Alternatives and similar repositories for MagCache

Users that are interested in MagCache are comparing it to the libraries listed below

• bebebe666 / OptimalSteps
  Official PyTorch Implementation of "Optimal Stepsize for Diffusion Sampling".
  ☆191Updated 7 months ago
• GoatWu / CausVid-Plus
  Unofficial extension implementation of CausVid
  ☆65Updated 6 months ago
• ModelTC / Wan2.2-Lightning
  Wan2.2-Lightning: Speed up wan2.2 model with distillation
  ☆218Updated last week
• ChenDarYen / Normalized-Attention-Guidance
  Official implementation of "Normalized Attention Guidance"
  ☆171Updated 4 months ago
• Alpha-VLLM / Lumina-Accessory
  ☆111Updated 6 months ago
• madebyollin / taehv
  Tiny AutoEncoder for Hunyuan Video (and other video models)
  ☆217Updated last week
• spacepxl / WanTraining
  ☆87Updated 4 months ago
• Vchitect / FasterCache
  [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality
  ☆251Updated 10 months ago
• czg1225 / AsyncDiff
  [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
  ☆206Updated last month
• spacepxl / HunyuanVideo-Training
  ☆79Updated 8 months ago
• junhahyung / STGuidance
  ☆172Updated last month
• mit-han-lab / radial-attention
  [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation
  ☆553Updated this week
• aejion / AccVideo
  Official code for AccVideo: Accelerating Video Diffusion Model with Synthetic Dataset
  ☆267Updated 5 months ago
• fenfenfenfan / VMix
  Official code for VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Control
  ☆187Updated 10 months ago
• dc-ai-projects / DC-Gen
  DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
  ☆285Updated last month
• dvlab-research / Jenga
  [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving
  ☆253Updated 3 months ago
• Dashverse / hunyuan-video-keyframe-control-lora
  HunyuanVideo Keyframe Control Lora is an adapter for HunyuanVideo T2V model for keyframe-based video generation
  ☆165Updated 7 months ago
• eisneim / ltx_lora_training_i2v_t2v
  Lora traing script for Lightricks LTX-video
  ☆66Updated 9 months ago
• lodestone-rock / flow
  ☆164Updated 3 weeks ago
• Eyeline-Labs / CineScale
  Code for CineScale, higher-resolution video generation based on Wan
  ☆173Updated 2 months ago
• bytedance / UMO
  🔥🔥 Official Repo of UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward
  ☆165Updated 2 months ago
• GoatWu / Self-Forcing-Plus
  Unofficial extension implementation of Self-Forcing to support I2V && 14B training.
  ☆244Updated last month
• ModelTC / LightX2V
  Light Video Generation Inference Framework
  ☆789Updated this week
• ZulutionAI / MoviiGen1.1
  MoviiGen 1.1: Towards Cinematic-Quality Video Generative Models
  ☆179Updated 3 months ago
• Huage001 / URAE
  [ICML 2025] Official PyTorch implementation of paper "Ultra-Resolution Adaptation with Ease".
  ☆111Updated 6 months ago
• MAGREF-Video / MAGREF
  Official implementation of MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement
  ☆271Updated last month
• yandex-research / swd
  Scale-wise Distillation of Diffusion Models
  ☆112Updated 2 months ago
• D2I-ai / EchoShot
  ☆68Updated 3 months ago
• TheDenk / wan2.2-controlnet
  Controlnet module for Wan2.2
  ☆34Updated 2 weeks ago
• ignoww / RALU
  [arXiv 2025] Upsample What Matters: Region-Adaptive Latent Sampling for Accelerated Diffusion Transformers
  ☆48Updated 3 months ago