DiT (Diffusion Transformers) is a novel diffusion model proposed by William Peebles (one of the research leaders at Sora) and Xie Saining, an assistant professor at New York University. It combines a denoising diffusion probability model (...
VideoPoet is an AI video generation solution developed by Google's research team, based on a large model. It supports synthesizing high-quality video content from text, images, or video input and generating matching audio. VideoPoet's core...
SDXL-Lightning is a text-to-image generation technology based on a diffusion model, developed by ByteDance's research team. It aims to address the limitations of traditional diffusion models in terms of image generation speed and computational cost. This model is based on...
Stable Diffusion 3 is an advanced text-to-image generation model developed by Stability AI. It is the latest iteration in the Stable Diffusion series and is designed to generate high-quality images from text prompts. ...
ConsiStory, developed by researchers at NVIDIA and Tel Aviv University, is a training-free method for generating images from text. It allows images to follow different text styles while maintaining their original style and subject matter...
ScreenAgent is a computer-controlled intelligent agent developed by a research team at the School of Artificial Intelligence, Jilin University. This agent is based on a Visual Language Model (VLM) and can interact with a real computer screen. Scr...
YOLOv9 is a next-generation advanced object detection system developed by a research team from institutions such as Academia Sinica and Taipei University of Technology. It is the latest version of the YOLO (You Only Look Once) algorithm series. YOLOv9 builds upon its predecessors...
VideoPrism is a general-purpose video encoder developed by Google Research, designed to handle various video understanding tasks with a single frozen model. This model is able to extract rich semantic representations from videos, enabling it to...
GPT-SoVITS is an open-source voice cloning project. This speech synthesis tool combines the GPT model with SoVITS voice changer technology, achieving high-quality voice cloning and text-to-speech conversion with only a small amount of sample data. This tool...
OpenCodeInterpreter is an open-source code interpreter system designed to assist developers in generating, testing, and optimizing code during the software development process by leveraging large models combined with code generation, execution, and iterative refinement capabilities.
ChatMusician is an open-source, large-scale language model for understanding and generating music, developed by researchers from the Multimodal Art Projection Research Community, Skywork AI, and the Hong Kong University of Science and Technology.
EMO (Emote Portrait Alive) is a framework developed by researchers at Alibaba Group's Intelligent Computing Research Institute. It's an audio-driven AI portrait video generation system capable of generating images from a single reference image and audio input...
StarCoder 2 is a next-generation large-scale code language model developed by the BigCode project team, designed to provide robust support for code generation, editing, and inference tasks. This model series builds upon the previous generation of StarCoder models...
MeloTTS is an open-source, high-quality, multilingual text-to-speech (TTS) library developed by MyShell AI. It converts text into natural, fluent speech output and supports multiple languages. MeloTTS boasts impressive speech synthesis speed...
Snap Video is an AI video generation model developed by Snap Inc.'s research team. Its goal is to synthesize videos based on text descriptions; users can input descriptive text, and the model can generate videos based on that text...
LayerDiffusion, proposed by researchers from Stanford University, is a technique for generating transparent images using large-scale pre-trained latent diffusion models. It can help users generate single transparent images or multiple transparent layers.
Text-Diffuser 2 is a newly developed text rendering method based on a diffusion model, developed by researchers from Microsoft Research, Hong Kong University of Science and Technology, and Sun Yat-sen University. It aims to address the limitations of image diffusion models in generating text, particularly in terms of flexibility...
UniEdit is an innovative video editing framework developed by researchers from Zhejiang University, Microsoft Research, and Peking University. It allows users to edit the motion and appearance of videos without requiring model fine-tuning...
DUSt3R is a 3D reconstruction framework developed by researchers from Aalto University and Naver Europe Labs in Finland. It aims to simplify the process of reconstructing 3D scenes from arbitrary image sets without prior knowledge of camera calibration or visual signatures...
ScreenAI is a readable screen AI visual language model developed by Google's research team, specifically designed for understanding and processing user interfaces (UIs) and infographics. This model is based on the PaLI architecture, combining visual and language processing...
ResAdapter, developed by researchers at ByteDance, is a resolution adapter designed for diffusion models (such as Stable Diffusion), allowing these image generation models to generate images with arbitrary resolution and aspect ratios...
AtomoVideo is a high-fidelity image-to-video (I2V) generation framework proposed by Alibaba's research team. It aims to generate high-quality video content from input still images. This framework maintains the quality of the generated video while retaining the original image...
Moondream is a free and open-source small AI visual language model. Despite its small parameter set, it offers high-performance visual processing capabilities and can run on local computers, mobile devices, or even a Raspberry Pi.
PixArt-Σ is a text-based graph model developed by researchers from Huawei Noah's Ark Lab, Dalian University of Technology, and the University of Hong Kong. It is based on the Diffusion Transformer architecture (DiT) and is specifically designed for extracting text from prompts...