Stars
Qwen-Image-Layered: Layered Decomposition for Inherent Editablity
(SRA) No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves
Sharp Monocular View Synthesis in Less Than a Second
Official code implementation of "OmniPSD: Layered PSD Generation with Diffusion Transformer"
The official Pixel Streaming servers and frontend.
Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform
Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"
Efficient Triton Kernels for LLM Training
SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds
cuTile is a programming model for writing parallel kernels for NVIDIA GPUs
A framework for efficient model inference with omni-modality models
Flash Attention in ~100 lines of CUDA (forward pass only)
Official inference repo for FLUX.2 models
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation
A generative and self-guided robotic agent that endlessly propose and master new skills.
BEHAVIOR-1K: a platform for accelerating Embodied AI research. Join our Discord for support: https://discord.gg/bccR5vGFEx
GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 training.
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
Native Multimodal Models are World Learners