ELLA (Efficient Large Language Model Adapter) is a novel method developed by Tencent researchers, designed to improve the performance of text-to-image generation models in handling complex text...
Transformer Debugger (TDB) is a tool developed by OpenAI's Superalignment team to help researchers and developers gain a deeper understanding and analysis of the internal workings of Transformer models...
Pix2Gif is a motion-guided diffusion model proposed by researchers at Microsoft Research, specifically designed to convert static images into dynamic GIF animations/videos. This model achieves image...
Follow-Your-Click is an image-to-video (I2V) generation model jointly developed by researchers from Tencent (Hunyuan Team), Tsinghua University, and Hong Kong University of Science and Technology. It allows...
AutoDev is an AI programming and application development intelligent agent framework developed by Microsoft researchers. It is specifically designed for autonomously planning and executing complex software engineering tasks, such as code writing, debugging, testing, and version control. Au...
Grok-1 is a large-scale language model developed by xAI, an AI startup founded by Elon Musk. It's a hybrid expert (MoE) model with 314 billion parameters, making it the largest open-source language model in terms of parameter count...
Open-Sora is an open-source video generation model developed by the Colossal-AI team, designed to replicate OpenAI's Sora video generation product. Open-Sora is also based on the DiT architecture and undergoes training in three stages: large-scale image pre-training, large-scale...
VLOGGER AI is a multimodal diffusion model developed by Google's research team, specifically designed to generate realistic, coherent human-motion videos from a single input image and audio sample. The model's main function is to utilize artificial intelligence...
Stable Video 3D (SV3D) is an advanced 3D technology developed by Stability AI that can generate high-quality new perspective views and 3D meshes from a single image. This model is based on the previously released Stable Video...
AnimateDiff-Lightning, a high-quality video generation model recently launched by ByteDance researchers, utilizes progressive adversarial diffusion distillation technology to achieve rapid video generation. This model aims to address the challenges of existing video...
StreamMultiDiffusion is a real-time interactive image generation framework that combines the high-quality image synthesis capabilities of a diffusion model with the flexibility of region control. It can generate real-time, interactive images based on user-specified region text prompts...
Mora is a multi-agent (AI agent) framework developed by researchers from Microsoft and Lehigh University, specifically designed for general video generation tasks. Its goal is to simulate and extend OpenAI's Sora video generation model. This framework...
LATTE3D is a text-to-3D object generation model developed by NVIDIA researchers. It can quickly generate high-quality 3D content from text prompts (in just 400 milliseconds). The core of this technology lies in a technique called "...
BrushNet is a plug-and-play image inpainting model based on a diffusion model, developed by researchers from Tencent PCG's ARC Labs and the University of Hong Kong. It effectively utilizes a decomposed, two-branch architecture...
SUPIR is a groundbreaking image inpainting and enhancement method that utilizes the large-scale generative model StableDiffusion-XL (SDXL) and model extension techniques. Through deep learning and multimodal methods, it achieves high-quality image restoration...
StreamingT2V is a text-to-video generation model developed by the PicsArt AI research team. It aims to address the limitations of existing models, which can only generate high-quality short videos of 16 or 24 frames per second, while encountering issues with longer videos such as poor video quality...
VoiceCraft is an open-source neural codec language model developed by a research team at the University of Texas at Austin, focusing on zero-shot speech editing and text-to-speech (TTS) tasks. The model employs the Transformer architecture...
Champ is a 3D-based model proposed by researchers from Alibaba, Fudan University, and Nanjing University for converting human images into video animations. This method combines 3D parametric models (especially the SMPL model) and latent...
Jamba, launched by AI21 Labs, is the first production-grade large language model based on the Mamba architecture. Currently, most large language models (such as GPT, Gemini, and Llama) are based on the Transformer architecture. Jamba, however...
Voice Engine is OpenAI's latest AI-powered speech synthesis and voice cloning technology. It can generate near-natural-sounding speech from short 15-second audio samples and text input. This technology has been available since 2022...
SWE-agent is an open-source AI programmer and software engineer system developed by researchers in the NLP group at Princeton University. It leverages the capabilities of large language models (such as GPT-4) to automatically solve problems in GitHub repositories. ...
DreaMoving is a human video generation framework based on a diffusion model, developed by the research team at Alibaba Group. DreaMoving achieves precise control over human movements and appearance through a video control network and a content guide...
AniPortrait is an open-source AI video generation framework for photo lip-syncing, similar to EMO previously launched by Alibaba. It can generate high-quality animations from audio and a reference portrait image.
InstantStyle is an open-source, style-consistent personalized text-to-image generation framework developed by the InstantX team at Xiaohongshu. It aims to solve a key problem in text-to-image generation: how to maintain style consistency while...