mit-han-lab / nunchaku
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
☆657Updated this week
Alternatives and similar repositories for nunchaku:
Users that are interested in nunchaku are comparing it to the libraries listed below
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆654Updated 2 months ago
- Context parallel attention that accelerates DiT model inference with dynamic caching☆178Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆326Updated this week
- Enhance-A-Video: Better Generated Video for Free☆328Updated this week
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆320Updated last month
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆352Updated 3 weeks ago
- [NeurIPS 2024] Boosting the performance of consistency models with PCM!☆431Updated 2 months ago
- Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x fast…☆244Updated 4 months ago
- ☆257Updated last month
- (NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis☆648Updated 3 weeks ago
- HART: Efficient Visual Generation with Hybrid Autoregressive Transformer☆416Updated 4 months ago
- Memory-optimized training scripts for video models based on Diffusers☆842Updated this week
- [ICLR 2025] Official Implementation of Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image…☆282Updated 2 months ago
- Official Implementation of "Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraini…☆541Updated 5 months ago
- A pipeline parallel training script for diffusion models.☆512Updated this week
- T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!☆381Updated 5 months ago
- Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation☆503Updated 4 months ago
- [CVPR 2024] DeepCache: Accelerating Diffusion Models for Free☆848Updated 7 months ago
- Training-free Regional Prompting for Diffusion Transformers 🔥☆551Updated 2 months ago
- FastVideo is a lightweight framework for accelerating large video diffusion models.☆993Updated this week
- ☆422Updated 2 months ago
- ⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation (AAAI 2025 Oral)☆540Updated 3 weeks ago
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆177Updated 4 months ago
- Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".☆194Updated this week
- Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossi…☆948Updated this week
- [ECCV 2024] HiDiffusion: Increases the resolution and speed of your diffusion model by only adding a single line of code!☆799Updated 2 months ago
- 📖A curated list of Awesome Diffusion Inference Papers with codes: Sampling, Caching, Multi-GPUs, etc. 🎉🎉☆187Updated last month
- Official implementation of OneDiffusion paper☆595Updated 2 months ago
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆194Updated last month
- text to image to generation: CogView3-Plus and CogView3(ECCV 2024)☆283Updated last month