A curated collection of current and important research in Diffusion and Flow-based generative models. This repository compiles foundational concepts, groundbreaking papers, and practical applications in this rapidly evolving field—covering inference acceleration, model optimization, image editing, and personalized generation.
📌 Note: This collection is actively maintained with the most significant and up-to-date research in the field.
| Rating |
|---|
| ⭐⭐⭐⭐⭐ |
| ⭐⭐⭐⭐ |
| ⭐⭐⭐ |
| ⭐⭐ |
| ⭐ |
- Milestone Models
- Inference Acceleration
- Optimization
- Model Distillation
- Reinforcement Learning
- Flow Matching Concepts
- Image Editing
- Personalized - ID Preserving Image Generation
Seedream 4.0: Toward Next-generation Multimodal Image Generation ⭐⭐⭐⭐⭐
[Paper]
Qwen-Image ⭐⭐⭐⭐
[Paper]
[Project Page]
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer ⭐⭐⭐⭐⭐
[Paper]
[Project Page]
FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space ⭐⭐⭐⭐⭐
[Paper]
Timestep Embedding Tells: It’s Time to Cache for Video Diffusion Model ⭐⭐⭐⭐⭐
[Paper]
[Project Page]
MagCache: Fast Video Generation with Magnitude-Aware Cache ⭐⭐⭐⭐⭐
[Paper]
[Project Page]
Training-free Diffusion Acceleration with Bottleneck Sampling ⭐⭐⭐
[Paper]
[Project Page]
NAMI: Efficient Image Generation via Progressive Rectified Flow Transformers ⭐⭐
[Paper]
SVDQUANT: ABSORBING OUTLIERS BY LOW-RANK COMPONENTS FOR 4-BIT DIFFUSION MODELS ⭐⭐⭐⭐
[Paper]
From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers ⭐⭐⭐
[Paper]
[Project Page]
SAGEATTENTION: ACCURATE 8-BIT ATTENTION FOR PLUG-AND-PLAY INFERENCE ACCELERATION ⭐⭐⭐⭐
[Paper]
[Project Page]
SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization ⭐⭐⭐⭐
[Paper]
SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-bit Training ⭐⭐⭐⭐
[Paper]
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness ⭐⭐⭐⭐⭐
[Paper]
[Project Page]
FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning ⭐⭐⭐⭐⭐
[Paper]
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision ⭐⭐⭐⭐⭐
[Paper]
SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation ⭐⭐⭐
[Paper]
[Project Page]
One-step Diffusion with Distribution Matching Distillation ⭐⭐⭐⭐⭐
[Paper]
Improved Distribution Matching Distillation for Fast Image Synthesis ⭐⭐⭐⭐
[Paper]
DECOUPLED DMD: CFG AUGMENTATION AS THE SPEAR, DISTRIBUTION MATCHING AS THE SHIELD ⭐⭐⭐⭐⭐
[Paper]
[Project Page]
Distribution Matching Distillation Meets Reinforcement Learning ⭐⭐⭐⭐⭐
[Paper]
Distribution Matching Distillation Meets Reinforcement Learning ⭐⭐⭐⭐⭐
[Paper]
X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again ⭐⭐⭐⭐
[Paper]
Flow-GRPO: Training Flow Matching Models via Online RL ⭐⭐⭐⭐
[Paper]
[Project Page]
FLOW MATCHING FOR GENERATIVE MODELING ⭐⭐⭐⭐⭐
[Paper]
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer ⭐⭐⭐⭐⭐
[Paper]
[Project Page]
FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing ⭐
[Paper]
[Project Page]
FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models ⭐⭐
[Paper]
[Project Page]
HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer ⭐⭐⭐
[Paper]
[Project Page]
PuLID: Pure and Lightning ID Customization via Contrastive Alignment ⭐⭐⭐⭐
[Paper]
[Project Page]
InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity ⭐⭐⭐
[Paper]
[Project Page]
WithAnyone: Towards Controllable and ID-Consistent Image Generation ⭐⭐
[Project Page]
LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers ⭐⭐
[Paper]
[Project Page]
FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers ⭐⭐
[Paper]