Alternatives and similar repositories for rectified-flow

Users that are interested in rectified-flow are comparing it to the libraries listed below

• Alpha-VLLM / Lumina-DiMOO
  Lumina-DiMOO - An Open-Sourced Multi-Modal Large Diffusion Language Model
  ☆872Updated last week
• Tencent-Hunyuan / MixGRPO
  MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
  ☆1,033Updated last month
• ckczzj / PDAE
  Official PyTorch implementation of PDAE (NeurIPS 2022)
  ☆219Updated last year
• EvolvingLMMs-Lab / lmms-engine
  A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.
  ☆476Updated this week
• TransDiff / TransDiff
  ☆142Updated 4 months ago
• jiaosiyu1999 / FlexVAR
  ☆119Updated 8 months ago
• PKU-YuanGroup / NeuralGS
  [AAAI 2026 🔥] Official implementation of "NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representation"
  ☆172Updated 3 months ago
• XueZeyue / DanceGRPO
  An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation
  ☆1,181Updated 3 weeks ago
• yuanze-lin / Learnable_Regions
  [CVPR 2024] Official code for "Text-Driven Image Editing via Learnable Regions"
  ☆226Updated last year
• JavisVerse / JavisDiT
  Official implementation of "JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization"
  ☆285Updated last month
• JetAstra / SDAR
  SDAR (Synergy of Diffusion and AutoRegression), a large diffusion language model（1.7B, 4B, 8B, 30B）
  ☆280Updated 3 weeks ago
• LiQiiiii / DLLM-Survey
  [Arxiv] Discrete Diffusion in Large Language and Multimodal Models: A Survey
  ☆333Updated 2 weeks ago
• 360CVGroup / Qihoo-T2X
  Efficient DiT architecture for text2any tasks, ICLR2025
  ☆450Updated 6 months ago
• sy77777en / CameraBench
  [NeurIPS 2025 Spotlight] Towards Understanding Camera Motions in Any Video
  ☆244Updated 3 weeks ago
• ZhengrongYue / UniFlow
  Official Implementation of "UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation"
  ☆123Updated 3 weeks ago
• 3DTopia / 4DNeX
  4DNeX: Feed-Forward 4D Generative Modeling Made Easy
  ☆785Updated last month
• WisconsinAIVision / YoChameleon
  🦎 Yo'Chameleon: Your Personalized Chameleon (CVPR 2025)
  ☆148Updated 6 months ago
• PKU-YuanGroup / DreamDance
  ☆73Updated 7 months ago
• Alpha-Innovator / AdaptiveDiffusion
  [NeurIPS'24] Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy
  ☆72Updated 9 months ago
• onecat-ai / OneCAT
  OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation
  ☆232Updated last month
• MingXiangL / DEVIL
  Evaluation of Text-to-Video Generation Models: A Dynamics Perspective[NeurIPS 2024].
  ☆276Updated 11 months ago
• jinjianRick / latexblend
  CVPR 2025 Highlight
  ☆37Updated 2 months ago
• alibaba / identity-grpo
  Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learning
  ☆152Updated 3 weeks ago
• AGI-Arena / MARS
  The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models
  ☆713Updated 2 weeks ago
• Alpha-VLLM / Lumina-Video
  ☆412Updated 8 months ago
• Friedrich-M / Instruct-4D-to-4D
  [CVPR2024] Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusion
  ☆134Updated last year
• JAMESYJL / ShapeLLM-Omni
  [NeurIPS 2025 Spotlight] A Native Multimodal LLM for 3D Generation and Understanding
  ☆498Updated 3 weeks ago
• yxymessi / DTC123
  The official PyTorch implementation of Diffusion Time-step Curriculum for One Image to 3D Generation (CVPR 2024)
  ☆74Updated last year
• 360CVGroup / WISA
  World Simulator Assistant for Physics-Aware Text-to-Video Generation
  ☆250Updated last month
• LiQiiiii / Neural-Ligand
  [ICCV‘25] Official implementation of paper "Towards Performance Consistency in Multi-Level Model Collaboration"
  ☆42Updated 3 weeks ago