SUPIR is an open-source, text-guided AI model for high-fidelity image restoration, enhancing detail, clarity, and realism across photos, films, games, and archival imagery.
eSearch is a free, open-source desktop and web tool that captures screenshots, extracts text via OCR, searches the web, translates content, and performs reverse image search — all in one streamlined workflow.
EMO is an open-source audio-driven portrait video generator that creates expressive, lip-synced, and pose-aware talking or singing videos from a single image and any audio clip.
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.
F5-TTS is an open-source, high-performance text-to-speech tool that generates natural, expressive speech using flow matching and diffusion transformer models.
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.
EasyAnimate is an open-source, Transformer-based video generation framework that enables high-quality, customizable short video synthesis from text or images.
Clapper is an open-source AI video synthesis tool that lets users create videos through intuitive, high-level storytelling—no editing skills or AI engineering required.
CosyVoice 2.0 is an open-source, high-fidelity streaming text-to-speech model that delivers ultra-low-latency, multilingual, emotionally expressive, and speaker-controllable voice synthesis.
AtomoVideo is an open-source image-to-video framework that generates high-fidelity, temporally consistent videos from single input images using modular time-aware extensions to pretrained text-to-image models.
Swarm is an experimental, client-side educational framework for lightweight, customizable multi-agent orchestration—designed to help developers prototype agent workflows without server state or official production support.
JoyHallo is an open-source digital human model that generates high-fidelity, audio-driven talking-head videos in Mandarin and English using optimized semi-decoupled architecture.
Motionshop is an open-source framework that replaces real people in videos with expressive, lighting-aware 3D digital humans while preserving natural motion, timing, and visual continuity.
Mochi is an open-source, high-fidelity text-to-video model that generates smooth, physically plausible 480p videos with strong prompt adherence and efficient architecture.
LongCat is Meituan's general-purpose AI assistant app, backed by its own language, video and multimodal models for chat, search, reasoning and everyday tasks.
Qwen Image is an open-source 20B-parameter multimodal diffusion model for image generation and precise editing, with strong multilingual text rendering.
TigerBot is an open-source multilingual large language model family from TigerResearch, offering multi-task capability, search augmentation and domain-tuned variants.