Open-Sora: Democratizing Efficient Video Production for All

Official inference repo for FLUX.1 models

Contexts Optical Compression

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Janus-Series: Unified Multimodal Understanding and Generation Models

Wan: Open and Advanced Large-Scale Video Generative Models

Wan: Open and Advanced Large-Scale Video Generative Models

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...)…

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails

HunyuanVideo: A Systematic Framework For Large Video Generation Model

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…

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

DUSt3R: Geometric 3D Vision Made Easy

Open-source unified multimodal model

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

PyTorch code and models for V-JEPA self-supervised learning from video.

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive arch…

Advancing Open-source World Models

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

[ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

Official implementation of BLIP3o-Series

Official repository for BrickGPT, the first approach for generating physically stable toy brick models from text prompts.