DeepSeek Harness (DSH) Web
Wan2.2: Open and Advanced Large-Scale Video Generative Model
Open image model at the forefront of design
AI cognitive-enhancement Skills based on Anthropic's J-space
Continuous Autonomy for the AI SDK
Qwen-Image is a powerful image generation foundation model
Qwen-Image-Layered: Layered Decomposition for Inherent Editablity
Controllable & emotion-expressive zero-shot TTS
Plugin and skin collection for DeepSeek Harness (DSH) Web UI
Open-source framework for intelligent speech interaction
A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming
Renderer for the harmony response format to be used with gpt-oss
Foundation model for image generation
Achieving 3+ generation speedup on reasoning tasks
Bidirectional token-classification model for identifiable info
A Pragmatic VLA Foundation Model
Safety reasoning models built-upon gpt-oss
LLM-based Reinforcement Learning audio edit model
MOSS‑TTS Family open‑source speech and sound generation model
High-Fidelity and Controllable Generation of Textured 3D Assets
Advancing Open-source World Models
Real-time behaviour synthesis with MuJoCo, using Predictive Control
Latent Diffusion and Stable Diffusion Implementation
Let us control diffusion models
Code for "Image Generation from Scene Graphs", Johnson et al, CVPR 201