Alternatives and similar repositories for mochi-xdit

Users that are interested in mochi-xdit are comparing it to the libraries listed below

• Vchitect / FasterCache
  [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality
  ☆255Updated 11 months ago
• huggingface / flux-fast
  Making Flux go brrr on GPUs.
  ☆158Updated 5 months ago
• Yuanshi9815 / Video-Infinity
  Video-Infinity generates long videos quickly using multiple GPUs without extra training.
  ☆189Updated last year
• eai-lab / On-device-Sora
  [arXiv] On-device Sora: Enabling Diffusion-Based Text-to-Video Generation for Mobile Devices
  ☆128Updated 3 weeks ago
• czg1225 / AsyncDiff
  [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
  ☆210Updated 2 months ago
• krea-ai / realtime-video
  Krea Realtime 14B. An open-source realtime AI video model.
  ☆431Updated last month
• dc-ai-projects / DC-Gen
  DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
  ☆313Updated 2 months ago
• sayakpaul / diffusers-torchao
  End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).
  ☆388Updated 6 months ago
• AdaCache-DiT / AdaCache
  Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"
  ☆163Updated last year
• ai-forever / Kandinsky-4
  Text and image to video generation: Kandinsky 4.0 (2024)
  ☆149Updated last year
• sayakpaul / tt-scale-flux
  Inference-time scaling of diffusion-based image and video generation models.
  ☆172Updated last week
• Huage001 / LinFusion
  Official PyTorch and Diffusers Implementation of "LinFusion: 1 GPU, 1 Minute, 16K Image"
  ☆311Updated last year
• Huage001 / CLEAR
  [NeurIPS 2025] Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".
  ☆212Updated 2 months ago
• Vchitect / DCM
  [ICCV2025] DCM: Dual-Expert Consistency Model for Efficient and High-Quality Video Generation
  ☆200Updated 6 months ago
• mit-han-lab / radial-attention
  [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation
  ☆565Updated last month
• AMD-AGI / Nitro-E
  ☆105Updated 2 weeks ago
• Vchitect / RepVideo
  The official implementation of ”RepVideo: Rethinking Cross-Layer Representation for Video Generation“
  ☆123Updated 11 months ago
• dvlab-research / Jenga
  [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving
  ☆259Updated 4 months ago
• Gengzigang / TokenSet
  Official PyTorch implementation of TokenSet.
  ☆127Updated 9 months ago
• chengzeyi / ParaAttention
  https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching
  ☆407Updated 5 months ago
• open-mmlab / Live2Diff
  Live2Diff: A Pipeline that processes Live video streams by a uni-directional video Diffusion model.
  ☆199Updated last year
• modelscope / DiffSynth-Engine
  ☆330Updated this week
• Diffusion-CoT / ReflectionFlow
  [ICCV 2025] Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning
  ☆208Updated last month
• victorchall / genmoai-smol
  The best OSS video generation models
  ☆135Updated last year
• madebyollin / taehv
  Tiny AutoEncoder for Hunyuan Video (and other video models)
  ☆255Updated last week
• sayakpaul / flux-image-editing
  Scripts to teach Flux the task of image editing from language with the Flux Control framework.
  ☆96Updated 5 months ago
• huggingface / video-dataset-scripts
  Collection of scripts to build small-scale datasets for fine-tuning video generation models.
  ☆75Updated 9 months ago
• Roblox / SmoothCache
  Implementation of SmoothCache, a project aimed at speeding-up Diffusion Transformer (DiT) based GenAI models with error-guided caching.
  ☆46Updated 5 months ago
• microsoft / RAS
  An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…
  ☆149Updated 6 months ago
• Zehong-Ma / MagCache
  The official code for NeurIPS 2025 "MagCache: Fast Video Generation with Magnitude-Aware Cache"
  ☆245Updated last month