Genmo AIGenmo is an AI research lab building open, state-of-the-art video generation models. Try Mochi 1, their cutting-edge text-to-video model, in the browser or run it locally for free.(0)0
M MagicDanceMagicDance uses identity-aware diffusion to transfer human poses and facial expressions onto any target in video — zero fine-tuning required. Open-source ICML 2024 research.(0)0
S SadTalker AISadTalker generates realistic talking head videos from a single portrait and audio clip using 3D motion coefficients. Open-source CVPR 2023 research tool.(0)0
A AIOZ-GDANCEAIOZ-GDANCE is a large-scale open-source dataset and AI model for generating coherent group dance choreographies from music, covering 7 dance styles and 16 music genres. Published at CVPR 2023.(0)0
DisCoDisCo is an open-source AI model that generates realistic human dance images and videos with disentangled control over subject appearance, background, and pose — enabling flexible, faithful, and compositional dance synthesis.(0)0
A AnimateDiffAnimateDiff is an open-source framework that injects a motion modeling module into personalized Stable Diffusion models to generate animated images from text prompts—no fine-tuning required.(0)0
M MiniGPT-4MiniGPT-4 aligns a visual encoder with the Vicuna LLM to deliver GPT-4-like multimodal capabilities including image description, website generation from sketches, and more.(0)0
OpenSoundscapeOpenSoundscape is a free, open-source Python library for bioacoustic data analysis, featuring CNN training, spectrogram tools, automated sound detection, and acoustic localization.(0)0
DanceVisionDanceVision uses MediaPipe pose estimation and machine learning to assess dance proficiency by analyzing body movements frame by frame from video input.(0)0
TopazTopaz is an open-source deep learning pipeline for automated particle picking and denoising in cryo-electron microscopy images using CNNs trained on positive-unlabeled examples.(0)0
