Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
3,195
repos tracked
105
surfaced this week
193
created < 30d
Python
top language
36 repos
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
Multimodal RL training framework for diffusion & omni models
-
Official Code for "Video Diffusion Avatars: Taming Video Diffusion Models into Controllable 3D Avatars"
-
[NeurIPS 2024] Simple and Effective Masked Diffusion Language Model
-
📖 This is a repository for organizing papers, codes, and other resources related to Latent Reasoning.
-
Side-by-side DiffusionGemma and Gemma 4 FP8 demos, live diffusion previews, and profiling on two DGX Sparks
-
Official implementation of "Correction Training for Diffusion Models"
-
DiffusionGemma NVFP4 structured decisions on a DGX Spark: container recipe
-
DFMDock (Denoising Force Matching Dock), a diffusion model that unifies sampling and ranking within a single framework.
-
Sub-real-time MiniMax H3 on Hopper: 13.506 s for a 14.375 s 768p video with audio on 8xH100. Four runtime patches removing 9.72 s of non-model overhead from FastVideo.
-
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.
-
dInfer: An Efficient Inference Framework for Diffusion Language Models
-
[ICML'26] PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
-
Eden is building autonomous creative agents.
-
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
-
A Datacenter Scale Distributed Inference Serving Framework
-
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
-
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
-
Official implementation of ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation (SIGGRAPH 2026).
-
Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++
-
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM Computing Surveys, 2026.
-
Procedural terrain generation with diffusion models (in Minecraft)
-
[SIGGRAPH 2026] InfiniteDiffusion & Terrain Diffusion: Procedural generation with diffusion models
-
[ICLR 2026] This repository is the official implementation of "EasyTune: Efficient Reinforcement Fine-Tuning for Diffusion-Based Motion Generation".
-
[ICLR'26 & TPAMI‘26] This repository is the official implementation of "EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation" and its extended version "MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation"
-
World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.
-
DFlash: Block Diffusion for Flash Speculative Decoding
-
ABC: Scalable Behavior Cloning with Open Data, Training, and Evaluation
-
★ 107 Andy-Cheng/Flex4DHumanFlex4DHuman turns monocular or sparse multi-view videos of dynamic subjects into synchronized dense multi-view videos.
-
Code release for "i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models"
-
NVIDIA FastGen: Fast Generation from Diffusion Models
-
Lens is a 3.8B-parameter text-to-image diffusion model that achieves quality competitive with and in several cases surpassing models like FLUX and SD3, while requiring significantly less training compute. Key ideas include maximizing data information density per batch and accelerating convergence.
-
Repository for the CVPR 2026 paper MeshFlow Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer by Weiyu Li, Antoine Toisoul, Tom Monnier, Roman Shapovalov, Rakesh Ranjan, Ping Tan and Andrea Vedaldi.
-
[ICCV 2025 Oral] DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior