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
  ☆231Updated 5 months ago
• czg1225 / AsyncDiff
  [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
  ☆202Updated 4 months ago
• eai-lab / On-device-Sora
  [arXiv] On-device Sora: Enabling Diffusion-Based Text-to-Video Generation for Mobile Devices
  ☆116Updated 4 months ago
• Yaofang-Liu / Pusa-VidGen
  Pusa: Thousands Timesteps Video Diffusion Model
  ☆199Updated this week
• chengzeyi / ParaAttention
  https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching
  ☆300Updated last month
• lucidrains / MIMO-pytorch
  Pytorch implementation of MIMO, Controllable Character Video Synthesis with Spatial Decomposed Modeling, from Alibaba Intelligence Group
  ☆133Updated 8 months ago
• ByteDance-Seed / SeedVR
  Repo for SeedVR2 & SeedVR (CVPR2025 Highlight)
  ☆232Updated this week
• Huage001 / CLEAR
  Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".
  ☆206Updated 2 months ago
• sayakpaul / flux-image-editing
  Scripts to teach Flux the task of image editing from language with the Flux Control framework.
  ☆87Updated 3 months ago
• Vchitect / DCM
  DCM: Dual-Expert Consistency Model for Efficient and High-Quality Video Generation
  ☆160Updated 2 weeks ago
• AdaCache-DiT / AdaCache
  Adaptive Caching for Faster Video Generation with Diffusion Transformers
  ☆150Updated 7 months ago
• sayakpaul / tt-scale-flux
  Inference-time scaling of diffusion-based image and video generation models.
  ☆151Updated 3 months ago
• snap-research / BitsFusion
  ☆125Updated 3 months ago
• Yuanshi9815 / Video-Infinity
  Video-Infinity generates long videos quickly using multiple GPUs without extra training.
  ☆181Updated 10 months ago
• Huage001 / URAE
  [ICML 2025] Official PyTorch implementation of paper "Ultra-Resolution Adaptation with Ease".
  ☆98Updated last month
• TencentARC / FluxKits
  ☆90Updated 6 months ago
• sayakpaul / diffusers-torchao
  End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).
  ☆360Updated 3 weeks ago
• Vchitect / RepVideo
  The official implementation of ”RepVideo: Rethinking Cross-Layer Representation for Video Generation“
  ☆117Updated 4 months ago
• Huage001 / LinFusion
  Official PyTorch and Diffusers Implementation of "LinFusion: 1 GPU, 1 Minute, 16K Image"
  ☆302Updated 6 months ago
• ai-forever / Kandinsky-4
  Text and image to video generation: Kandinsky 4.0 (2024)
  ☆145Updated 6 months ago
• Alpha-VLLM / Lumina-Accessory
  ☆96Updated last month
• Shenyi-Z / TaylorSeer
  From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
  ☆179Updated last month
• ByteFlow-AI / DetailFlow
  🔥 Official impl. of "DetailFlow: 1D Coarse-to-Fine Autoregressive Image Generation via Next-Detail Prediction"
  ☆111Updated last week
• victorchall / genmoai-smol
  The best OSS video generation models
  ☆134Updated 8 months ago
• junhahyung / STGuidance
  ☆163Updated 2 months ago
• chenllliang / DreamEngine
  Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think!
  ☆113Updated 3 months ago
• CodeGoat24 / MagicFace
  Official implementation of MagicFace: Training-free Universal-Style Human Image Customized Synthesis.
  ☆63Updated 6 months ago
• Correr-Zhou / MagicTailor
  [IJCAI 2025] Offical implementation of the paper "MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models"…
  ☆87Updated last month
• microsoft / RAS
  An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…
  ☆130Updated 4 months ago
• dvlab-research / Jenga
  Official Implementation: Training-Free Efficient Video Generation via Dynamic Token Carving
  ☆203Updated last week