mit-han-lab / nunchaku
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
☆1,033Updated this week
Alternatives and similar repositories for nunchaku:
Users that are interested in nunchaku are comparing it to the libraries listed below
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆571Updated last week
- A pipeline parallel training script for diffusion models.☆765Updated this week
- Enhance-A-Video: Better Generated Video for Free☆483Updated last week
- ☆270Updated 2 months ago
- Context parallel attention that accelerates DiT model inference with dynamic caching☆228Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆394Updated last month
- 📹 A more flexible framework that can generate videos at any resolution and creates videos from images.☆680Updated this week
- ☆479Updated this week
- Memory-optimized training library for diffusion models☆995Updated 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…☆1,185Updated this week
- Nodes for image juxtaposition for Flux in ComfyUI☆1,184Updated 2 months ago
- FastVideo is a lightweight framework for accelerating large video diffusion models.☆1,264Updated this week
- ☆511Updated 2 months ago
- Training-free Regional Prompting for Diffusion Transformers 🔥☆591Updated 4 months ago
- ☆772Updated 4 months ago
- ☆636Updated 4 months ago
- ☆836Updated this week
- [WIP] The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.☆904Updated this week
- A minimal and universal controller for FLUX.1.☆1,328Updated 2 weeks ago
- A set of ComfyUI nodes providing additional control for the LTX Video model☆472Updated 3 weeks ago
- ☆584Updated this week
- [NeurIPS 2024] Boosting the performance of consistency models with PCM!☆447Updated 3 months ago
- Official repository of In-Context LoRA for Diffusion Transformers☆1,715Updated 3 months ago
- SpargeAttention: A training-free sparse attention that can accelerate any model inference.☆328Updated last week
- [ECCV 2024] HiDiffusion: Increases the resolution and speed of your diffusion model by only adding a single line of code!☆808Updated 3 months ago
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆670Updated 3 months ago
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆334Updated last month
- ☆1,445Updated last month
- A set of nodes to edit videos using the Hunyuan Video model☆420Updated last month
- (NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis☆728Updated 3 weeks ago