xdit-project / mochi-xditView external linksLinks
faster parallel inference of mochi-1 video generation model
☆125Feb 25, 2025Updated 11 months ago
Alternatives and similar repositories for mochi-xdit
Users that are interested in mochi-xdit are comparing it to the libraries listed below
Sorting:
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆18Nov 18, 2024Updated last year
- [IEEE/CVF CVPR'2022] "ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation", Duolikun Danier, Fan Zhang, David Bull☆13Oct 9, 2023Updated 2 years ago
- Benchmark tests supporting the TiledCUDA library.☆18Nov 19, 2024Updated last year
- The best OSS video generation models, created by Genmo☆3,595Nov 14, 2025Updated 3 months ago
- Music production for silent film clips.☆32Apr 30, 2025Updated 9 months ago
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆259Dec 27, 2024Updated last year
- A parallelism VAE avoids OOM for high resolution image generation☆85Aug 4, 2025Updated 6 months ago
- Open deep learning compiler stack for cpu, gpu and specialized accelerators☆19Updated this week
- A CUDA kernel for NHWC GroupNorm for PyTorch☆22Nov 15, 2024Updated last year
- ☆30Oct 7, 2024Updated last year
- DiT for VAE (and Video Generation)☆35Sep 2, 2024Updated last year
- ☆25Sep 19, 2023Updated 2 years ago
- Code repository for T2V-Turbo and T2V-Turbo-v2☆310Jan 31, 2025Updated last year
- Scalable and memory-optimized training of diffusion models☆1,335Jun 4, 2025Updated 8 months ago
- Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"☆166Nov 5, 2024Updated last year
- A unified inference and post-training framework for accelerated video generation.☆3,059Feb 7, 2026Updated last week
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆393Jan 8, 2026Updated last month
- Official repository for VQDM:Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization paper☆34Sep 17, 2024Updated last year
- Problem-Oriented Segmentation and Retrieval EMNLP 2024 Findings☆34Nov 12, 2024Updated last year
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆422Jul 5, 2025Updated 7 months ago
- HunyuanVideo: A Systematic Framework For Large Video Generation Model☆48Dec 14, 2024Updated last year
- ☆19Jul 31, 2024Updated last year
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 2025)☆45Sep 1, 2025Updated 5 months ago
- Let's finetune video generation models!☆539Sep 15, 2025Updated 5 months ago
- Recaption large (Web)Datasets with vllm and save the artifacts.☆52Nov 23, 2024Updated last year
- [WIP] Better (FP8) attention for Hopper☆32Feb 24, 2025Updated 11 months ago
- An implementation of PSGD Kron second-order optimizer for PyTorch☆98Jul 24, 2025Updated 6 months ago
- EDL composer can be used to create Edit Decision List. EDL, Edit Decision List, is a plain text format that describes a video sequence. …☆20Mar 4, 2023Updated 2 years ago
- vLLM performance dashboard☆41Apr 26, 2024Updated last year
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆56Jul 23, 2024Updated last year
- Text and image to video generation: Kandinsky 4.0 (2024)☆149Dec 17, 2024Updated last year
- [EMNLP'2025] "EasyRec: Simple yet Effective Language Model for Recommendation"☆137Nov 3, 2025Updated 3 months ago
- finetune your florence2 model easy☆21Jul 27, 2024Updated last year
- [CCS 2024] "BadMerging: Backdoor Attacks Against Model Merging": official code implementation.☆35Aug 22, 2024Updated last year
- ☆21Apr 29, 2024Updated last year
- Source code of our paper "PairDistill: Pairwise Relevance Distillation for Dense Retrieval", EMNLP 2024 Main.☆22Nov 28, 2024Updated last year
- Official implementation of "VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis"☆20Jan 26, 2025Updated last year
- Official implementation of "Self-Improving Video Generation"☆77Apr 25, 2025Updated 9 months ago