Alternatives and similar repositories for Awesome-Generation-Acceleration

Users that are interested in Awesome-Generation-Acceleration are comparing it to the libraries listed below

• Shenyi-Z / ToCa
  [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching
  ☆173Updated 5 months ago
• Shenyi-Z / DuCa
  (ToCa-v2) A New version of ToCa，with faster speed and better acceleration!
  ☆39Updated 5 months ago
• svg-project / Sparse-VideoGen
  [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
  ☆417Updated this week
• thu-nics / DiTFastAttn
  ☆173Updated 7 months ago
• Shenyi-Z / TaylorSeer
  [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
  ☆269Updated 2 weeks ago
• lxa9867 / Awesome-Autoregressive-Visual-Generation
  This is a repo to track the latest autoregressive visual generation papers.
  ☆390Updated 2 months ago
• thu-nics / ViDiT-Q
  [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
  ☆115Updated 5 months ago
• ModelTC / TFMQ-DM
  [CVPR 2024 Highlight & TPAMI 2025] This is the official PyTorch implementation of "TFMQ-DM: Temporal Feature Maintenance Quantization for…
  ☆103Updated last month
• AdaCache-DiT / AdaCache
  Adaptive Caching for Faster Video Generation with Diffusion Transformers
  ☆156Updated 9 months ago
• ChaofanTao / Autoregressive-Models-in-Vision-Survey
  [TMLR 2025🔥] A survey for the autoregressive models in vision.
  ☆686Updated last week
• xlite-dev / Awesome-DiT-Inference
  📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉
  ☆380Updated last week
• XueZeyue / DanceGRPO
  An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation
  ☆637Updated this week
• horseee / learning-to-cache
  [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
  ☆111Updated last year
• thu-ml / SpargeAttn
  SpargeAttention: A training-free sparse attention that can accelerate any model inference.
  ☆695Updated 2 weeks ago
• xie-lab-ml / awesome-alignment-of-diffusion-models
  The collection of awesome papers on alignment of diffusion models.
  ☆324Updated last week
• VainF / TinyFusion
  [CVPR 2025 Highlight] TinyFusion: Diffusion Transformers Learned Shallow
  ☆137Updated 4 months ago
• CodeGoat24 / UnifiedReward
  Official implementation of UnifiedReward & UnifiedReward-Think
  ☆521Updated this week
• prathebaselva / FORA
  FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.
  ☆48Updated last year
• wdrink / SimpleAR
  Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"
  ☆397Updated 2 months ago
• baaivision / NOVA
  [ICLR 2025] Autoregressive Video Generation without Vector Quantization
  ☆564Updated 3 weeks ago
• feizc / DiT-MoE
  Scaling Diffusion Transformers with Mixture of Experts
  ☆365Updated 11 months ago
• NUS-HPC-AI-Lab / Dynamic-Diffusion-Transformer
  ☆84Updated 5 months ago
• AIoT-MLSys-Lab / Efficient-Diffusion-Model-Survey
  [TMLR 2025] Efficient Diffusion Models: A Survey
  ☆100Updated 2 months ago
• mit-han-lab / vila-u
  [ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
  ☆382Updated 4 months ago
• AIDC-AI / Awesome-Unified-Multimodal-Models
  Awesome Unified Multimodal Models
  ☆619Updated last week
• ByteVisionLab / TokenFlow
  [CVPR 2025] 🔥 Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".
  ☆373Updated 3 weeks ago
• microsoft / RAS
  An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…
  ☆138Updated 2 months ago
• A-suozhang / Awesome-Efficient-Diffusion
  Curated list of methods that focuses on improving the efficiency of diffusion models
  ☆46Updated last year
• JunyiWuCode / QuantCache
  ☆13Updated last month
• NVlabs / Fast-dLLM
  Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"
  ☆386Updated this week