GOT-OCR2.0 is an open-source, multimodal OCR model that converts complex documents—including math, charts, music scores, and multilingual text—into editable Markdown or LaTeX with interactive region control and long-context understanding.
ScreenAgent is an open-source AI agent that observes real computer screens and autonomously performs complex desktop tasks using vision-language understanding and reinforcement learning.
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.
StarCoder 2 is an open-weight, high-performance large language model designed specifically for code generation, understanding, and interactive programming assistance across 600+ languages.
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.
HivisionIDPhotos is a lightweight, open-source AI tool that generates professional ID photos with automatic matting, background replacement, layout printing, and optional beautification — all running locally on CPU.
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.
MinerU is an open-source AI tool that intelligently extracts and structures text, formulas, tables, and images from PDFs into clean Markdown and JSON formats for developers and researchers.
MaskGCT is an open-source, multilingual text-to-speech model that delivers high-fidelity voice synthesis, real-time voice cloning, cross-lingual conversion, and fine-grained prosodic control.
RMBG is an open, high-precision AI model for removing image backgrounds using the novel BiRefNet architecture — optimized for complex scenes and commercial safety.
OpenVoice is an open-source, real-time voice cloning model that replicates speaker identity and style across languages—even without training data in the target language.
MoLiMan is a web-based AI platform that automates the full dynamic comic production pipeline — from script and character design to animated scenes, voice-synced editing, and multi-platform video publishing.
Shenbi Ma Liang is a web-based AI analytics platform that delivers real-time box office data, audience sentiment, and market trend insights to help film enthusiasts and professionals make data-informed decisions.
TagoMovie is a web-based AI platform that transforms novels and story ideas into publish-ready animated dramas and short videos — no technical skills required.
JuLingHui is a web-based AI platform that transforms story ideas into professionally structured short drama scripts and high-quality cinematic videos with automated scene parsing, prompt generation, and integrated video synthesis.
HuiMeng Workshop is a web-based AI platform for industrial-scale short drama creation, transforming scripts into animated videos with consistent characters, scenes, and cinematic motion.