DesignEdit is an AI image editing framework jointly developed by a research team from Microsoft Research Asia and Peking University. It introduces the layer concept from the design field, employing multi-layered potential decomposition and fusion techniques to achieve processing without additional layers...
CodeGemma is a large-scale language model released by Google, focused on code generation and understanding. This series includes three different scale models: a 2B pre-trained model, a 7B pre-trained model, and a 7B instruction fine-tuning model, designed to improve...
Parler-TTS is an open-source text-to-speech (TTS) model developed by Hugging Face. It can mimic the style of a specific speaker (gender, tone, speaking style, etc.) based on input prompts, generating high-quality, audible audio...
VASA-1 is a framework proposed by Microsoft Research Asia that converts still photos into lip-syncing videos. It can generate realistic 3D speaking facial animations in real time based on a single still face photo and a piece of audio.
Llama 3 is Meta's latest open-source release of a new generation of large-scale language models (LLMs), including models with 8B and 70B parameters, marking another significant advancement in the field of open-source artificial intelligence. As the third in the Llama series...
FunClip is a fully open-source, locally deployed automated video editing tool developed by Alibaba DAMO Academy. It achieves automated speech recognition for videos by utilizing the FunASR Paraformer series models from Alibaba Tongyi Labs...
Phi-3 is a new generation of advanced small language models from Microsoft Research, including three different sizes: phi-3-mini, phi-3-small, and phi-3-medium. These models maintain a small parameter size while...
Hyper-SD is a high-efficiency image generation framework developed by researchers at ByteDance. Through Trajectory Segmentation Consistent Distillation (TSCD) technology, combined with human feedback learning and fractional distillation, it significantly improves the performance of diffusion models with fewer...
Arctic is a high-performance, open-source, enterprise-grade large-scale language model developed by the AI research team of cloud computing giant Snowflake. This large model boasts 48 billion (480B) parameters and is constructed by 128 fine-grained experts...
OpenELM is Apple's latest series of high-performance open-source language models, including versions with different parameter scales such as OpenELM-270M, OpenELM-450M, OpenELM-1_1B, and OpenELM-3B. This large model utilizes layers...
ID-Animator is a zero-shot human video generation technology developed by researchers from Tencent Photon Studio, the University of Science and Technology of China, and the Hefei Institutes of Physical Science, Chinese Academy of Sciences. It can generate videos based on a single reference facial image...
IDM-VTON is an advanced AI virtual try-on technology proposed by researchers from the Korea Advanced Institute of Science and Technology (KAIST) and OMNIOUS.AI. It generates realistic images of people wearing clothes by improving the diffusion model, achieving a more realistic virtual try-on effect.
VideoGigaGAN is a novel generative video super-resolution (VSR) model proposed by researchers from Adobe and the University of Maryland. It can upscale video resolution by up to 8 times, transforming blurry videos into richly detailed ones...
Vidu is China's first long-duration, highly consistent, and highly dynamic video model, jointly developed by Shengshu Technology and Tsinghua University. This AI video generation model employs the original U-ViT architecture, combining Diffusion and Transformer...
PuLID is an open-source personalized text-to-image generation technology developed by ByteDance. Through contrast alignment and fast sampling methods, it achieves efficient ID customization without adjusting the model, easily realizing image face-swapping effects.
IC-Light is an AI image lighting tool developed by Zhang Lvmin, the author of ControlNet. It allows for manipulation of light sources and reconstruction of light and shadow in images, achieving perfect integration with various backgrounds. Users simply upload their images, select the appropriate lighting...
AniTalker is an AI-powered lip-syncing video generation framework developed by researchers from the X-LANCE Lab at Shanghai Jiao Tong University and AISpeech. It can convert a single static image of a person and input audio into lifelike animation...
Hunyuan-DiT is a high-performance text-to-image diffusion Transformer model developed by Tencent's Hunyuan team. It possesses fine-grained Chinese and English understanding capabilities and can generate multi-resolution images based on text prompts...
Veo is a video generation model developed by Google DeepMind. Users can be guided to generate the desired video content using text, images, or video prompts. It can generate high-quality 1080p resolution videos longer than one minute...
CogVLM2 is a new generation of multimodal large-scale model launched by Zhipu AI. It has achieved significant performance improvements in visual and language understanding, supports text lengths of up to 8K and image inputs of 1344*1344 resolution, and has powerful text processing capabilities...
Universal-1 is a multilingual speech recognition and transcription model launched by AI speech startup AssemblyAI. It has been trained on more than 12.5 million hours of multilingual audio data and supports languages such as English, Spanish, French, and German.
Codestral is a code generation AI model launched by the French artificial intelligence startup Mistral AI. Designed to improve software development efficiency, it supports over 80 programming languages, including but not limited to Python, Java, C, C++, etc.
ChatTTS is a text-to-speech (TTS) model designed specifically for conversational scenarios, supporting both Chinese and English. It is trained on approximately 100,000 hours of Chinese and English data and can generate high-quality, natural, and fluent conversational speech.
Seed-TTS is a series of advanced text-to-speech (TTS) models developed by ByteDance. It can generate high-quality speech that is extremely similar to human speech and has excellent context learning ability and naturalness.