video generation. Tools...
ItiNera is a smart city travel planning system jointly developed by the University of Hong Kong and MIT. Based on Large Language Models (LLM) and spatial optimization technology, it generates C++ templates with a single click based on the user's personalized needs, such as couples' bars or anime/manga themed locations...
Huazhi Big Model 5.0 is an AI big model jointly launched by Tongfang Knowledge Network and Huawei Cloud, possessing multimodal understanding and generation capabilities. The biggest highlight of Huazhi Big Model 5.0 lies in its multi-dimensional model construction capabilities, covering multiple dimensions from 7B to 135B...
LVCD (Large Video Color Diffusion) is a video diffusion framework specifically designed for coloring line art in animated videos. It can automatically convert black and white line art into color animated videos. LVCD uses an advanced diffusion model...
LLaMA-Omni is a novel model architecture developed by researchers at the Institute of Computing Technology, Chinese Academy of Sciences, and the University of Chinese Academy of Sciences, for achieving low-latency, high-quality speech interaction with large language models (LLMs). It integrates pre-trained...
SCoRe (Self-Correction via Reinforcement Learning) is an innovative multi-round reinforcement learning method developed by Google DeepMind, designed to improve the self-correction capabilities of large language models (LLMs). Through...
AiNiee is an AI translation tool that can automatically translate RPG and SLG games, Epub and TXT novels, Srt and Lrc subtitle files with a single click. The tool supports multiple file formats and connects to several mainstream AI interface platforms, such as OpenAI...
ANTO is an open-source Windows desktop subtitle translation tool for translating SRT format video subtitle files. It integrates multiple translation engines, such as Google Translate, DeepL, Microsoft Translate, Baidu Translate, and Youdao Translate, allowing users to customize the translation process...
OpenMusic is a high-quality text-based music model based on QA-MDT (Quality-aware Masked Diffusion Transformer) technology. It uses advanced AI algorithms to generate high-quality music based on text descriptions...
SFR-RAG is a large-scale language model developed by Salesforce AI Research, focused on improving machine learning capabilities in understanding and generating text. The model places particular emphasis on faithful understanding of context, particularly in enhanced text retrieval...
oneWebot2 is a one-click WeChat AI robot launcher software package. Users can simply download the .exe file and double-click to start it, without needing complex Python environment configuration. It features a graphical interface, simplifying the configuration process, making it easy for non-technical users to set up...
GOT-OCR 2.0 is an advanced optical character recognition (OCR) model that propels OCR technology into the 2.0 era. The GOT-OCR 2.0 end-to-end model consists of a high-compression encoder and a long context decoder, capable of processing text, ...