From Vibe Coding to Agentic Engineering
GLM-5: From Vibe Coding to Agentic Engineering
Awesome multilingual OCR toolkits based on PaddlePaddle
Official inference repo for FLUX.1 models
Lets make video diffusion practical
Wan2.2: Open and Advanced Large-Scale Video Generative Model
Wan2.1: Open and Advanced Large-Scale Video Generative Model
New set of lightweight state-of-the-art, open foundation models
gpt-oss-120b and gpt-oss-20b are two open-weight language models
State-of-the-art TTS model under 25MB
GLM-4.5: Open-source LLM for intelligent agents by Z.ai
Official repository for LTX-Video
Advanced language and coding AI model
Qwen3.5 is the large language model series developed by Qwen team
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
Qwen2.5-VL is the multimodal large language model series
Official inference repo for FLUX.2 models
Agentic, Reasoning, and Coding (ARC) foundation models
Visual Causal Flow
A Family of Open Sourced Music Foundation Models
Open image model at the forefront of design
Recovering the Visual Space from Any Views
Text and image to video generation: CogVideoX and CogVideo
Qwen-Image is a powerful image generation foundation model
The Clay Foundation Model - An open source AI model and interface