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.
MotionCtrl is an open-source motion controller for video generation models that enables independent, precise control of camera movement and object motion in AI-generated videos.
MMMLU is a large-scale, multilingual, multitask benchmark dataset for rigorously evaluating language models across 14 languages and 57 academic disciplines.
PortraitGen is an open-source AI video editing tool that enables high-fidelity, temporally consistent editing of human portrait videos using 3D Gaussian splatting and neural texture modeling.
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.
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.
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.
Snap Video is a research-grade text-to-video generator developed by Snap Inc. that produces high-fidelity, motion-rich videos using a video-first transformer architecture and extended EDM framework.
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.
GameNGen is Google's experimental AI-powered game engine that generates playable video game frames in real time using neural networks—no traditional game code or rendering pipeline required.
EasyAnimate is an open-source, Transformer-based video generation framework that enables high-quality, customizable short video synthesis from text or images.
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.
DreaMoving is an open-source diffusion-based framework for highly controllable human video generation, enabling precise identity preservation, pose-driven motion, and text-guided visual styling.
EchoMimic is an open-source tool that creates lifelike digital human animations driven by audio and facial landmarks for expressive, multilingual talking avatars.
Fluid is a research-grade text-to-image autoregressive model that uses continuous tokens and randomized token ordering to generate high-fidelity, semantically aligned images.
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.
Seaweed APT is a breakthrough AI video generator that produces high-resolution, photorealistic 2-second videos in a single neural network evaluation—dramatically accelerating speed without sacrificing quality.
Zhibiao Linghang is a Chinese AI assistant that automates bid document analysis, generation, and tender monitoring for procurement and corporate bidding workflows.
Xinghuo Bid is an AI-powered proposal writing assistant by iFLYTEK that helps enterprises rapidly draft, verify, and optimize tender documents using domain-specific knowledge and large language models.