FineVideo is a large-scale, open multimodal video dataset designed to advance AI models’ understanding of spatial-temporal scenes, emotions, narratives, and cross-modal relationships in video.
Vary-toy is a compact, open-source visual language model enabling document OCR, image description, visual question answering, and multimodal dialogue on consumer-grade hardware.
Lepton Search is an open-source, cloud-native platform for building and running conversational AI search applications powered by large language models and integrated search engines.
Follow Your Pose is an open research framework that generates highly controllable, temporally coherent videos from text prompts and user-specified human pose sequences.
OLMo is a fully open, high-performance language model framework offering transparent training data, reproducible code, and standardized evaluation tools for researchers and developers.
DiffusionGPT is an open-source, LLM-driven text-to-image system that intelligently selects and coordinates specialized diffusion models to generate high-fidelity images from diverse, complex prompts.
Llama 3.2 is Meta's open-weight multimodal model family optimized for edge devices, supporting vision-language understanding, on-device text generation, and customizable local deployment.
MMMLU is a large-scale, multilingual, multitask benchmark dataset for rigorously evaluating language models across 14 languages and 57 academic disciplines.
V-JEPA is an open-source, self-supervised video foundation model that learns visual representations by predicting masked frame features—enabling robust video understanding without labels.
OpenCodeInterpreter is an open-source AI coding assistant that generates, executes, and iteratively refines code using large language models and real-time execution feedback.
ChatMusician is an open-source large language model that understands and generates music using text-based notation—enabling composition, theory Q&A, and stylistic imitation without external multimodal components.
TextDiffuser-2 is an open-source text-to-image diffusion model that generates high-fidelity, resolution-flexible images from natural language descriptions.
OmniGen is an open-source unified diffusion model that handles text-to-image generation, image editing, subject-driven synthesis, visual conditioning, and even classic CV tasks—all within a single streamlined architecture.
I2VGen is an open-source image-to-video model by Alibaba DAMO Academy that transforms static images into high-resolution, temporally coherent videos using cascaded diffusion.
WiseFlow is an open-source AI workflow tool that automatically crawls, parses, classifies, and organizes web and social media content—including WeChat articles—using LLMs and statistical learning, all without GPU requirements.
OmniParser is a lightweight, open-source screen parsing module that converts UI screenshots into structured, actionable elements to boost visual-language model performance in GUI-based agent tasks.
Seed-VC is a zero-shot voice cloning model that converts speech to new voices without needing target speaker recordings, hosted as a free Hugging Face Space.
VideoDoodles is a free, web-based research prototype from Adobe Research that lets creators draw and animate hand-drawn elements directly onto videos using AI-powered scene-aware canvases.
RMBG is an open, high-precision AI model for removing image backgrounds using the novel BiRefNet architecture — optimized for complex scenes and commercial safety.
NotebookLlama is an open-source Meta project that automatically converts PDF documents into professionally narrated podcast episodes using LLaMA models and TTS synthesis.