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.
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.
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.
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.
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.
LingHui is a web-based AI platform that transforms text scripts into fully animated short dramas — with auto-generated scenes, consistent characters, synchronized voiceovers, and multiple artistic styles — all in under three minutes.
Zhibiao Linghang is a Chinese AI assistant that automates bid document analysis, generation, and tender monitoring for procurement and corporate bidding workflows.
AGI-Eval is a collaborative, open evaluation platform for large language and foundation models, offering transparent benchmarks, human-in-the-loop testing, and community-built datasets.
AI Artist is a web-based Chinese AI painting tool that transforms simple text prompts into expressive artwork using intuitive controls and diverse artistic styles.
K2 is an open-source geoscience language model from Shanghai Jiao Tong University, further pretrained on earth science literature and fine-tuned with knowledge-intensive instruction data.
OrionStar's Orion-14B is an enterprise-focused large language model with 32K token context, quantization, and multilingual support for long-text processing.
Yayi is an enterprise large language model platform from Wenge, offering private deployment, domain knowledge Q&A, information extraction, and multimodal content generation.
孟子大模型 is Langboat's self-developed large pre-trained language model, built for multilingual, multimodal understanding and generation across industry use cases.
ModelBest (面壁智能) builds the CPM family of pretrained language models and the ModelForce platform for efficient training, fine-tuning, compression and inference.
VALL-E is a Microsoft Research text-to-speech model that uses discrete audio codes and in-context learning to synthesize personalized speech from short samples.